CN111291466B - Analysis method and system for bearing fatigue life influence factors - Google Patents
Analysis method and system for bearing fatigue life influence factors Download PDFInfo
- Publication number
- CN111291466B CN111291466B CN202010028584.9A CN202010028584A CN111291466B CN 111291466 B CN111291466 B CN 111291466B CN 202010028584 A CN202010028584 A CN 202010028584A CN 111291466 B CN111291466 B CN 111291466B
- Authority
- CN
- China
- Prior art keywords
- bearing
- data
- class
- multiplied
- fatigue life
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a method and a system for analyzing bearing fatigue life influencing factors, comprising the following steps: s1: collecting data of a period of the bearing; s2: bearing data are imported into a VAE network model, and bearing data of different large-class influence factors are obtained; s3: and importing the bearing data in the major-class influence factors into an SVM classification model, performing multi-classification processing, and obtaining the influence degree of different minor-class influence factors under different major-class influence factors on the fatigue life of the bearing so as to adjust the use scheme of the bearing by using the influence degree. The invention has novel design and simple mode, and can be suitable for analyzing the fatigue life of most bearings so as to process influencing factors.
Description
Technical Field
The invention relates to the field of bearing life analysis, in particular to a method and a system for analyzing bearing fatigue life influencing factors.
Background
With the development of industrial technology, the application range of the bearing is also wider, and under some conditions, such as high temperature, high speed, heavy load and the like, the bearing performance needs to be optimized. Further, the automobile hub bearing is used as one of key parts of an automobile, so that the running stability, comfort and safety of the automobile are guaranteed, and once the automobile fails, the parts are abnormal, the automobile fails, the automobile cannot run normally, the service life is reduced, the safety performance is reduced and the like.
In practical application, the automobile hub bearing has a serious failure phenomenon. However, the failure of the automobile hub bearing is caused by a plurality of factors in the manufacturing process, such as material smelting, heat treatment, assembly and the like, and external factors such as service environment, lubrication and the like. In general, failure modes of the automobile hub bearing mainly comprise raceway surface fatigue failure, sealing performance failure, flange bending fatigue fracture and the like.
Therefore, the analysis of the service life of the bearing is very important, so that the abrasion or damage of the automobile hub bearing can be reduced or avoided to a certain extent, the probability of failure of the automobile in the driving way is reduced, the safety coefficient is improved, the development technology of the hub bearing can be further perfected, and the development of the automobile bearing is promoted.
In the process of analyzing the service life of the automobile hub bearing, the influence factors of the service life of the bearing are more, the analysis time is longer, and each influence parameter is difficult to accurately determine, so that a simple and effective analysis method for the influence factors of the fatigue service life of the bearing is necessary to design, the research and development cost can be reduced, and the manpower and material resources are saved.
Disclosure of Invention
The application provides a method and a system for analyzing influence factors of fatigue life of a bearing, which are used for solving the problems that in the prior art, because the influence factors of the fatigue life of the bearing are more, the analysis time is long, and each influence parameter is difficult to accurately determine.
In order to achieve the above purpose, the present invention is realized by the following technical scheme:
the invention provides a method for analyzing bearing fatigue life influencing factors, which comprises the following steps:
s1: collecting data of a period of the bearing;
s2: bearing data are imported into a VAE network model, and bearing data of different large-class influence factors are obtained;
s3: and importing the bearing data in the major-class influence factors into an SVM classification model, performing multi-classification processing, and obtaining the influence degree of different minor-class influence factors under different major-class influence factors on the fatigue life of the bearing so as to adjust the use scheme of the bearing by using the influence degree.
In one embodiment, the step S2 further comprises data preprocessing the bearing data.
In one embodiment, the method of preprocessing the bearing data includes: and (3) performing data cleaning on the collected bearing data by using the Python language, a NumPy module and a Pandas module thereof, wherein the data cleaning comprises the processing of abnormal values and missing values.
In one embodiment, in the step S2, importing the bearing data into a VAE network model includes performing a data normalization process on the bearing data after the preprocessing.
In one embodiment, the method for normalizing data includes compressing the preprocessed bearing data to a [0,1] interval using a formula x= (x-min)/(max-min), where x is the preprocessed bearing data, min is a data minimum, max is a data maximum, and max-min is a very bad.
