[go: up one dir, main page]

CN118035733B - Bearing retainer service life detection method and device - Google Patents

Bearing retainer service life detection method and device Download PDF

Info

Publication number
CN118035733B
CN118035733B CN202410436894.2A CN202410436894A CN118035733B CN 118035733 B CN118035733 B CN 118035733B CN 202410436894 A CN202410436894 A CN 202410436894A CN 118035733 B CN118035733 B CN 118035733B
Authority
CN
China
Prior art keywords
vibration data
local range
noise
level value
points
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.)
Active
Application number
CN202410436894.2A
Other languages
Chinese (zh)
Other versions
CN118035733A (en
Inventor
汪兵
汪浩洋
汪永卫
姜俊华
孙汝修
吕仁中
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Linqing Zhongrui Machinery Technology Co ltd
Liaocheng Zhongrui Bearing Co ltd
Original Assignee
Linqing Zhongrui Machinery Technology Co ltd
Liaocheng Zhongrui Bearing Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Linqing Zhongrui Machinery Technology Co ltd, Liaocheng Zhongrui Bearing Co ltd filed Critical Linqing Zhongrui Machinery Technology Co ltd
Priority to CN202410436894.2A priority Critical patent/CN118035733B/en
Publication of CN118035733A publication Critical patent/CN118035733A/en
Application granted granted Critical
Publication of CN118035733B publication Critical patent/CN118035733B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00Testing of machine parts
    • G01M13/04Bearings
    • G01M13/045Acoustic or vibration analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2131Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/243Classification techniques relating to the number of classes
    • G06F18/2433Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The invention relates to the field of data processing, in particular to a service life detection method and device of a bearing retainer, wherein the method comprises the following steps: acquiring vibration data points of the bearing retainer in normal operation to generate a vibration data set; setting a filter window as a local range, and calculating the chaotic degree of the fluctuation frequency and the size of the data in the local range, so as to obtain the periodicity of the vibration data as a noise expression degree value; correcting the noise expression degree based on periodicity to obtain a significant noise expression degree value, and calculating an average value as a noise level value; performing self-adaptive filtering window on the noise level value to obtain a denoised vibration data set; and (3) carrying out vibration data analysis on the denoised vibration data set to obtain specific frequency components of the bearing retainer, thereby carrying out service life detection on the bearing retainer. According to the invention, effective denoising is performed by dynamically adjusting according to the local characteristics of the vibration data, and the detection efficiency is improved.

