CN116579125A - Bearing remaining life prediction method, device, equipment and readable storage medium - Google Patents
Bearing remaining life prediction method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN116579125A CN116579125A CN202310350083.6A CN202310350083A CN116579125A CN 116579125 A CN116579125 A CN 116579125A CN 202310350083 A CN202310350083 A CN 202310350083A CN 116579125 A CN116579125 A CN 116579125A
- Authority
- CN
- China
- Prior art keywords
- bearing
- data
- maintenance
- reliability
- result
- 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 126
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000012423 maintenance Methods 0.000 claims abstract description 94
- 238000012545 processing Methods 0.000 claims abstract description 59
- 230000008859 change Effects 0.000 claims abstract description 32
- 230000004083 survival effect Effects 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000009826 distribution Methods 0.000 claims description 57
- 238000005315 distribution function Methods 0.000 claims description 44
- 230000006870 function Effects 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000013178 mathematical model Methods 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 7
- 238000012954 risk control Methods 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000013100 final test Methods 0.000 claims description 4
- 238000000611 regression analysis Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000001276 Kolmogorov–Smirnov test Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 230000008439 repair process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000001186 cumulative effect Effects 0.000 description 4
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical group C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000006866 deterioration Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000012888 cubic function Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- 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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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]
Abstract
The invention provides a method, a device, equipment and a readable storage medium for predicting the residual life of a bearing, which relate to the technical field of transportation and comprise the steps of acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data; processing bearing fault data based on a survival curve algorithm to obtain a first reliability model; analyzing the change rules of the failure rate of each stage of the bearing in different maintenance intervals, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model; and processing the first reliability model and the second reliability model by adopting a maintenance method taking reliability as a center to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result. The invention has the beneficial effects of effectively predicting the residual life of the bearing, intuitively providing service mileage and effectively guiding the maintenance of a maintenance unit.
Description
Technical Field
The invention relates to the technical field of transportation, in particular to the technical field of bearing analysis of motor train units, and particularly relates to a method, a device and equipment for predicting residual life of a bearing and a readable storage medium.
Background
With the increase of the high-speed rail transportation mileage in China, the duty ratio of the motor train unit in railway passenger transport is continuously increased, and the cost required by the operation and maintenance of the motor train unit is also continuously increased. The axle box bearing is used as a key component in the axle box device, the bearing load is large, the operation working condition is severe and changeable, and according to the application and maintenance data, a large number of axle box bearings are found to be damaged each year, so that the train can run at a slow speed and be stopped late, even temporarily.
Because the bearing is easy to fail due to the operation of high-speed rail and long-way traffic in China and the severe environment of the bearing, the state management technology of the bearing is necessary to be researched, and the residual life prediction technology of the axle box bearing of the high-speed train is researched so as to predict the life of the axle box bearing to the limit time, thereby guiding the maintenance of an operation and maintenance unit and improving the running safety of the train.
Disclosure of Invention
An object of the present invention is to provide a method, apparatus, device and readable storage medium for predicting remaining life of a bearing, so as to improve the above-mentioned problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
In a first aspect, the present application provides a method for predicting remaining life of a bearing, including:
acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data, wherein the operation and maintenance data comprise vehicle-mounted system alarm data and fault data to be overhauled;
processing bearing fault data based on a survival curve algorithm to obtain a first reliability model;
analyzing the change rules of the failure rate of each stage of the bearing in different maintenance intervals, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model;
and adopting a maintenance method taking the reliability as a center, respectively processing the first reliability model and the second reliability model to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result.
Preferably, the preprocessing the bearing carrier data to obtain bearing fault data includes:
cleaning and rechecking the acquired bearing operation and maintenance data to obtain a first processing result, wherein the cleaning comprises filling processing of missing data, eliminating processing of abnormal data and non-vectorization processing of data;
Analyzing the first processing result to obtain a second processing result, wherein the analysis comprises descriptive analysis, data dynamic analysis, correlation analysis and regression analysis of the first processing result;
and classifying and storing the second processing result according to the keywords to obtain bearing fault data, wherein the keywords comprise vehicle types and maintenance levels.
Preferably, the processing the bearing fault data based on the survival curve algorithm obtains a first reliability model, which includes:
and obtaining a reliability distribution function by adopting a survival curve algorithm, wherein the survival curve algorithm has the formula as follows:
wherein R (t) is a reliability function,to survive the distribution function, Z (i) As variable Z i Of (c) wherein Z i ＝min(X i ,Y i )，X i Is a non-negative random variable, Y i Is a corresponding disturbance random variable; delta (i) To determine whether it is a parameter of the truncated data, i.e. a truncated indication function, if it is truncated data, δ (i) =0; if the life is real life, delta (i) ＝1。
Based on the reliability distribution function and a functional relation corresponding to the bearing reliability, obtaining a failure probability experience distribution function;
fitting the failure probability empirical distribution function by using a mathematical model to obtain a first reliability model, wherein the fitting process comprises the selection of the distribution type of the bearing, the estimation of the distribution parameters and the verification of the distribution type.
Preferably, the fitting process includes an estimation of a distribution parameter of the bearing, including:
the parameter estimation is carried out by using application mathematical software, and the method used for the parameter estimation is a Weibull probability paper method, wherein the calculation formula of the Weibull probability paper is as follows:
wherein F (t) is a Weibull distribution cumulative failure probability function and a failure probability distribution function; lambda is a size parameter, alpha is a shape parameter, t is mileage/time, the above is deformed, and the two sides of the same sign are subjected to linear calculation by taking logarithm calculation at the same time, so that a linear result can be obtained:
in the method, in the process of the invention,at t i Failure probability value observed by time/travel mileage,/->Is defined as at t i The ratio of the number of products that failed before to the number of products that began the test;
and calculating a linear result according to a least square linear regression method to obtain estimated values of the shape parameter and the size parameter of the Weibull distribution.