In one embodiment, in the step S2, the bearing data is imported into a VAE network model, and the bearing data of different major influencing factors is obtained, which further includes:
s21: performing matrix transformation on the bearing data by utilizing a reshape function to obtain matrix data of m rows and n columns, namely an m multiplied by n matrix;
s22: the m multiplied by n matrix is led into the VAE network model in batches for training, and the training is iterated for a plurality of times;
s23: after training, importing all the trained array data into a VAE network model, extracting hidden space features, reducing the array data step by step, and reducing the array data to s dimension;
s24: clustering all s-dimensional array data by using a k-means algorithm to form t-class array data, wherein t is the type of the screened large-class influence factors, and the class center vector is t multiplied by s;
s25: inputting the class center vector t multiplied by s into a decoder of the VAE network model for decoding to obtain t multiplied by m multiplied by n;
s26: and (3) performing matrix reduction processing on the t multiplied by m multiplied by n by utilizing a reshape function, and extracting the corresponding bearing data of the t-class influence factors.
In one embodiment, in the step S3, the multi-classification processing of the bearing data by the SVM classification model is implemented by calling a libSVM toolbox.
In one embodiment, the large group of influencing factors includes, but is not limited to, materials, heat treatment, lubrication, service environment, bearing structure design.
The invention provides an analysis system of bearing fatigue life influencing factors, which comprises:
the device comprises a collection module, a preprocessing module, a major-class influence factor processing module and a minor-class influence factor processing module,
the collecting module is used for collecting data in a period of the bearing;
the preprocessing module is used for preprocessing the bearing data;
the large-class influence factor processing module is used for importing bearing data into a VAE network model to obtain the bearing data of different large-class influence factors;
the minor influence factor processing module is used for importing the bearing data in the major influence factors into an SVM classification model, performing multi-classification processing, and obtaining the influence degree of different minor influence factors under different major influence factors on the fatigue life of the bearing so as to adjust the use scheme of the bearing by using the influence degree.
The invention provides a computer device which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the analysis method for bearing fatigue life influencing factors.
The present invention provides a storage medium storing computer readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the method of analyzing bearing fatigue life influencing factors described above.
Compared with the prior art, the invention has the advantages that:
the processing method of the fatigue life influence factors is used for bearing fatigue life theoretical analysis, saves test cost, is strict in theory and simple in steps, can replace life influence factor inspection experiments with high cost in actual production, is novel in design, can be used for carrying out corresponding influence factor processing and bearing fatigue life analysis on the bearing fatigue life, and can be applied to theoretical life analysis of various automobile bearings.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.
FIG. 1 is a flow chart of a method for analyzing bearing fatigue life influencing factors in accordance with one embodiment of the present invention;
FIG. 2 is a schematic diagram of a network architecture of a VAE network model according to one embodiment of the present invention;
FIG. 3 is a training flow diagram of a VAE network model according to another embodiment of the present invention;
FIG. 4 is a schematic flow chart of an analysis method of bearing fatigue life influencing factors in one embodiment.
Detailed Description
The invention will be described in further detail (which may also be omitted) below by means of the detailed description of the embodiments with reference to the accompanying drawings.
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
Referring to fig. 1 and 4, in one embodiment, a method for analyzing a bearing fatigue life influencing factor is provided, where the method for analyzing a bearing fatigue life influencing factor may specifically include the following steps: s1, S2 and S3.
Step S1: data is collected over a period of the bearing.
In this embodiment, the collected bearing data is used to judge and analyze the relationship between various influencing factors and the bearing data. The influencing factors comprise major influencing factors and minor influencing factors, and the major influencing factors are equivalent to the upper concepts of the minor influencing factors. Data is collected about the fatigue life of the bearing among various influencing factors. A large class of influencing factors includes, but is not limited to, materials, heat treatments, lubrication, service environments, and bearing structure design. Referring to FIG. 2, a large class of influencing factors corresponding to different manners may include different small classes of influencing factors of the large class of influencing factors. For example, the privacy of the material with the bearing, which affects the data of the bearing, is greatly affected by the corresponding material, and when the material is made of iron, aluminum, plastic and other materials, the corresponding material is slightly affected by the corresponding material.
