CN109086945A - A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance - Google Patents
A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance Download PDFInfo
- Publication number
- CN109086945A CN109086945A CN201811009454.XA CN201811009454A CN109086945A CN 109086945 A CN109086945 A CN 109086945A CN 201811009454 A CN201811009454 A CN 201811009454A CN 109086945 A CN109086945 A CN 109086945A
- Authority
- CN
- China
- Prior art keywords
- covariant
- spare part
- time
- machine tool
- model
- 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
Classifications
-
- 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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Complex Calculations (AREA)
Abstract
The present invention provides a kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance, is related to numerical control machine tool technique field.This method extracts the historical failure data of main shaft of numerical control machine tool first and influences the operation covariant correlative factor of part life, and use ratio risk model establishes the reliability model of spare part needed for equipment component；It is then based on Data Analysis Software SPSS screening covariant and determines the regression coefficient value of final covariant；Renewal process model is finally used, calculates the number of faults of components that the fault data of unrepairable is independently distributed in special time period, and then obtain the predicted quantity of spare part needed for components.Machine tool chief axis spare part prediction technique provided by the invention based on operation analysis of covariance, improves the accuracy of required spare part prediction data, reduces the amount of storage of equipment and spare part, to significantly reduce the operation cost of enterprise.
Description
Technical field
The present invention relates to numerical control machine tool technique field more particularly to a kind of machine tool chief axis based on operation analysis of covariance are standby
Part prediction technique.
Background technique
Spare part supply in time be machine system timely maintenance basic guarantee.The timely supply of spare part can be set with hoisting machine
The validity of standby production, and shutdown loss can be reduced；But excessive spares reserve will cause stock again, generate inventory at
This, while occupying a large amount of circulating fund.Therefore accurate spare part prediction is not only concerning production, while being related to the accounting of cost.
Empirical method is most basic spare part prediction technique, is had based on time sequence relative to such method precision of prediction is slightly higher
Column method mainly includes exponential smoothing (SES), Croston method, Bootstrap method etc..Feng Yang proposes the spare part based on SES
Prediction, it is preferable to solve the spare part prediction that mass data is zero in historical data and sample；Croston considers historic demand amount
With required time interval both sides factor, innovatively propose rarely used spare parts demand sequence being split as demand and demand
Two continuous sequences are spaced to be predicted respectively.But Croston method can only calculate the average demand of fixed time period；
Thomas etc. introduces bootstrap method and predicts interruption demand.Explanatory variable is added on the basis of the method in Central China life
Influence, propose IFM prediction technique.But Bootstrap method assumes theory hardly possible of the required time sequence there are autocorrelation
To be guaranteed, and it can only obtain the demand distribution of early period.
The fault observer of equipment is determined by its inherent reliability, but external operating environment influent factor is to a certain extent
It can promote or the generating period of delay fault point, change the reliability of the equipment in certain time.Ghodrati is being calculated
The influence for ignoring covariant when the quantity of spare part needed for the mine Ji Lvna unloader hydraulic jack (lifting cylinder) may cause
About 20% difference.When being based on geolocation analysis seabed gas compression system, the operational capacity of worker, work pressure are found
The failure risk that the factors such as power and fatigue conditions generate its device systems accounts for very big ratio.Although being predicted in spare part
The importance of aspect covariant approved, but at present for only a small number of paper describe its Quantitative Analysis Model.It is standby
In part forecasting research, the time is only classified as unique Variable Factors by most of research research, seldom can be other shadows
The factor of sound is included in the scope of covariant, and usually these external influence factors cannot be ignored in many cases.
Summary of the invention
It is a kind of based on operation covariant the technical problem to be solved by the present invention is in view of the above shortcomings of the prior art, provide
The machine tool chief axis spare part prediction technique of analysis realizes the Accurate Prediction to machine tool chief axis spare part.