Description

Bearing retainer service life detection method and device
Technical Field
The present invention relates generally to the field of data processing. More particularly, the present invention relates to a life detection method and apparatus for a bearing cage.
Background
Bearing cage, which refers to a bearing part that partly encloses all or part of the rolling elements and moves therewith, serves to isolate the rolling elements and also generally guides and retains them in the bearing. The reliability and performance of the bearings is critical for all rotating machinery. Therefore, monitoring and maintaining the condition of the bearings, particularly the condition of the bearing cage, is important for preventing failures, extending the service life of the equipment, and reducing maintenance costs.
Conventional bearing inspection methods focus on periodic physical inspection or replacement of bearings, which methods typically rely on planned maintenance procedures, which may lead to premature replacement of bearings or sudden failure due to failure to discover the failure in time.
At present, life detection is performed on a bearing retainer based on sensor technology, data analysis and the internet of things, and in the detection process, when vibration data of the bearing retainer in the operation process are collected by utilizing a vibration sensor, noise appears in the vibration data due to the fact that the vibration sensor is subjected to electromagnetic interference, and electromagnetic interference possibly received at different moments can be different, namely the noise level of the vibration data can be different in different areas. However, the traditional filtering algorithm often uses neighborhood blocks with the same size to measure the similarity, which can cause that in the area with larger local variation of data or rich details, the larger blocks can not accurately reflect the local characteristics, so that the denoising effect is poor or the details are lost, thereby influencing the service life detection method and the efficiency of the device of the final bearing frame.
Disclosure of Invention
In order to solve one or more of the technical problems, the invention analyzes the noise level in a search window of a vibration data point NLM filtering algorithm, adapts the neighborhood block size of the data points when the similarity measurement is carried out, thereby carrying out accurate data denoising on vibration data and finally improving the efficiency of a bearing retainer service life detection method and device.
In a first aspect, a life detection method of a bearing holder includes: acquiring vibration data points of the bearing retainer in normal operation to generate a vibration data set; setting a filter window, and acquiring a target data point in the filter window as a central pointData point length as local range; obtaining an extreme point sequence of the vibration data point in the local range and a time sequence corresponding to the extreme point sequence by using a difference method in the local range; calculating the variance of the time interval corresponding to the adjacent extreme points in the local range to obtain the chaotic degree of the data fluctuation frequency, and calculating the variance of the difference value of the adjacent extreme points in the local range to obtain the chaotic degree of the data fluctuation; according to the degree of confusion of the data fluctuation frequency and the degree of confusion of the data fluctuation, the periodicity of the time sequence is obtained and used as a noise expression degree value; correcting the noise expression degree based on the periodicity of the time sequence to obtain a significant noise expression degree value; traversing the significant noise expression degree value of each vibration data in the local range, and calculating the average value of the significant noise expression degree values of all the vibration data in the local range as a noise level value in the local range; performing self-adaptive filtering window on the noise level value by using a denoising algorithm to obtain a denoised vibration data set; and (3) carrying out vibration data analysis on the denoised vibration data set to obtain specific frequency components of abrasion, crack or fracture of the bearing retainer, and carrying out service life detection on the bearing retainer by using a detection device.
In one embodiment, the noise performance level value satisfies the following relation:
In the method, in the process of the invention, Represents the/>Noise performance level value of each vibration data point,/>Representing a linear normalization function,/>Representing the variance of the time intervals corresponding to adjacent extreme points in the local range,/>Representing the variance of the differences between adjacent extremum points within the local range.
In one embodiment, the significance level value satisfies the following relationship:
In the method, in the process of the invention, Represents the/>Significant noise performance level value corrected by each vibration data point,/>Represents the/>Noise performance level value of each vibration data point,/>Representing the total number of reference points,/>Representing covariance function,/>Represents the local in-range/>Vibration data points,/>Represents the/>The vibration data corresponds to the first/>, in the local rangeReference points/>Representing an exponential function.
In one embodiment, the noise level value satisfies the following relationship:
In the method, in the process of the invention, Noise performance level value representing vibration data points in local range,/>Representing the number of vibration data points in a local range,/>Represents the/>The vibration data points correspond to the first/>, within the local rangeVibration data points.
In one embodiment, the adaptive filtering window is performed on the noise level value using a denoising algorithm, comprising the steps of:
A non-local mean value filtering algorithm is used for the noise level value, a field block with similar local range corresponding to the target data point is obtained, and pixel difference between two adjacent blocks is calculated to obtain a similar value, wherein the field block is a local area in an image;
The noise level in the local range is self-adaptive to the size of the neighborhood block, the size of the filtering window is enlarged in response to the high noise level value, and the filtering window is reduced in response to the low noise level value;
in one embodiment, the size of the adaptive filter window satisfies the following relationship:
In the method, in the process of the invention, Neighborhood block size representing target data points within a local range,/>Representing a reference neighborhood block size,Noise performance level value representing vibration data points in local range,/>As a round-up function.
In a second aspect, the present invention provides a life detection device for a bearing holder, comprising: the device comprises a processor and a memory, wherein the memory stores computer program instructions which when executed by the processor realize the service life detection method of the bearing retainer.
The invention has the following effects:
1. According to the invention, by analyzing the noise levels of different areas and carrying out self-adaptive neighborhood block sizes when using an NLM filtering algorithm based on noise level values, dynamic adjustment is effectively carried out according to local characteristics of vibration data, smaller neighborhood blocks are used for areas with rich details, and larger neighborhood blocks are used for flat areas, so that details and quality of original signals or images are reserved to the greatest extent while denoising is carried out.
2. The invention provides a more flexible and effective denoising method through a self-adaptive neighborhood block size method, which is favorable for dynamic adjustment according to the local characteristics of vibration data, thereby improving the denoising effect of an NLM filtering algorithm on the vibration data and further improving the efficiency of a life detection method and device of a bearing retainer.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
fig. 1 is a flowchart of a method of step S1 to step S9 in a life detection method of a bearing cage according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method of detecting a life of a bearing holder according to an embodiment of the present invention, from step S80 to step S81.
Fig. 3 is a block diagram showing a life detection device for a bearing holder according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a method for detecting the life of a bearing cage includes steps S1 to S7, specifically as follows:
s1: vibration data points of the bearing retainer during normal operation are acquired, and a vibration data set is generated.
Further to the description, in this embodiment, the vibration sensor is installed at the bearing accessory, obtains the vibration data of the bearing retainer in the operation process of the equipment, and the acquisition frequency is 50HZ, obtains the vibration data of 1 minute that gathers.
S2: setting a filter window, and acquiring a target data point in the filter window as a central pointData point length as local range.
Further, when vibration data is collected, electromagnetic interference to which the vibration sensor is subjected at different moments may be different, which may cause different noise levels to be received at different areas in the vibration data; when denoising is performed based on a filtering algorithm, an NLM (Non-Local mean filtering) algorithm is adopted in the embodiment, and the basic principle is that for each vibration data point, other data points similar to the vibration data point in the data set are searched, and the weighted average value of the similar points is used for replacing the original data point, so that the denoising effect is achieved. The unified neighborhood block size of the data with different noise levels may cause loss of detail information of the data or reduction of noise suppression capability, so as to set a filtering window and denoise a local area.
In this embodiment, the search window of the NLM algorithm is set to be centered on the current filtering pointData point length (empirical/>,/>Odd), wherein the two data points are not enough to be truncated. The size of the neighborhood block in each search window is self-adaptive through the noise performance level in the search window, one data point corresponds to one search window, and one search window corresponds to one neighborhood block size, so that the neighborhood block size in each search window, namely, the neighborhood block size is self-adaptive to each data point.
S3: and obtaining an extreme point sequence of the vibration data point in the local range and a time sequence corresponding to the extreme point sequence by using a difference method in the local range.
Further, in the present embodiment, the difference method is a method commonly used for extracting local features from time series, wherein the extreme point sequence represents a local maximum or minimum in the vibration data point sequence, and the corresponding time series is the time corresponding to the extreme points.
S4: and calculating the variance of the time interval corresponding to the adjacent extreme points in the local range to obtain the chaotic degree of the data fluctuation frequency, and calculating the variance of the difference value of the adjacent extreme points in the local range to obtain the chaotic degree of the data fluctuation.
Further, in normal operation, the vibration signal may exhibit periodic fluctuations corresponding to the relative movement of the bearing elements (e.g., rolling elements, cage, inner race, and outer race) and their contact points. Bearings are designed for high speed rotating equipment, whose vibration signals may exhibit relatively high frequency but low amplitude fluctuations. The periodicity of the vibration data points can thus be used to reflect its noise performance level, which is lower if the vibration data points are more periodic in their local extent.
S5: and obtaining the periodicity of the time sequence as a noise expression level value according to the chaotic degree of the data fluctuation frequency and the chaotic degree of the data fluctuation.
The noise performance level value satisfies the following relation:
In the method, in the process of the invention, Represents the/>Noise performance level value of each vibration data point,/>Representing a linear normalization function,/>Representing the variance of the time intervals corresponding to adjacent extreme points in the local range,/>Representing the variance of the differences between adjacent extremum points within the local range.
Further, the periodicity of the vibration data points can be expressed by the degree of confusion of the data fluctuation frequency and the degree of confusion of the data fluctuation size in the local range, and the better the degree of confusion is, the worse the periodicity is, and the higher the noise expression degree is. The degree of confusion of the data fluctuation frequency can be calculated by using the variance of the time intervals of adjacent extreme points in the local range of the data point, and the larger the variance is, the more inconsistent the time intervals of the adjacent extreme points are, namely the larger the degree of confusion of the data fluctuation frequency is; the degree of confusion of the magnitude of the data fluctuation can be represented by the variance of the difference values of the adjacent extreme points in the local range, and the larger the variance is, the more inconsistent the difference values of the adjacent extreme points are, and the larger the degree of confusion of the magnitude of the data fluctuation is.