Preferably, the fitting process includes a verification of the distribution type of the bearing, including:
establishing a distribution function of the bearing by adopting a theoretical distribution method;
and (3) checking the distribution function based on K-S (K-S) checking to obtain a maximum deviation value, wherein the checking formula is as follows:
D n ＝sup|F n (t)-F 0 (t)|
wherein sup (-) is max (-), F n (t) is an empirical distribution function of sample volume n, F 0 (t) is a theoretical distribution function, D n Is the maximum deviation value;
and comparing the maximum deviation value with a preset critical value to obtain a final test result.
Preferably, the analyzing the change rule of the failure rate of each stage of the bearing in the different maintenance intervals includes:
determining failure rate and mileage in the operation of the bearing in unit time;
obtaining a bearing failure rate curve according to the failure rate and mileage, wherein the failure rate curve comprises an early failure period, a product service life period and a wear failure period;
and judging the change rule condition of the fault rate based on the slope condition in the fault curve.
Preferably, the obtaining a first remaining life result includes:
acquiring a bearing failure rule evolution curve;
based on the first reliability model, the working environment of the bearing and preset safety conditions are synthesized, and the residual life of the bearing is preliminarily predicted by adopting a maintenance method taking reliability as a center;
and determining a bearing risk control requirement, and predicting the residual life of the preliminarily predicted bearing again when the bearing running risk reaches the control requirement to obtain a first residual life result.
In a second aspect, the application further provides a device for predicting the residual life of a bearing, which comprises an acquisition module, a processing module, a fitting module and a calculation module, wherein:
The acquisition module is used for: the method comprises the steps of acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data, wherein the operation and maintenance data comprise vehicle-mounted system alarm data and fault data to be overhauled;
the processing module is used for: the method comprises the steps of processing bearing fault data based on a survival curve algorithm to obtain a first reliability model;
fitting module: the method comprises the steps of analyzing the change rules of the failure rate of each stage of the bearing in different maintenance intervals, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model;
the calculation module: the method is used for adopting a maintenance method taking reliability as a center, processing the first reliability model and the second reliability model respectively to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result.
In a third aspect, the present application also provides a bearing remaining life prediction apparatus, comprising:
a memory for storing a computer program;
and a processor for implementing the steps of the method for predicting the remaining life of the bearing when executing the computer program.
In a fourth aspect, the present application also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described bearing remaining life prediction method.
The beneficial effects of the application are as follows:
the method adopts the pretreatment of the bearing carrier data, improves the accuracy of data analysis and processing, avoids the defect of large data error and reduces the follow-up working pressure.
The application builds two reliable digital models, which are based on different angles, but are aimed at improving the working safety and reliability of the bearing, and on the premise of effectively predicting the residual service life of the axle box bearing and optimizing the maintenance repair procedure, the algorithm can intuitively give the residual service life of the bearing by taking the running mileage as a unit and can effectively guide the maintenance of the maintenance unit.
The application adopts a maintenance method with reliability as a center to determine reasonable risk control requirement indexes and reliability indexes so as to realize the prediction of the residual service life of the bearing and the optimization of maintenance repair procedures.
The application adopts the K-S test method, has no special requirement on sample capacity and can test given deviation, and is suitable for most scenes, so that the test result is more accurate.
The bearing is used as a key part of the bogie, the residual service life of the bogie is predicted, the occurrence of accidents can be prevented, and important basis can be provided for the establishment of policies such as repairing, improving and preventing of trains.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for predicting the residual life of a bearing according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a device for predicting remaining life of a bearing according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a bearing residual life prediction apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a product failure rate curve of a residual life prediction of a bearing according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of active risk control for bearing residual life prediction according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of maintenance repair of a bearing residual life prediction according to an embodiment of the present invention.
In the figure: 701. an acquisition module; 7011. a cleaning unit; 7012. an analysis unit; 7013. a storage unit; 702. a processing module; 7021. a first obtaining unit; 7022. a second obtaining unit; 7023. fitting unit; 70231. an estimation unit; 70232. a calculation unit; 70233. establishing a function unit; 70234. a checking unit; 70235. a comparison unit; 703. fitting a module; 7031. a determination unit; 7032. a third obtaining unit; 7033. a judging unit; 704. a computing module; 7041. an acquisition unit; 7042. a first prediction unit; 7043. a second prediction unit; 800. bearing remaining life prediction means; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected 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.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a method for predicting the residual life of a bearing.
Referring to fig. 1, the method is shown to include step S100, step S200, step S300, and step S400.
S100, acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data, wherein the operation and maintenance data comprise vehicle-mounted system alarm data and fault data to be overhauled.
Specifically, massive axle box bearing operation and maintenance data (mainly including vehicle-mounted system alarm data and axle box bearing fault data found by maintenance and inspection by staff) have various problems of large data volume, isomerism, multidimensional, multiscale and the like, and the subsequent analysis can be performed only by processing the data, if an algorithm or a model is directly built on an original operation and maintenance data set, inaccurate analysis results or large errors are likely to be caused. Bearing operation and maintenance data need to be processed and analyzed in order to relieve subsequent operating pressures. The main contents are as follows:
it will be appreciated that step S100 includes steps S101, S102 and S103, wherein:
s101, cleaning and rechecking the acquired bearing operation and maintenance data to obtain a first processing result, wherein the cleaning comprises filling processing of missing data, eliminating processing of abnormal data and non-dimensionality processing of data; the data rechecking aims at the validity of the data and aims at improving the accuracy of the data.