A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance, comprising the following steps:
Step 1, the historical failure data for extracting main shaft of numerical control machine tool and the operation covariant phase for influencing part life
Pass factor, method particularly includes:
The interval time of machine tool chief axis failure is collected, and the time between failures is ranked up；To lathe master
The movement of axis is analyzed, while according to the summary of experience of fault in production data and maintenance personal, primarily determining influence main shaft
The operation covariant factor of failure, and run covariant factor to it and carry out quantitative expression；
When the machine tool chief axis fault data includes that main shaft of numerical control machine tool breaks down, collected main shaft failure is sent out for the first time
Raw time, the fault data calculated as numerical value；
The operation covariant factor, the factor that the reliability of components has an impact when for equipment operation, for not
With machinery equipment institute collection analysis influence factor it is also not identical, specific equipment will have according in the true working order of lathe
Body analysis；
Step 2, the influence for considering running environment covariant factor, use ratio risk model are established needed for equipment component
The reliability model of spare part, method particularly includes:
Shown in the following formula of Reliability Function for considering the proportional hazard model of running environment covariant factor:
Wherein, ziFor the mean value of each covariant relevant to equipment component, n is to influence component failure correlation height
Covariant number；βiThe regression parameter of reliability model is influenced to define each covariant, most by Partial likelihood
Bigization obtains βiThe estimation of parameter；R (t, z) is the Reliability Function for considering the proportional hazard model of covariant, R0It (t) is equipment
The basic reliability of components, t are the interval time before equipment component breaks down；
The failure rate function for considering the proportional hazard model of running environment covariant factor, shown in following formula:
Wherein, λ (t, z) is the failure rate function for considering the proportional hazard model of covariant, λ0It (t) is equipment component
Basic failure rate indicates the covariant coefficient of discharge and the covariant mean value sum of products that influence reliability；
Step 3, according to the characteristics of fault data and operation covariant influence, verifying use proportional hazards regression models
The correctness of the reliability model of spare part needed for equipment component is established, while covariant is screened based on Data Analysis Software SPSS
Amount, and determine the regression coefficient value of final covariant；
It is described to verify the correct of the reliability model for using proportional hazards regression models to establish spare part needed for equipment component
Property, it is verified using trend test and the serial correlation method of inspection；The trend test is by drawing the accumulative event of components
The relational graph of barrier frequency and accumulative fault time judges；The serial correlation, which is upchecked, draws components d-1
The relational graph of secondary time between failures and the d times time between failures judges；
The regression coefficient value of the screening covariant and determining final covariant method particularly includes: processing covariant number
According to when, all covariant quantized value and fault time value be input to analysis software SPSS in, with proportion risk regression
Model analysis obtains covariant regression coefficient table, then carries out significance test respectively to each covariant, and it is aobvious to observe each covariant
Whether work property meets 0.1 significance test, screens covariant and determines the regression coefficient value of final covariant；
Step 4, using renewal process model, calculate components that the fault data of unrepairable is independently distributed when specific
Between number of faults in section, and then obtain the predicted quantity of spare part needed for components；
For can not Awaiting Parts take the maintenance mode directly replaced, using renewal process model calculate special time period
Interior number of faults；For the renewal process of non-repair system, if equipment component operating time t is too long, operating
Equipment component several times is needed replacing in time, then considers the desired value H for the equipment component update times that covariant influencess
(t), shown in following formula:
Wherein, E (N (t)) is the desired value of fault data, and N (t) is the equipment component occurred in specific operation time t
Update times, and assume stochastic variable Xi′, i ' > 1 be there are out-of-service time when covariant, variable be it is independent and
With common distribution F (t), Fn′(t) be F (t) n ' times of convolution,For the average time between failures that can not repair spare part, σ
It (T) is the standard deviation of time between failures；
The average time between failures that spare part can not be repairedWith the following formula of calculating of the standard deviation sigma (T) of fault time
It is shown:
Wherein, α and β is respectively the dimensional parameters and form parameter for considering the reliability model of covariant, andβ=β0, α0And β0The dimensional parameters and shape ginseng of the reliability model of the benchmark of covariant are not considered respectively
Number,
The time span range of the equipment component operating time t is very big, and according to central-limit theorem, N (t) obeys close
Like normal distribution, then in operation between required spare part quantitative value N in ttShown in following formula:
Wherein, φ-1It (p) is the inverse function of normal function, p is spare part fraction.