Step S2: and importing the bearing data into a VAE network model to obtain bearing data of different large-class influence factors.
Further comprises: and collecting the collected bearing data into a database to form a feature matrix, and screening the major influence factors by utilizing a correlation analysis method of mutual information, and screening different major influence factors related to the fatigue life of the bearing and different minor influence factors corresponding to each major influence factor.
Further, a VAE network model is constructed in advance by utilizing a plurality of large-class influence factors of the fatigue life of the bearing; and constructing an SVM classification model in advance by utilizing different minor influence factors of each major influence factor.
Referring to fig. 2, a VAE network model is constructed using a plurality of major factors affecting bearing fatigue life, further comprising: and taking the screened multiple influencing factors as a VAE network model, and analyzing and processing dimensional characteristic parameters of the bearing fatigue life to realize the associated characteristic selection of the large influencing factors related to the bearing fatigue life.
Constructing an SVM classification model by utilizing different subclasses of influence factors of each influence factor; further comprises: and taking different minor influence factors of each screened major influence factor as dimension characteristic parameters of SVM classification model analysis processing so as to realize the associated characteristic selection of different minor influence factors in each major influence factor.
The VAE network model in this embodiment is a Variational auto-encoder (Variational auto-encoder) that combines neural networks and bayesian reasoning, including encoders and decoders. The SVM classification model (SVM, support Vector Machine) in the present embodiment is a support vector machine, which is a discrimination model. Based on linear partitioning, it is envisioned that not all data may be partitioned linearly, such as two classes of points in two-dimensional space may require a curve to partition their boundaries. The principle of the support vector machine is to map points in a low-dimensional space into a high-dimensional space, so that the points are linearly separable, and then use the principle of linear division to judge the boundaries of classification, wherein in the high-dimensional space, the points are linearly divided, and in the original data space, the points are non-linearly divided.
Step S2, preprocessing the collected bearing data before importing the bearing data into the VAE network model. Further, the method comprises the steps of carrying out data cleaning on the collected bearing data, wherein the data cleaning mainly comprises the steps of deleting irrelevant data and repeated data in the collected bearing data, smoothing noise data, screening out data irrelevant to mining subjects, and processing missing values and abnormal values.
In this embodiment, the Python language, the Numpy module and the Pandas module are utilized to perform data cleaning on the collected bearing data, and delete bearing data in an abnormal state, for example, some data of the bearing during abnormal operation, for example, bearing data of the automobile hub bearing in a car accident state.
Wherein Python is a computer programming language. The Umpy module, namely Numerical Python, is used to provide support for multidimensional array objects for the Python language. The Numpy module supports advanced and large number of dimensional arrays and matrix operations, and in addition, provides a large number of mathematical function libraries for array operations. The Pandas module is Pannel Data Analysis (panel data analysis). Pandas was constructed based on Numpy for providing support for time series analysis. There are two main data structures in Pandas, one is Series and the other is DataFrame.
And inputting the preprocessed bearing data into a VAE network model to obtain bearing data of different large-class influence factors.
Further, the method further comprises the step of carrying out data standardization processing on the preprocessed bearing data before inputting the preprocessed bearing data into the VAE network model for training.
Normalization (normalization) is the scaling of data to fall within a small specified interval. The unit/condition limitation of the data is removed, and the data is converted into dimensionless pure numerical values, so that indexes of different units or magnitudes can be compared and weighted. Preferably, the data is normalized, i.e., the data is uniformly mapped onto the [0,1] interval.
In this embodiment, the data normalization method adopts normalization, including using the formula x = (x-min)/(max-min),
and compressing the preprocessed bearing data to a [0,1] interval, wherein x is the preprocessed bearing data, min is a data minimum value, max is a data maximum value, and max-min is extremely poor.
The partial codes are as follows:
in one embodiment, if it is desired to map the data to [ -1,1], the formula is changed to: x= (x-xmean)/(xmax-xmin), where x_mean represents the mean of the data.
Referring to fig. 3, in step S2, bearing data is imported into the VAE network model to obtain bearing data of different major types of influencing factors, and further including the steps of: s21, S22, S23, S24, S25, S26.
Step S21: and performing matrix transformation on the preprocessed bearing data by utilizing a reshape function to obtain matrix data of m rows and n columns, namely an m multiplied by n matrix.