S102, analyzing the first processing result to obtain a second processing result, wherein the analysis comprises descriptive analysis, data dynamic analysis, correlation analysis and regression analysis of the first processing result;
s103, classifying and storing the second processing result according to the keywords to obtain bearing fault data, wherein the keywords comprise vehicle types and maintenance levels.
The bearing operation and maintenance data which are finally cleaned and analyzed are stored in a partitioned mode according to keywords such as vehicle types, maintenance levels and the like, so that subsequent data deepening processing is facilitated.
In the embodiment, a reliability model needs to be built from two aspects, namely, a corresponding mathematical model is built according to the reliability evolution rule of the axle box bearing; analyzing reliability performance evolution rules of the journal bearing in the service mileage of the current stage according to fault data processed by the data, and selecting a proper distribution model to fit the reliability performance evolution rules of the journal bearing; the second is to combine the maintenance mileage of the axle box bearing, consider the influence of the assembly and other problems brought by maintenance on the reliability performance of the axle box bearing, namely the influence of the residual life, mainly establish a failure rate mathematical model by analyzing the failure rate change curves of the axle box bearing in different maintenance intervals, and then establish a reliability degree model of the axle box bearing according to the functional relationship between the failure rate and the reliability. In this embodiment, the first mathematical model is a first reliability model and the second mathematical model is a second reliability model.
And S200, processing bearing fault data based on a survival curve algorithm to obtain a first reliability model.
It should be noted that, because the service time of the high-speed motor train unit is shorter, the obtained bearing fault data is not full life cycle data, but is truncated data based on a certain time point, so when researching the evolution rule of the service performance of the axle box bearing, the fault data needs to be processed by applying a related theory, and the specific contents are as follows:
it will be appreciated that the present step S200 includes steps S201, S202 and S203, wherein:
s201, obtaining a reliability distribution function by adopting a survival curve algorithm, wherein the survival curve algorithm has the following formula:
wherein R (t) is a reliability function,to survive the distribution function, Z (i) As variable Z i Of (c) wherein Z i ＝min(X i ,Y i )，X i Is a non-negative random variable, Y i Is a corresponding disturbance random variable; delta (i) To determine whether it is a parameter of the truncated data, i.e. a truncated indication function, if it is truncated data, δ (i) =0; if the life is real life, delta (i) ＝1。
It should be noted that the truncated data needs to be processed before the survival curve is adopted to obtain the survival distribution probability of the bearing, which is also called Product Limit (PL) estimation. The calculation formula and assumption involved are as follows:
Set X 1 ,X 2 ,...,X n Is a non-negative random variable and has a common survival function S (t), Y 1 ,Y 2 ,...,Y n Is the corresponding disturbance random variable, namely:
wherein Z is (1) ,Z (2) ,...,Z (n) Is Z 1 ,Z 2 ,...,Z n Sequence statistics of (2); delta (1) ,δ (2) ,...,δ (n) Is equal to Z (1) ,Z (2) ,...,Z (n) Corresponding truncated indication function, for simple calculation, see Z (1) ,Z (2) ,...,Z (n) Is constant and is
Due to longer life than Z (i-1) N-i+1 of individuals, if Z (i) Is the real life (delta) (i) =1), then it indicates a lifetime longer than Z (i-1) Exactly one of the n-i+1 individuals in (1) is in (Z (i-1) ，Z (i) ]Death in the middle; conversely, if Z (i) For truncating data (delta) (i) =0), then the lifetime is longer than Z (i-1) None of the n-i+1 individuals of (2) are in (Z (i-1) ，Z (i) ]Death in the middle. Thereby P (X)>Z (i) |X>Z (i-1) ) Is a reasonable estimate of:
in the method, in the process of the invention,is an estimation of the survival probability of this interval, assuming that when no death occurs, the survival probability is 1, and if a death occurs, the failure probability is 1/(n-i-1), and the survival probability becomes (1-1/(n-i-1))
The formula of the finishing formula is as follows:
wherein R (t) is a reliability function,to survive the distribution function, Z (i) As variable Z i Of (c) wherein Z i ＝min(X i ,Y i )，X i Is not aNegative random variable, Y i Is a corresponding disturbance random variable; delta (i) To determine whether it is a parameter of the truncated data, i.e. a truncated indication function, if it is truncated data, δ (i) =0; if the life is real life, delta (i) ＝1。
S202, obtaining an empirical distribution function of failure probability based on a reliability distribution function and a functional relation corresponding to the reliability of the bearing;
the functional relation between the reliability and the failure probability is as follows:
f (t) =1-R (t) or R (t) =1-F (t) (5)
Wherein F (t) is an empirical distribution function of failure probability, and R (t) is a reliability function.
S203, fitting the failure probability empirical distribution function by using a mathematical model to obtain a first reliability model, wherein the fitting process comprises the selection of the distribution type of the bearing, the estimation of the distribution parameter and the verification of the distribution type.
It should be noted that, from the obtained empirical distribution function F (t) of failure probability, the evolution rule of the failure probability of the axle box bearing can be known, then a proper mathematical model needs to be selected, and the failure probability of the axle box bearing is fitted, which mainly includes the selection of the distribution type, the estimation of the distribution parameter and the inspection of the distribution type, so as to obtain the failure probability distribution model. The following is the fitting process:
in this embodiment, the distribution type of the bearings is selected as follows: the usual distribution forms of the mechanical parts include normal distribution, exponential distribution, weibull distribution, and the like. In the present embodiment, it is assumed that the pedestal bearing conforms to three distribution types of normal distribution, lognormal distribution, and weibull distribution.