S6: and correcting the noise expression degree based on the periodicity of the time sequence to obtain a significant noise expression degree value.
The significance level value satisfies the following relationship:
In the method, in the process of the invention, Represents the/>Significant noise performance level value corrected by each vibration data point,/>Represents the/>Noise performance level value of each vibration data point,/>Representing the total number of reference points,/>Representing covariance function,/>Represents the local in-range/>Vibration data points,/>Represents the/>The vibration data corresponds to the first/>, in the local rangeReference points/>Representing an exponential function.
Further, in the present embodiment,Representation of/>Reference points and vibration data pointsThe covariance mean value of the local range represents the regularity of the repeated occurrence of the current vibration data point on time sequence; the correction factor of the noise expression degree is/>
Since the rotational speed of the mechanical device is known, the time taken for one revolution of the bearing cage (referred to as the interval time) The similarity between the local range corresponding to the data points at every other interval in all the acquired vibration data sequences and the local range of the current vibration data points represents the regularity of repeated occurrence in time sequence, and the higher the similarity is, the higher the regularity is.
That is, the current vibration data point local range is 3 data points on the left and 5 data points on the right, and then the corresponding data points at other intervals have a window size of 11 vibration data points, but in order to keep the same with the current vibration data point local range, the left 3 data points and the right 5 data points are also taken.
For vibration data pointsFind its nearest/>, to the vibration data sequencePersonal (empirical value/>)The local range of 100 vibration data points can be matched with the current vibration data point/>Consistent local range distribution) distanceInterval time with a time length of integer times/>For/>, as a reference pointCalculating the local range and the current vibration data point/>, by using the reference pointsMean value of covariance of data points in local range, used for representing similarity degree of variation trend of two vibration data points,/>, andThe mean value of the covariance indicates the regularity of the current vibration data point repeatedly appearing in time sequence, and the larger the mean value of the covariance is, the higher the regularity is.
S7: and traversing the significant noise expression degree value of each vibration data in the local range, and calculating the average value of the significant noise expression degree values of all the vibration data in the local range as the noise level value in the local range.
The noise level value satisfies the following relation:
In the method, in the process of the invention, Noise performance level value representing vibration data points in local range,/>Representing the number of vibration data points in a local range,/>Represents the/>The vibration data points correspond to the first/>, within the local rangeVibration data points.
Further, the mean of the noise performance levels of all vibration data points in the local range is used as the noise performance level of the filtering window.
S8: and carrying out self-adaptive filtering window on the noise level value by using a denoising algorithm to obtain a denoised vibration data set.
Referring to fig. 2, step S80-step S81 are included:
S80: a non-local mean filtering algorithm is used for the noise level value, a field block with similar local range corresponding to the target data point is obtained, and pixel difference between two adjacent blocks is calculated to obtain a similar value, wherein the field block is a local area in an image;
s81: the noise level in the local range is self-adaptive to the size of the neighborhood block, the size of the filtering window is enlarged in response to the high noise level value, and the filtering window is reduced in response to the low noise level value;
The size of the adaptive filter window satisfies the following relationship:
In the method, in the process of the invention, Neighborhood block size representing target data points within a local range,/>Representing a reference neighborhood block size,Noise performance level value representing vibration data points in local range,/>As a round-up function.
Further, according to the noise level of vibration data in the local range, a proper neighborhood block is selected to improve the denoising effect, and under the condition of higher noise level, a larger neighborhood quickly contains more data points, so that noise can be restrained by averaging more information of similar points; under the condition of low noise level, a smaller neighborhood is enough for effective denoising, and meanwhile, the detail and structural information of the data are better reserved; therefore, the size of the field block is self-adapted, and the NLM filtering algorithm is carried out to denoise vibration data of the bearing retainer.
In the present embodiment, empirical valuesWherein/>The value is a smaller value, and the scheme is only adjusted upwards.
S9: and (3) carrying out vibration data analysis on the denoised vibration data set to obtain specific frequency components of abrasion, crack or fracture of the bearing retainer, and carrying out service life detection on the bearing retainer by using a detection device.
The invention also provides a service life detection device of the bearing retainer, which comprises the following components: a processor and a memory storing computer program instructions which, when executed by the processor, implement a method of life detection of a bearing cage according to the first aspect of the invention.
The system further comprises other components known to those skilled in the art, such as communication buses and communication interfaces, the arrangement and function of which are known in the art and therefore will not be described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (ENHANCED DYNAMIC Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), or the like, or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.