The reshape function is used to readjust the number of rows, columns, and dimensions of the matrix. For example, b=reshape (a, size) refers to returning an n-dimensional array identical to the a element, the size of the dimension of the reconstructed array is determined by vector size, and the number of prod (size (B)) must be consistent with prod (size (a)).
B=reshape (a, m, n), returning to a matrix B of m×n, the elements in B being obtained from a by column. If the number of elements in A is not m x n, an error is induced.
B=reshape (a, m, N, p.) and b=reshape (a, [ m N p.) ], returning an N (not the parameter N above) dimensional array with the same element as a. The size of B is m n p.
B=reshape (a., [ ], etc.), the length of the dimension represented by the placeholder [ ] is calculated, so that the product of the dimensions is equivalent to prod (size (a)), the value of prod (size (a)) must be divisible by the product of the specified dimensions. Wherein the placeholder [ ] can only be used once.
Step S42: the m×n matrix is input into the VAE network model encoder in batches for training, and the training is iterated for a plurality of times. In one embodiment, training is iterated 100 times.
The partial codes for the VAE network model training are as follows:
s23: after training, inputting all the trained array data into a VAE network model, extracting hidden space features, reducing the input array data step by step and reducing the input array data to s dimension;
s24: and clustering all s-dimensional array data by using a k-means algorithm to form t-class array data, wherein t is the type of the screened large-class influencing factors, and the class center vector is t multiplied by s. Wherein, the partial codes of the K-means cluster analysis are as follows:
step S25: inputting the class center vector t×s into a decoder of the VAE network model for decoding to obtain t×m×n;
step S26: and (3) performing matrix reduction processing on the t multiplied by m multiplied by n by using a reshape function, and extracting corresponding bearing data of t kinds of influence factors.
Step S3: bearing data in all the major classes of influence factors are imported into an SVM classification model, multi-classification processing is carried out, and influence degrees of different minor classes of influence factors under different major classes of influence factors on bearing fatigue life are obtained, so that the use scheme of the bearing is adjusted by using the influence degrees.
Further, in step S3, the multi-classification processing of the bearing data by the SVM classification model is implemented by calling the LibSVM tool box.
In one embodiment, an analysis system of bearing fatigue life influencing factors is provided, the analysis system of bearing fatigue life influencing factors comprising: the system comprises a collection module, a preprocessing module, a major-class influence factor processing module and a minor-class influence factor processing module.
The collection module is used for collecting data in a period of the bearing. Further, the collected bearing data may be, but is not limited to, data that may be related to bearing fatigue life at either end during design, machining, operation, and maintenance.
The preprocessing module is used for preprocessing the bearing data.
The large-class influence factor processing module is used for importing bearing data into the VAE network model to obtain bearing data of different large-class influence factors.
The small-class influence factor processing module is used for importing bearing data in all the large-class influence factors into the SVM classification model, performing multi-classification processing, and obtaining influence degrees of different small-class influence factors under different large-class influence factors on the bearing fatigue life so as to adjust the use scheme of the bearing by using the influence degrees.
Of course, the system also comprises a screening module and a modeling module.
The screening module is used for collecting the preprocessed bearing data into a database to form a feature matrix, screening the major influence factors by utilizing a correlation analysis method of mutual information, and screening different major influence factors corresponding to the fatigue life of the bearing and different minor influence factors corresponding to each major influence factor;
the modeling module is used for pre-constructing a VAE network model by utilizing a plurality of large-class influence factors of the fatigue life of the bearing; constructing an SVM classification model in advance by utilizing different minor influence factors of each major influence factor;
in one embodiment, a computer device is provided that includes a memory and a processor, the memory having stored therein computer readable instructions that when executed by the processor cause the processor to perform the steps of:
collecting data of a period of the bearing; bearing data are imported into a VAE network model, and bearing data of different large-class influence factors are obtained; bearing data in all the major classes of influence factors are imported into an SVM classification model, multi-classification processing is carried out, and influence degrees of different minor classes of influence factors under different major classes of influence factors on bearing fatigue life are obtained, so that the use scheme of the bearing is adjusted by using the influence degrees.