In this embodiment, the estimation of the distribution parameters of the bearing is: the parameter estimation method comprises a graph estimation method, a least square method, a maximum likelihood method, a moment estimation method and the like, wherein the distribution parameters of normal distribution and lognormal distribution are estimated by adopting a Gaussian-Newton method (realized by means of MATLAB software correlation functions), and the distribution parameters are estimated by adopting a Weibull probability paper method aiming at Weibull distribution:
in step S203, S2031 and S2032 are included, which includes:
s2031, carrying out parameter estimation by using application mathematical software, wherein a method used for parameter estimation is a Weibull probability paper method, and the calculation formula of the Weibull probability paper is as follows:
wherein λ is a size parameter, α is a shape parameter, t is mileage/time, F (t) is a weibull distribution function, and the linear result can be obtained by performing linear calculation by simultaneously taking logarithmic operation on both sides of the equivalent number by deforming (6):
in the method, in the process of the invention,at t i Failure probability value observed by time/travel mileage,/->Is defined as at t i The ratio of the number of products that failed before to the number of products that began the test;
introducing variable y i 、x i The specific relational expressions of a and b are as follows:
then y can be obtained i ＝a+bx i (9)
Wherein a and b are introduced variables.
By introducing variables, equations (8) and (9) preserve the functional relationship of equation (7), simplifying the calculation process.
S2032, calculating a linear result according to a least square linear regression method to obtain estimated values of shape parameters and size parameters of the Weibull distribution.
By least squares linear regression, can obtain
In the formula, a is the same as a in the formulas (8) and (9), and is obtained by converting the formulas to obtain the shape parameter and the size parameter of the Weibull distribution;
wherein the method comprises the steps ofRespectively the observed value x i And y i Is obtainable according to formulae (8) and (10),
based on the above, the shape parameters of the Weibull distribution can be finally obtainedAnd size parameter->Is used for the estimation of the estimated value of (a).
In this embodiment, the test of the distribution type of the bearing is: the common fitting goodness test method comprises χ 2 Test methods and K-S test methods. The K-S test is suitable for most scenes because the K-S test has the advantages of accurate test, no special requirement on sample capacity, capability of testing given deviation and the like, and therefore, the assumed distribution type is tested by adopting the K-S test method.
It should be noted that, step S203 further includes S2033, S2034, and S2035, which include:
S2033, establishing a distribution function of the bearing by adopting a theoretical distribution method;
it should be noted that, at the significance level α, a hypothetical formula is established:
H：F(x)＝F 0 (x)；H 1 ：F(x)≠F 0 (x)
wherein F is 0 (x) Representing a distribution function, i.e., a theoretical distribution, to which the sample population is assumed to be subjected; f (x) refers to an empirical failure probability distribution function, the above formula is a general expression for probability theory hypothesis test, H is an original hypothesis, and H1 is an alternative hypothesis.
In this embodiment, the K-S test is based on the fact that the cumulative distribution of word detection is very close to the true cumulative distribution. The measurement method of the goodness of fit is to find out the maximum deviation value between subsamples and parent, namely the test statistic is as follows (13), and the method comprises the following steps:
s2034, checking the distribution function based on K-S test to obtain a maximum deviation value, wherein the checking formula is as follows:
D n ＝sup|F n (t)-F 0 (t)| (13)
wherein sup (-) is max (-), F n (t) is an empirical distribution function of sample volume n, F 0 (t) is a theoretical distribution function, D n Is the maximum deviation value.
S2035, comparing the maximum deviation value with a preset critical value to obtain a final test result.
The maximum deviation D n And a critical value D (n,α) In comparison, if D n <D (n,α) The original hypothesis is accepted, otherwise rejected.
After the checking step is completed, rejecting the distribution model which does not accord with the evolution rule of the bearing failure probability, accepting the distribution model which accords with the bearing failure rule, thereby establishing a failure probability distribution model, and establishing a bearing reliability degree model, namely a first reliability model, according to the formula (5).
S300, analyzing the change rules of the failure rate of the bearings in different maintenance intervals at each stage, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model.
Besides the failure probability, reliability and the like can be used for describing the overall reliability level of the product, the failure rate is taken as a characteristic quantity of the ratio of the number of products which fail in the next unit time after t is predicted (t is the time when the product works to a certain time) to the number of products which do not fail at the moment, and the failure rate is also one of the common quantity characteristics of the reliability of the product, and the lower the reliability of the product with higher failure rate is, the calculation formula is as follows:
wherein lambda (t) is a failure rate function, t is a characteristic quantity of a ratio of the number of failed products to the number of products not failed yet operated to that time in a next unit time after the operation of the products to a time, X is a random variable, expressed in (t, t+Deltat]Random variables within the interval, and Δt→0 + 。
Assuming that a limit exists and that a density function f (t) of X exists, the relationship between the failure rate λ (t) and the reliability R (t) is
Or (b)
Wherein R is ′ (t) is the first derivative of the reliability function R (t), u is a hypothetical variable that is used to distinguish the variables t, f (t) from the density function.
In addition, since some parts or the pedestal bearing itself are reassembled during maintenance, and the related parts are re-worn and adapted, the failure rate is too high in the initial stage after maintenance, and the relationship between the failure rate and the reliability shows that the higher the failure rate is, the lower the reliability is, namely the pedestal bearing cannot maintain good working performance, and the residual service life of the pedestal bearing is affected. The axle box bearing is used as a key part of the bogie, the residual service life of the axle box bearing is predicted, the occurrence of accidents can be prevented, and important basis can be provided for the establishment of policies such as repairing, improving and preventing of trains, so that the influence of maintenance performance on the service life of the axle box bearing needs to be analyzed in an emphasized manner.