Claims (7)

1. A life detection method of a bearing holder, comprising:
Acquiring vibration data points of the bearing retainer in normal operation to generate a vibration data set;
setting a filter window, and acquiring a target data point in the filter window as a central point Data point length as local range;
Obtaining an extreme point sequence of the vibration data point in the local range and a time sequence corresponding to the extreme point sequence by using a difference method in the local range;
Calculating the variance of the time interval corresponding to the adjacent extreme points in the local range to obtain the chaotic degree of the data fluctuation frequency, and calculating the variance of the difference value of the adjacent extreme points in the local range to obtain the chaotic degree of the data fluctuation;
According to the degree of confusion of the data fluctuation frequency and the degree of confusion of the data fluctuation, the periodicity of the time sequence is obtained and used as a noise expression degree value;
correcting the noise expression degree based on the periodicity of the time sequence to obtain a significant noise expression degree value;
Traversing the significant noise expression degree value of each vibration data in the local range, and calculating the average value of the significant noise expression degree values of all the vibration data in the local range as a noise level value in the local range;
performing self-adaptive filtering window on the noise level value by using a denoising algorithm to obtain a denoised vibration data set;
And (3) carrying out vibration data analysis on the denoised vibration data set to obtain specific frequency components of abrasion, crack or fracture of the bearing retainer, and carrying out service life detection on the bearing retainer by using a detection device.
2. The life detection method of a bearing holder according to claim 1, wherein the noise performance level value satisfies the following relation:
In the method, in the process of the invention, Represents the/>Noise performance level value of each vibration data point,/>Representing a linear normalization function,/>Representing the variance of the time intervals corresponding to adjacent extreme points in the local range,/>Representing the variance of the differences between adjacent extremum points within the local range.
3. The life detection method of a bearing retainer according to claim 1, wherein the significance level value satisfies the following relation:
In the method, in the process of the invention, Represents the/>Significant noise performance level value corrected by each vibration data point,/>Represents the/>Noise performance level value of each vibration data point,/>Representing the total number of reference points,/>Representing covariance function,/>Represents the local in-range/>Vibration data points,/>Represents the/>The vibration data corresponds to the first/>, in the local rangeReference points/>Representing an exponential function.
4. The life detection method of a bearing holder according to claim 1, wherein the noise level value satisfies the following relation:
In the method, in the process of the invention, Noise performance level value representing vibration data points in local range,/>Representing the number of vibration data points in a local range,/>Represents the/>The vibration data points correspond to the first/>, within the local rangeVibration data points.
5. The method for detecting the life of a bearing cage according to claim 1, wherein the noise level value is subjected to an adaptive filter window using a denoising algorithm, comprising the steps of:
A non-local mean value filtering algorithm is used for the noise level value, a field block with similar local range corresponding to the target data point is obtained, and pixel difference between two adjacent blocks is calculated to obtain a similar value, wherein the field block is a local area in an image;
the noise level in the local range adapts to the neighborhood block size, and in response to a high noise level value, the filter window size is enlarged, and in response to a low noise level value, the filter window is reduced.
6. The method for detecting the life of a bearing cage according to claim 5, wherein the size of the adaptive filter window satisfies the following relation:
In the method, in the process of the invention, Neighborhood block size representing target data points within a local range,/>Representing a reference neighborhood block size,/>Noise performance level value representing vibration data points in local range,/>As a round-up function.
7. A life detection device for a bearing holder, comprising: a processor and a memory storing computer program instructions which, when executed by the processor, implement a method of life detection of a bearing cage according to any one of claims 1-6.
CN202410436894.2A 2024-04-12 2024-04-12 Bearing retainer service life detection method and device Active CN118035733B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410436894.2A CN118035733B (en) 2024-04-12 2024-04-12 Bearing retainer service life detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410436894.2A CN118035733B (en) 2024-04-12 2024-04-12 Bearing retainer service life detection method and device

Publications (2)

Publication Number Publication Date
CN118035733A CN118035733A (en) 2024-05-14
CN118035733B true CN118035733B (en) 2024-06-18

Family

ID=90997134

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410436894.2A Active CN118035733B (en) 2024-04-12 2024-04-12 Bearing retainer service life detection method and device

Country Status (1)