In one embodiment, a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
collecting data of a period of the bearing; bearing data are imported into a VAE network model, and bearing data of different large-class influence factors are obtained; bearing data in all the major classes of influence factors are imported into an SVM classification model, multi-classification processing is carried out, and influence degrees of different minor classes of influence factors under different major classes of influence factors on bearing fatigue life are obtained, so that the use scheme of the bearing is adjusted by using the influence degrees.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing embodiments represent only some exemplary embodiments of the present invention, which are described in more detail and are not to be construed as limiting the scope of the present invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A method for analyzing bearing fatigue life influencing factors, the method comprising the steps of:
s1: collecting data of a period of the bearing;
s2: importing bearing data into a VAE network model, and acquiring the bearing data of different major factors, wherein the method further comprises the following steps:
s21: performing matrix transformation on the bearing data by utilizing a reshape function to obtain matrix data of m rows and n columns, namely an m multiplied by n matrix;
s22: the m multiplied by n matrix is led into the VAE network model in batches for training, and the training is iterated for a plurality of times;
s23: after training, importing all the trained array data into a VAE network model, extracting hidden space features, reducing the array data step by step, and reducing the array data to s dimension;
s24: clustering all s-dimensional array data by using a k-means algorithm to form t-class array data, wherein t is the type of the screened large-class influence factors, and the class center vector is t multiplied by s;
s25: inputting the class center vector t multiplied by s into a decoder of the VAE network model for decoding to obtain t multiplied by m multiplied by n;
s26: performing matrix reduction processing on t multiplied by m multiplied by n by utilizing a reshape function, and extracting the corresponding bearing data of the t classes of the large-class influence factors;
s3: and importing the bearing data in the major-class influence factors into an SVM classification model, performing multi-classification processing, and obtaining the influence degree of different minor-class influence factors under different major-class influence factors on the fatigue life of the bearing so as to adjust the use scheme of the bearing by using the influence degree.
2. The method of analyzing bearing fatigue life influencing factors according to claim 1, further comprising data preprocessing the bearing data prior to S2.
3. The method of analyzing bearing fatigue life influencing factors according to claim 2, wherein the method of preprocessing the bearing data comprises: and (3) performing data cleaning on the collected bearing data by using the Python language, a Numpy module and a Pandas module thereof, wherein the data cleaning comprises the processing of abnormal values and missing values.
4. The method of analyzing bearing fatigue life influencing factors according to claim 2, wherein importing the bearing data into a VAE network model in S2 includes performing a data normalization process on the bearing data after the preprocessing.
5. The method of analyzing bearing fatigue life influencing factors according to claim 4, wherein the data normalization process comprises compressing the preprocessed bearing data to a [0,1] interval using a formula x = (x-min)/(max-min), wherein x is the preprocessed bearing data, min is a data minimum, max is a data maximum, and max-min is a very bad.
6. The method according to claim 1, wherein in S3, the multi-classification processing of the bearing data by the SVM classification model is implemented by calling a LibSVM tool box.
7. The method of analyzing bearing fatigue life influencing factors according to claim 1, wherein the large class of influencing factors includes, but is not limited to, materials, heat treatments, lubrication, service environments, bearing structural design.
8. A system for analyzing bearing fatigue life influencing factors, the system comprising:
the device comprises a collection module, a preprocessing module, a major-class influence factor processing module and a minor-class influence factor processing module,
the collecting module is used for collecting data in a period of the bearing;
the preprocessing module is used for preprocessing the bearing data, and further comprises:
s21: performing matrix transformation on the bearing data by utilizing a reshape function to obtain matrix data of m rows and n columns, namely an m multiplied by n matrix;
s22: the m multiplied by n matrix is led into the VAE network model in batches for training, and the training is iterated for a plurality of times;
s23: after training, importing all the trained array data into a VAE network model, extracting hidden space features, reducing the array data step by step, and reducing the array data to s dimension;
s24: clustering all s-dimensional array data by using a k-means algorithm to form t-class array data, wherein t is the type of the screened large-class influence factors, and the class center vector is t multiplied by s;
s25: inputting the class center vector t multiplied by s into a decoder of the VAE network model for decoding to obtain t multiplied by m multiplied by n;
s26: performing matrix reduction processing on t multiplied by m multiplied by n by utilizing a reshape function, and extracting the corresponding bearing data of the t classes of the large-class influence factors;
the large-class influence factor processing module is used for importing bearing data into a VAE network model to obtain the bearing data of different large-class influence factors;
the minor influence factor processing module is used for importing the bearing data in the major influence factors into an SVM classification model, performing multi-classification processing, and obtaining influence degrees of different minor influence factors under different major influence factors on the fatigue life of the bearing so as to adjust the use scheme of the bearing by using the influence degrees.