In order to study the service life influence of maintenance performance on the axle box bearing, considering the maintenance interval as a limit, analyzing the fault rate change curve of the axle box bearing in different maintenance intervals. The specific method comprises the following steps:
it will be appreciated that the present step S300 includes S301, S302 and S303, where:
s301, determining failure rate and mileage in the bearing unit time work;
it should be noted that, firstly, a bathtub curve, namely a product failure rate curve, is drawn according to the failure rate and mileage in the working time.
S302, obtaining a bearing failure rate curve according to the failure rate and mileage, wherein the failure rate curve comprises an early failure period, a product service life period and a wear failure period;
it should be noted that, as shown in fig. 4, the time-dependent change of the failure rate of the product can be divided into three stages: early failure, occasional failure and wear failure, wherein occasional failure is the best working period of the product, and the duration of the occasional failure is longer, also called the service life of the product. However, in actual situations, in a certain maintenance interval of the axle box bearing, the change of the fault rate curve does not completely include three stages, and random combination of the three stages may occur, for example, the situation that the axle box bearing is always in an accidental failure period, or is always in an early failure period, then is always in an accidental failure period, and so on, so that judgment needs to be made on the situation occurring in the certain maintenance interval.
S303, judging the change rule condition of the fault rate based on the slope condition in the fault curve.
Specifically, the following details are respectively described in terms of the change phases:
1. early failure period judgment: as can be seen from the bathtub curve, when the bathtub is in the early failure stage, the failure rate is continuously reduced along with the increase of time (mileage), so that whether the bathtub is in the early failure stage can be judged according to the slope of the change of the adjacent failure rates, and if the slope is smaller than 0 in a certain continuous time (mileage) in the maintenance interval, the failure rate of the continuous time (mileage) can be judged to be in the early failure stage.
2. Accidental expiration period judgment: as can be seen from the bathtub curve, the failure rate is unchanged with the increase of time (mileage) when the bathtub curve is in the accidental failure period, so if the failure rate is kept stable and unchanged in a certain continuous time (mileage) in the maintenance interval, the failure rate in the continuous time (mileage) can be judged to be in the accidental failure period.
3. Judging the wear-out failure period: as can be seen from the bathtub curves, the failure rate gradually increases with time (mileage) during the wear-out failure period. The judging method is similar to the early failure period, and if the slope is larger than 0 in a certain continuous time (mileage) in the maintenance interval, the failure rate of the continuous time (mileage) can be judged to be in the wear-out failure stage.
Specifically, after the change rule is determined, an appropriate mathematical model is selected, including but not limited to fitting the change rule of each stage of the failure rate using an exponential function, a cubic function, a logarithmic function, and the like. Wherein, since the failure rate is constant in the accidental failure stage, the change of the reliability accords with an exponential function according to the functional relation (16) between the failure rate and the reliability, so that the exponential function is selected to fit the failure rate in the accidental failure stage. Based on the formula (2), a reliability degree model, namely a second reliability model, of the axle box bearing in each maintenance interval can be obtained according to the formula (15) or the formula (16) between the failure rate and the reliability.
S400, adopting a maintenance method taking reliability as a center to respectively process the first reliability model and the second reliability model to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result.
It will be appreciated that the present step S400 includes steps S401, S402 and S403, wherein:
s401, acquiring a bearing failure rule evolution curve;
s402, based on a first reliability model, the working environment of the bearing and preset safety conditions are synthesized, and the residual life of the bearing is preliminarily predicted by adopting a maintenance method with reliability as a center;
s403, determining a bearing risk control requirement, and predicting the residual life of the preliminarily predicted bearing again when the bearing running risk reaches the control requirement to obtain a first residual life result.
It should be noted that, as shown in fig. 5, the reliability-centric maintenance method may upgrade the maintenance strategy from the conventional "fault prevention" to "active risk management". According to a bearing failure law evolution curve (the change trend of the working reliability of the axle box bearing from 1 to 0, namely the change trend of the risk from 0 to 1), a maintenance method with reliability as a center is applied to predict the residual life of the axle box bearing, the axle box bearing working environment and the safety requirement are comprehensively considered, the axle box bearing risk control requirement is determined, and when the running risk of the axle box bearing reaches the control requirement, the residual life (service mileage) of the axle box bearing can be determined.
Based on maintenance repair optimization based on a maintenance method with reliability as a center, the requirements of failure deterioration speed, redundancy and the like are comprehensively considered, the failure influence level is divided into three levels of safety, usability and economy, wherein the safety refers to the failure level which can cause safety accidents such as derailment, overturning, rear-end collision and the like of a motor train unit after the failure occurs, the usability refers to the failure level which can cause the influence on the train operation quality and passenger experience of the motor train unit such as parking, transfer and the like after the failure occurs, the economy refers to the failure level which does not influence the use of the motor train unit after the failure occurs, but the labor and material resources are required to be increased for maintenance to cause unnecessary economic loss, the failure deterioration speed is divided into two levels of high speed and low speed, and the redundancy is divided into two levels of low speed and high speed, so that the acceptable minimum reliability index of the safe operation of the motor train unit under different failure influence levels and different failure deterioration speeds and redundancy levels can be determined. In combination with the reliability change rule curve of the axle box bearing, when the reliability operation of the axle box bearing is reduced to the reliability index, the corresponding time/mileage is the maintenance time node of the axle box bearing, namely the maintenance repair course, as shown in fig. 6.