Country Link
CN (1) CN118035733B (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118133053B (en) * 2024-05-08 2024-07-09 山东瑞福锂业有限公司 Industrial data collecting and processing system and method
CN118294145B (en) * 2024-06-05 2024-08-20 聊城市中瑞轴承配件股份有限公司 Bearing fault prediction method and system
CN118349786B (en) * 2024-06-14 2024-08-20 东华理工大学南昌校区 Uranium ore model construction method oriented to extrusion background
CN118333284B (en) * 2024-06-14 2024-09-06 国网山东省电力公司泰安供电公司 Method and system for processing transformer area voltage monitoring data based on electrical parameter analysis
CN118329196B (en) * 2024-06-17 2024-09-03 济南红太阳数控设备有限公司 Cutter vibration signal detection method of vibrating cutter cutting machine
CN118377777B (en) * 2024-06-20 2024-09-24 无锡东雄重型电炉有限公司 Method and system for acquiring process data in steelmaking process
CN118646449A (en) * 2024-08-15 2024-09-13 国网辽宁省电力有限公司盘锦供电公司 A data feature extraction method and system for HPLC broadband carrier
CN118656766B (en) * 2024-08-20 2024-11-19 国网辽宁省电力有限公司盘锦供电公司 Data collection method and system based on power collection terminal
CN118885946B (en) * 2024-09-29 2025-04-11 广州威德玛环境仪器有限公司 Test equipment life analysis method and system based on big data
CN119046620B (en) * 2024-10-28 2025-01-28 广州市凯捷电源实业有限公司 On-line monitoring method and system for running state of battery shell airtight detection equipment
CN119023066B (en) * 2024-10-29 2025-02-07 武汉精隧科技有限公司 Reinforced steel ring vibration data monitoring method and system for subway tunnel

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0574969A2 (en) * 1992-06-19 1993-12-22 Agfa-Gevaert N.V. A method and apparatus for noise reduction
CN115984148A (en) * 2023-03-21 2023-04-18 吉林华瑞基因科技有限公司 Denoising enhancement method for high-throughput gene sequencing data

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110595602B (en) * 2019-04-26 2021-10-15 深圳市豪视智能科技有限公司 Vibration detection method and related products
CN110377984B (en) * 2019-07-02 2023-08-18 中国科学院深圳先进技术研究院 Industrial equipment residual effective life prediction method and system and electronic equipment

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0574969A2 (en) * 1992-06-19 1993-12-22 Agfa-Gevaert N.V. A method and apparatus for noise reduction
CN115984148A (en) * 2023-03-21 2023-04-18 吉林华瑞基因科技有限公司 Denoising enhancement method for high-throughput gene sequencing data

Also Published As

Publication number Publication date
CN118035733A (en) 2024-05-14

Similar Documents

Publication Publication Date Title
CN118035733B (en) Bearing retainer service life detection method and device
CN115829883B (en) Surface image denoising method for special-shaped metal structural member
CN117272210A (en) Method and system for detecting abnormal hidden danger data of building construction
CN111582054B (en) Point cloud data processing method and device and obstacle detection method and device
CN114638827B (en) Visual detection method and device for impurities of lubricating oil machinery
US20110153270A1 (en) Outlier processing
CN111783583B (en) SAR image speckle suppression method based on non-local mean algorithm
CN118552549B (en) A transmission shaft component defect detection method and system based on image processing
CN118037726B (en) Railway accessory defect detection method and system
CN118795203B (en) Large-current test data processing method and system for explosion-proof electric appliance
CN119475273B (en) A method and system for real-time monitoring of yarn conveying operation status
CN118329197B (en) Abnormality monitoring method and system for printing plate roller
CN113610041A (en) Reading identification method and device for pointer instrument
CN114565000A (en) Method and device for determining faults of ball bearing and storage medium
CN117743836A (en) Abnormal vibration monitoring method for bearing
CN109978855A (en) A kind of method for detecting change of remote sensing image and device
CN110333078A (en) A Method for Determining Degradation State Stages of Rolling Bearings
CN118656766B (en) Data collection method and system based on power collection terminal
CN119359708A (en) Goat milk powder quality visual inspection method and system
JP2011013214A (en) Probabilistic determination method of time interval between periodic events disturbing signal
CN115781408B (en) Regulation and control system for inhibiting temperature rise of electric spindle of machine tool
Xu et al. Improved depth-wise separable convolution for transfer learning in fault diagnosis
CN120235860B (en) Intelligent recognition method for surface cracks in radiator vibration test
CN110927726A (en) Approach detection method and module
CN119848612B (en) A chemical equipment safety monitoring method and system based on artificial intelligence

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