9. A computer device comprising a memory and a processor, wherein the memory has stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the method of analyzing bearing fatigue life influencing factors according to any of claims 1 to 7.
10. A storage medium storing computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the method of analyzing bearing fatigue life influencing factors according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010028584.9A CN111291466B (en) | 2020-01-11 | 2020-01-11 | Analysis method and system for bearing fatigue life influence factors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010028584.9A CN111291466B (en) | 2020-01-11 | 2020-01-11 | Analysis method and system for bearing fatigue life influence factors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291466A CN111291466A (en) | 2020-06-16 |
| CN111291466B true CN111291466B (en) | 2023-05-26 |
Family
ID=71026184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010028584.9A Active CN111291466B (en) | 2020-01-11 | 2020-01-11 | Analysis method and system for bearing fatigue life influence factors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291466B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930931A (en) * | 2016-04-22 | 2016-09-07 | 国网浙江省电力公司经济技术研究院 | Electric power engineering cost management method |
| CN108153999A (en) * | 2018-01-26 | 2018-06-12 | 大连交通大学 | A kind of welding point fatigue life intelligent Forecasting based on fatigue characteristic domain |
| CN110261116A (en) * | 2019-07-08 | 2019-09-20 | 华南理工大学 | A kind of Bearing Fault Detection Method and device |
-
2020
- 2020-01-11 CN CN202010028584.9A patent/CN111291466B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291466A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ansuini et al. | Intrinsic dimension of data representations in deep neural networks | |
| CN109871860B (en) | Daily load curve dimension reduction clustering method based on kernel principal component analysis | |
| CN110659207B (en) | Heterogeneous cross-project software defect prediction method based on nuclear spectrum mapping migration integration | |
| CN112577743B (en) | Rolling bearing fault diagnosis method based on maximum local boundary criterion | |
| CN114548190B (en) | Wind turbine fault diagnosis method and device based on self-adaptive residual error neural network | |
| Schultz et al. | Approximation of diagonal line based measures in recurrence quantification analysis | |
| CN115618267A (en) | Unsupervised domain self-adaption and entropy optimization equipment sensing diagnosis method and system | |
| Zhang et al. | Intelligent machine fault diagnosis using convolutional neural networks and transfer learning | |
| CN111460161A (en) | Unsupervised text theme related gene extraction method for unbalanced big data set | |
| CN114139639B (en) | Fault classification method based on self-step neighborhood preserving embedding | |
| CN113837218A (en) | Text clustering method and system based on one-step post-fusion multi-view | |
| CN112734106A (en) | Method and device for predicting energy load | |
| CN111291466B (en) | Analysis method and system for bearing fatigue life influence factors | |
| CN111382792B (en) | Rolling bearing fault diagnosis method based on double-sparse dictionary sparse representation | |
| CN114398825A (en) | Method for predicting residual life of cutting tool for complex and variable working conditions | |
| Manca et al. | Clustering of similar historical alarm subsequences in industrial control systems using alarm series and characteristic coactivations | |
| CN115618083A (en) | Method and device for multi-source heterogeneous data normalization | |
| CN114154567A (en) | Wind power plant station operation data anomaly identification method based on machine learning | |
| Li et al. | Research on bearing fault detection based on convolution neural network | |
| Tsai et al. | Anomaly Detection Mechanism for Solar Generation using Semi-supervision Learning Model | |
| CN112444395A (en) | CMWPE and SaE-ELM based locomotive wheel pair bearing fault diagnosis method | |
| Li et al. | An improved k-means algorithm for clustering using entropy weighting measures | |
| Guo et al. | Integrating laplacian eigenmaps feature space conversion into deep neural network for equipment condition assessment | |
| Wang et al. | K-means clustering with feature selection for stream data | |
| Derevianchenko et al. | Improvement of the Quality for Cutting Tool Monitoring by Optimizing the Features of the State Space |
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 |