In step S400, the calculating an average value of the first remaining life result and the second remaining life result to obtain a final remaining life prediction result of the bearing includes:
it should be noted that, in the above process, two different bearing reliability digital models, namely a first reliability model and a second reliability model, are obtained, then the two different mathematical models are respectively calculated, so as to obtain the calculation results of the residual life of the axle box bearing and the maintenance repair procedure corresponding to the different models, and for balancing the difference between the two results, the average value of the calculation results of the residual life of the two mathematical models is considered to be calculated, so as to finally give the residual life/residual service mileage of the axle box bearing, and the maintenance repair procedure is also the same.
In summary, the reliability digital model of the two journal bearings is based on different angles, but aims to improve the working safety and reliability of the journal bearings, so as to effectively predict the residual service life of the journal bearings and optimize maintenance repair procedures. Meanwhile, the algorithm can intuitively give the residual service life of the axle box bearing by taking the travelling mileage as a unit, and can effectively guide the maintenance of a maintenance unit.
Example 2:
as shown in fig. 2, the present embodiment provides a device for predicting remaining life of a bearing, which referring to fig. 2 includes an acquisition module 701, a processing module 702, a fitting module 703, and a calculation module 704, wherein:
The acquisition module 701: the method comprises the steps of acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data, wherein the operation and maintenance data comprise vehicle-mounted system alarm data and fault data to be overhauled;
the processing module 702: the method comprises the steps of processing bearing fault data based on a survival curve algorithm to obtain a first reliability model;
fitting module 703: the method comprises the steps of analyzing the change rules of the failure rate of each stage of the bearing in different maintenance intervals, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model;
the calculation module 704: the method is used for adopting a maintenance method taking reliability as a center, processing the first reliability model and the second reliability model respectively to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result.
Specifically, the acquiring module 701 includes a cleaning unit 7011, an analyzing unit 7012, and a storing unit 7013, where:
cleaning unit 7011: the method comprises the steps of cleaning and rechecking acquired bearing operation and maintenance data to obtain a first processing result, wherein the cleaning comprises filling processing of missing data, eliminating processing of abnormal data and non-dimensionality processing of data;
Analysis unit 7012: the method comprises the steps of analyzing a first processing result to obtain a second processing result, wherein the analysis comprises descriptive analysis, data dynamic analysis, correlation analysis and regression analysis of the first processing result;
storage unit 7013: and the second processing result is used for classifying and storing according to the keywords to obtain bearing fault data, wherein the keywords comprise vehicle types and maintenance levels.
Specifically, the processing module 702 includes a first obtaining unit 7021, a second obtaining unit 7022, and a fitting unit 7023, wherein:
first obtaining unit 7021: the reliability distribution function is obtained by adopting a survival curve algorithm, wherein the formula of the survival curve algorithm is as follows:
wherein R (t) is a reliability function,to survive the distribution function, Z (i) As variable Z i Of (c) wherein Z i ＝min(X i ,Y i )，X i Is a non-negative random variable, Y i Is a corresponding disturbance random variable; delta (i) To determine whether it is a parameter of the truncated data, i.e. a truncated indication function, if it is truncated data, δ (i) =0; if the life is real life, delta (i) ＝1。
Second obtaining unit 7022: the method is used for obtaining an empirical distribution function of failure probability based on the reliability distribution function and a functional relation corresponding to the reliability of the bearing;
Fitting unit 7023: the method is used for fitting the failure probability empirical distribution function by using a mathematical model to obtain a first reliability model, wherein the fitting process comprises the selection of the distribution type of the bearing, the estimation of the distribution parameters and the verification of the distribution type.
Specifically, the fitting unit 7023 includes an estimating unit 70231 and a calculating unit 70232, wherein:
estimation unit 70231: the method for carrying out parameter estimation by utilizing mathematical software is a Weibull probability paper method, wherein the calculation formula of the Weibull probability paper is as follows:
wherein F (t) is a Weibull distribution cumulative failure probability function, lambda is a size parameter, alpha is a shape parameter, t is mileage/time, the above formula is deformed, and the two sides of the equivalent number are simultaneously subjected to logarithmic operation to perform linearization calculation, so that a linearization result can be obtained:
in the method, in the process of the invention,at t i Failure probability value observed by time/travel mileage,/->Is defined as at t i The ratio of the number of products that failed before to the number of products that began the test;
calculation unit 70232: and the method is used for calculating the linear result according to the least square linear regression method to obtain the estimated values of the shape parameter and the size parameter of the Weibull distribution.
Specifically, the fitting unit 7023 further includes a set-up function unit 70233, a verification unit 70234, and a comparison unit 70235, which further includes:
The set-up function unit 70233: the method is used for establishing a distribution function of the bearing by adopting a theoretical distribution method;
inspection unit 70234: the method is used for checking the distribution function based on K-S test to obtain the maximum deviation value, and the checking formula is as follows:
D n ＝sup|F n (t)-F 0 (t)|
wherein sup (-) is max (-), F n (t) is an empirical distribution function of sample volume n, F 0 (t) is a theoretical distribution function, D n Is the maximum deviation value;
comparison unit 70235: and comparing the maximum deviation value with a preset critical value to obtain a final test result.
Specifically, the fitting module 703 includes a determining unit 7031, a third obtaining unit 7032, and a judging unit 7033, wherein:
determination unit 7031: the method is used for determining the failure rate and the mileage in the bearing unit time operation;
third obtaining unit 7032: the method comprises the steps of obtaining a bearing failure rate curve according to failure rate and mileage, wherein the failure rate curve comprises an early failure period, a product service life period and a wear failure period;
determination unit 7033: and the method is used for judging the change rule condition of the fault rate based on the slope condition in the fault curve.