The beneficial effects of adopting the technical scheme are that provided by the invention a kind of based on operation covariant point
The machine tool chief axis spare part prediction technique of analysis, establishes reliability model based on proportional hazard model, simultaneously for can not repair zero
Component carries out the prediction of its required spare part using renewal process theoretical analysis method, flat relative to other prediction techniques such as index
Sliding method for Croston method etc., can preferably judge that the quantity of spare part needed for components becomes with the reliability that fault data changes
The prediction model of gesture, proposition has more reference value.Meanwhile point of component failure data is carried out with analysis method of the invention
Analysis, the reliability model of spare part needed for the analysis of trend of energy real-time tracking fault data goes out, while with more new model
The predicted quantity of spare part needed for theory deduction goes out, improves the accuracy of prediction data, reduces the amount of storage of equipment and spare part, from
And significantly reduce the operation cost of enterprise.
Detailed description of the invention
Fig. 1 is a kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance provided in an embodiment of the present invention
Flow chart；
Fig. 2 is the trend test figure of bearing fault data provided in an embodiment of the present invention；
Fig. 3 is that the serial correlation of bearing fault data provided in an embodiment of the present invention examines figure；
Fig. 4 is the accumulative survival comparison diagram of domestic spare part provided in an embodiment of the present invention and import spare part；
Fig. 5 is the risk function comparison diagram of domestic spare part provided in an embodiment of the present invention and import spare part；
Failure rate function comparison diagram when Fig. 6 is consideration covariant provided in an embodiment of the present invention and does not consider covariant；
Fig. 7 is consideration covariant provided in an embodiment of the present invention and the comparison diagram for not considering spare part prediction when covariant.
In figure, 1, domestic bearing (not considering covariant)；2, imported bearing.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
The present embodiment is by taking the cylinder roller bearing of certain main shaft of numerical control machine tool as an example, using of the invention based on operation covariant
The machine tool chief axis spare part prediction technique of analysis carries out the prediction of the machine tool chief axis spare part.
Cylinder roller bearing is superfinishing close fit workpiece in machine-tool spindle system, is born simultaneously during spindle processing
Dead load and dynamic loading, and the frequent adjustment of continuous variation and the main shaft positive and negative rotation due to tool feeding amount, receiving
Axial load and radial load change greatly immediately, so its failure rate occupy the first in machine-tool spindle system.
A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance, as shown in Figure 1, comprising the following steps:
Step 1, the historical failure data for extracting main shaft of numerical control machine tool and the operation covariant phase for influencing part life
Pass factor, method particularly includes:
The interval time of machine tool chief axis failure is collected, and the time between failures is ranked up；To lathe master
The movement of axis is analyzed, while according to the summary of experience of fault in production data and maintenance personal, primarily determining influence main shaft
The operation covariant factor of failure, and run covariant factor to it and carry out quantitative expression；
When machine tool chief axis fault data includes that main shaft of numerical control machine tool breaks down, when collected main shaft failure occurs for the first time
Between, as the fault data of numerical value calculating；
Run covariant factor, the factor that the reliability of components has an impact when for equipment operation, for different
The influence factor of machinery equipment institute collection analysis is not also identical, and specific equipment will specifically divide according in the true working order of lathe
Analysis；
For bearing, failure generation is mainly influenced by its inherent reliability, but external running environment because
Element can accelerate or slow down the period of failure generation.In the present embodiment, data acquisition produces vehicle with certain enterprise production disk-like accessory
Between machine failure data be research object, according to the summary of experience of fault in production data and maintenance personal, determine operation covariant
Amount factor is mainly environment temperature WD, processing dust FC, worker's qualification CZ and components source LY.