Specifically, the calculation module 704 includes an acquisition unit 7041, a first prediction unit 7042, and a second prediction unit 7043, wherein:
Acquisition unit 7041: the method is used for acquiring a bearing failure rule evolution curve;
first prediction unit 7042: the method is used for preliminarily predicting the residual life of the bearing by adopting a maintenance method taking reliability as a center on the basis of a first reliability model and integrating the working environment of the bearing and preset safety conditions;
second prediction unit 7043: and the method is used for determining the control requirement of the bearing risk, and when the running risk of the bearing reaches the control requirement, the preliminary prediction of the residual life of the bearing is carried out again to obtain a first residual life result.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
Example 3:
corresponding to the above method embodiment, there is also provided in this embodiment a bearing remaining life prediction apparatus, which will be described below, and a bearing remaining life prediction method described above may be referred to in correspondence with each other.
Fig. 3 is a block diagram of a bearing remaining life prediction apparatus 800, according to an example embodiment. As shown in fig. 3, the bearing remaining life prediction apparatus 800 includes: a processor 801 and a memory 802. The bearing remaining life prediction apparatus 800 further includes one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
Wherein the processor 801 is configured to control the overall operation of the bearing remaining life prediction apparatus 800 to perform all or part of the steps of the bearing remaining life prediction method described above. The memory 802 is used to store various types of data to support the operation of the bearing residual life prediction device 800, which may include, for example, instructions for any application or method operating on the bearing residual life prediction device 800, as well as application related data, such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, or buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the bearing remaining life prediction apparatus 800 and other apparatuses. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G, or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module or NFC module.
In an exemplary embodiment, the bearing remaining life prediction apparatus 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), digital signal processors (DigitalSignal Processor, abbreviated as DSP), digital signal processing apparatus (Digital Signal Processing Device, abbreviated as DSPD), programmable logic devices (Programmable Logic Device, abbreviated as PLD), field programmable gate arrays (Field Programmable Gate Array, abbreviated as FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the bearing remaining life prediction methods described above.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the bearing remaining life prediction method described above. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the bearing remaining life prediction apparatus 800 to perform the bearing remaining life prediction method described above.
Example 4:
corresponding to the above method embodiment, there is also provided a readable storage medium in this embodiment, and a readable storage medium described below and a bearing remaining life prediction method described above may be referred to in correspondence with each other.
The readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the bearing remaining life prediction method of the above method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A method of predicting remaining life of a bearing, comprising:
acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data, wherein the operation and maintenance data comprise vehicle-mounted system alarm data and fault data to be overhauled;
processing bearing fault data based on a survival curve algorithm to obtain a first reliability model;
analyzing the change rules of the failure rate of each stage of the bearing in different maintenance intervals, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model;
and adopting a maintenance method taking the reliability as a center, respectively processing the first reliability model and the second reliability model to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result.
2. The method of claim 1, wherein the preprocessing of the bearing carrier data to obtain bearing failure data comprises:
cleaning and rechecking the acquired bearing operation and maintenance data to obtain a first processing result, wherein the cleaning comprises filling processing of missing data, eliminating processing of abnormal data and non-vectorization processing of data;
Analyzing the first processing result to obtain a second processing result, wherein the analysis comprises descriptive analysis, data dynamic analysis, correlation analysis and regression analysis of the first processing result;
and classifying and storing the second processing result according to the keywords to obtain bearing fault data, wherein the keywords comprise vehicle types and maintenance levels.
3. The method for predicting remaining life of a bearing according to claim 1, wherein the processing the bearing failure data based on the survival curve algorithm to obtain a first reliability model includes:
and obtaining a reliability distribution function by adopting a survival curve algorithm, wherein the survival curve algorithm has the formula as follows:
wherein R (t) is a reliability function,to survive the distribution function, Z (i) As variable Z i Of (c) wherein Z i ＝min(X i ,Y i )，X i Is a non-negative random variable, Y i Is a corresponding disturbance random variable; delta (i) To determine whether it is a parameter of the truncated data, i.e. a truncated indication function, if it is truncated data, δ (i) =0; if the life is real life, delta (i) ＝1。
Based on the reliability distribution function and a functional relation corresponding to the bearing reliability, obtaining a failure probability experience distribution function;
fitting the failure probability empirical distribution function by using a mathematical model to obtain a first reliability model, wherein the fitting process comprises the selection of the distribution type of the bearing, the estimation of the distribution parameters and the verification of the distribution type.
4. A method of predicting remaining life of a bearing as claimed in claim 3, wherein the fitting process comprises an estimation of a distribution parameter of the bearing, comprising:
the parameter estimation is carried out by utilizing mathematical software, wherein the parameter estimation method is a Weibull probability paper method, and the calculation formula of the Weibull probability paper is as follows:
wherein F (t) is a failure probability distribution function, lambda is a size parameter, alpha is a shape parameter, t is mileage/time, the above deformation is performed, and the two sides of the equivalent number are simultaneously subjected to logarithmic operation to perform linearization calculation, so that a linearization result can be obtained:
in the method, in the process of the invention,at t i Failure probability value observed by time/travel mileage,/->Is defined as at t i The ratio of the number of products that failed before to the number of products that began the test;
and calculating a linear result according to a least square linear regression method to obtain estimated values of the shape parameter and the size parameter of the Weibull distribution.
5. A method of predicting remaining life of a bearing as claimed in claim 3, wherein the fitting process includes a verification of the type of distribution of the bearing, including:
establishing a distribution function of the bearing by adopting a theoretical distribution method;
and (3) checking the distribution function based on K-S (K-S) checking to obtain a maximum deviation value, wherein the checking formula is as follows:
D n ＝sup|F n (t)-F 0 (t)|
Wherein sup (-) is max (-), F n (t) is an empirical distribution function of sample volume n, F 0 (t) is a theoretical distribution function, D n Is the maximum deviation value;
and comparing the maximum deviation value with a preset critical value to obtain a final test result.
6. The method for predicting remaining life of a bearing according to claim 1, wherein analyzing the change law of failure rate of each stage of the bearing in different maintenance intervals comprises:
determining failure rate and mileage in the operation of the bearing in unit time;
obtaining a bearing failure rate curve according to the failure rate and mileage, wherein the failure rate curve comprises an early failure period, a product service life period and a wear failure period;
and judging the change rule condition of the fault rate based on the slope condition in the fault curve.
7. The method of claim 1, wherein the obtaining a first remaining life result comprises:
acquiring a bearing failure rule evolution curve;
based on the first reliability model, the working environment of the bearing and preset safety conditions are synthesized, and the residual life of the bearing is preliminarily predicted by adopting a maintenance method taking reliability as a center;
and determining a bearing risk control requirement, and predicting the residual life of the preliminarily predicted bearing again when the bearing running risk reaches the control requirement to obtain a first residual life result.
8. A bearing remaining life prediction apparatus, comprising:
the acquisition module is used for: the method comprises the steps of acquiring bearing operation and maintenance data, and preprocessing the bearing operation and maintenance data to obtain bearing fault data, wherein the operation and maintenance data comprise vehicle-mounted system alarm data and fault data to be overhauled;
the processing module is used for: the method comprises the steps of processing bearing fault data based on a survival curve algorithm to obtain a first reliability model;
fitting module: the method comprises the steps of analyzing the change rules of the failure rate of each stage of the bearing in different maintenance intervals, and fitting the change rules of the failure rate by adopting a first function to obtain a second reliability model;
the calculation module: the method is used for adopting a maintenance method taking reliability as a center, processing the first reliability model and the second reliability model respectively to obtain a first residual life result and a second residual life result, and obtaining an average value of the first residual life result and the second residual life result to obtain a final bearing residual life prediction result.
9. A bearing remaining life prediction apparatus, characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for predicting the remaining life of a bearing according to any one of claims 1 to 7 when executing said computer program.
10. A readable storage medium, characterized by: the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for predicting the remaining life of a bearing as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310350083.6A CN116579125A (en) | 2023-04-04 | 2023-04-04 | Bearing remaining life prediction method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310350083.6A CN116579125A (en) | 2023-04-04 | 2023-04-04 | Bearing remaining life prediction method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116579125A true CN116579125A (en) | 2023-08-11 |
Family
ID=87536687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310350083.6A Pending CN116579125A (en) | 2023-04-04 | 2023-04-04 | Bearing remaining life prediction method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116579125A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117195730A (en) * | 2023-09-14 | 2023-12-08 | 江西睿构科技有限公司 | Method and system for analyzing service life of electromechanical equipment of expressway |
-
2023
- 2023-04-04 CN CN202310350083.6A patent/CN116579125A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117195730A (en) * | 2023-09-14 | 2023-12-08 | 江西睿构科技有限公司 | Method and system for analyzing service life of electromechanical equipment of expressway |
| CN117195730B (en) * | 2023-09-14 | 2024-03-19 | 江西睿构科技有限公司 | Method and system for analyzing service life of electromechanical equipment of expressway |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107153914B (en) | System and method for evaluating automobile operation risk | |
| Lin et al. | Reliability analysis for degradation of locomotive wheels using parametric Bayesian approach | |
| CN110222437B (en) | Method and device for evaluating health status of train, and storage medium | |
| CN108896299B (en) | Gearbox fault detection method | |
| Lin et al. | Reliability analysis for preventive maintenance based on classical and Bayesian semi-parametric degradation approaches using locomotive wheel-sets as a case study | |
| CN106251361A (en) | A kind of rail surface defects image self-adapting division method | |
| CN105550757B (en) | Motor train unit maintenance decision method and device based on fault statistical analysis | |
| CN103617110A (en) | Server device condition maintenance system | |
| CN110203249B (en) | Train repair process method, device and storage medium | |
| CN116579125A (en) | Bearing remaining life prediction method, device, equipment and readable storage medium | |
| Braga et al. | Multivariate statistical aggregation and dimensionality reduction techniques to improve monitoring and maintenance in railways: The wheelset component | |
| Uyan et al. | Industry 4.0 foundry data management and supervised machine learning in low-pressure die casting quality improvement | |
| CN113247041A (en) | Wheel set axle box device state monitoring method based on digital twin model | |
| Liu et al. | A novel abnormal detection method for bearing temperature based on spatiotemporal fusion | |
| Gao et al. | Estimation of rail renewal period in small radius curves: A data and mechanics integrated approach | |
| CN110143217B (en) | Track state measuring method, system and device | |
| CN109625025B (en) | BTM equipment early warning system | |
| Asplund et al. | Assessment of the data quality of wayside wheel profile measurements. | |
| Lin et al. | Bayesian parametric analysis for reliability study of locomotive wheels | |
| CN115479949A (en) | Bridge safety monitoring and early warning method and system based on big data | |
| Caldeira et al. | Assessing wear evolutions in railway wheelsets using a survival modeling approach | |
| Yang et al. | Reliability assessment model and simulation of journal bearing of railway freight cars based on bayesian method under small sample sizes | |
| Men et al. | Reliability Modeling and Parameter Estimation for High-Speed Train Wheels Subject to Multi-Dimensional Degradation Processes Considering Mutual Dependency | |
| CN114117687A (en) | Method and system for building and predicting life prediction model of key parts of wheel set | |
| CN113836733A (en) | Method and device for determining layout position of vehicle curve passing performance monitoring equipment |
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 |