Processing dust has a great impact to processing precision of products, for its quantitative expression, mainly surveys with dust
Instrument is measured to be acquired data.Components source is broadly divided into domestic part and import parts, and being mainly manifested in machining accuracy has difference.
The quantized values of domestic component are set to 0, the quantized values of imported equipments and parts are set to 1.The height and lathe of the technical ability of operator
The failure rate to break down has direct relationship, and the horizontal high people's quantized values of operation are set to 1, the amount of the low people of technical level
Change numerical value and is set to 0.The variation of temperature can also generate very big shadow to the cooperation precision and machining state of machine tool chief axis and bearing
It rings.
In the present embodiment, data be certain machine tool plant's processing workshop production scene operation note volume and maintenance record list statistics and
Come.It is mainly derived from different machining areas, is divided into 1 and 2 machining areas.1 is mainly roughing process, this region processing dust
It is more；2 be mainly finishing step, this region processing dust is less, but processing temperature is slightly higher.Table 1 is 16 groups of bearing fault hairs
Locating running environment is horizontal when raw, while re-starting sequence according to time between failures TTF, and record covariant at that time
The magnitude size of amount.
1 cylinder roller bearing TTF of table and covariant magnitude
Step 2, the influence for considering running environment covariant factor, use ratio risk model are established needed for equipment component
The reliability model of spare part, method particularly includes:
Shown in the following formula of Reliability Function for considering the proportional hazard model of running environment covariant factor:
Wherein, ziFor the mean value of each covariant relevant to equipment component, n is to influence component failure correlation height
Covariant number；βiThe regression parameter of reliability model is influenced to define each covariant, most by Partial likelihood
Bigization obtains βiThe estimation of parameter；R (t, z) is the Reliability Function for considering the proportional hazard model of covariant, R0It (t) is equipment
The basic reliability of components, t are the interval time before equipment component breaks down；
The failure rate function for considering the proportional hazard model of running environment covariant factor, shown in following formula:
Wherein, λ (t, z) is the failure rate function for considering the proportional hazard model of covariant, λ0It (t) is equipment component
Basic failure rate indicates the covariant coefficient of discharge and the covariant mean value sum of products that influence reliability；
Step 3, according to the characteristics of fault data and operation covariant influence, verifying use proportional hazards regression models
The correctness of the reliability model of spare part needed for equipment component is established, while covariant is screened based on Data Analysis Software SPSS
Amount, and determine the regression coefficient value of final covariant；
It is described to verify the correct of the reliability model for using proportional hazards regression models to establish spare part needed for equipment component
Property, it is verified using trend test and the serial correlation method of inspection；The trend test is by drawing the accumulative event of components
The relational graph of barrier frequency and accumulative fault time judges；The serial correlation, which is upchecked, draws components d-1
The relational graph of secondary time between failures and the d times time between failures judges；
The regression coefficient value of the screening covariant and determining final covariant method particularly includes: processing covariant number
According to when, all covariant quantized value and fault time value be input to analysis software SPSS in, with proportion risk regression
Model analysis obtains covariant regression coefficient table, then carries out significance test respectively to each covariant, and it is aobvious to observe each covariant
Whether work property meets 0.1 significance test, screens covariant and determines the regression coefficient value of final covariant；
Should have two conditions: influence of the generation of 1 failure by environment covariant using proportional hazard model；2. therefore
Barrier time of origin meets independent same distribution.In order to confirm that fault data meets independent identically distributed it is assumed that the present embodiment uses
Gesture is examined and serial correlation is examined to be proved.The trend test of bearing fault data is as shown in Fig. 2, its abscissa is axis
The accumulative failure frequency held, ordinate are accumulative fault time.As can be seen from the figure the relational graph obtained is similar to one
The characteristics of straight line, then may determine that, trend is not present in the generation of time between failures, meet with distribution.Serial correlation inspection
Test as shown in figure 3, obtained scatter plot be it is mixed and disorderly unordered, illustrate the fault data of cylinder roller bearing without sequence correlation, therefore
The time point that barrier occurs is mutually independent.By the analysis of graphic-arts technique, the time between failures for obtaining bearing is to meet independence
With distribution.It is therefore possible to use proportional hazard model establishes the reliability model of bearing.
It is as shown in table 2 by analyzing the covariant regression coefficient that software SPSS is calculated in the present embodiment:
2 covariant regression coefficient table of table
In table, B is the regression coefficient value for running covariant, and SE is the standard error of the regression coefficient of running environment covariant
Value, Sig are the significance of running environment covariant, and numerical value is less than or equal to illustrate bearing covariant confidence level when 0.1
Pass through 0.1 significance test, show that its influence to the time between failures of bearing is significant, the range of calculating should be included in.
By analyzing table 2, four covariant regression coefficient values are observed, it can be seen that FC, WD and CZ's
Sig value is both greater than 0.1, does not meet 0.1 significance test, shows these three covariants to the time between failures of bearing
It influences smaller.Sig=0.066≤0.1 of factor LY shows that spare part source impact is significant.The present embodiment is to association as shown in Figure 4
The accumulative survival function and risk function as shown in Figure 5 of variables L Y is analyzed, and proves that spare part source difference is right with this
The influence of the fault time of bearing is different.
Figure 4, it is seen that domestic 1 spare part of bearing is standby relative to imported bearing 2 under identical time between failures
The time-to-live of part is small, adds up survival difference within the time of 3000h to 4000h and reaches maximum.As can be seen from Figure 5 tired
In the curvilinear function for counting risk, relative risk is gradually increased with the increase of fault time, domestic 1 failure rate of bearing and import axis
2 failure rates are held compared to significantly higher, illustrate machine bearing service stage in later period domestic spare part reliability will well below into
The reliability of mouth spare part.Illustrate that spare part source is larger for the reliability effect of bearing in summary, while by the recurrence system of table 2
Number tables it is found that covariant LY regression coefficient value βi=1.487.
Step 4, using renewal process model, calculate components that the fault data of unrepairable is independently distributed when specific
Between number of faults in section, and then obtain the predicted quantity of spare part needed for components；
For can not Awaiting Parts take the maintenance mode directly replaced, using renewal process model calculate special time period
Interior number of faults；For the renewal process of non-repair system, if equipment component operating time t is too long, operating
Equipment component several times is needed replacing in time, then considers the desired value H for the equipment component update times that covariant influencess
(t), shown in following formula:
Wherein, E (N (t)) is the desired value of fault data, and N (t) is the equipment component occurred in specific operation time t
Update times, and assume stochastic variable Xi′, i ' > 1 be there are out-of-service time when covariant, variable be it is independent and
With common distribution F (t), Fn′(t) be F (t) n ' times of convolution,For the average time between failures that can not repair spare part, σ
It (T) is the standard deviation of time between failures；
The average time between failures that spare part can not be repairedIt is public as follows with the calculating of the standard deviation sigma (T) of fault time
Shown in formula:
Wherein, α and β is respectively the dimensional parameters and form parameter for considering the reliability model of covariant, andβ=β0, α0And β0The dimensional parameters and shape ginseng of the reliability model of the benchmark of covariant are not considered respectively
Number,
The time span range of the equipment component operating time t is very big, and according to central-limit theorem, N (t) obeys close
Like normal distribution, then in operation between required spare part quantitative value N in ttShown in following formula:
Wherein, φ-1It (p) is the inverse function of normal function, p is spare part fraction.
In the present embodiment, the dimensional parameters for not considering to run the Weibull reliable model of covariant are calculated with matlab
α0=2.7727, form parameter β0=4538.9h.Covariant mean value for domestic and imported model spare part is zGC=0, zJK=
1.Assume that the lathe annual working time is 4000h simultaneously, providing spare part fraction is p=95%.For domestic spare part, meter
The dimensional parameters and form parameter for calculating the considerations of obtaining covariant model are respectively as follows:β=β0=
2.7727。
Obtain average time between failures and standard deviation are as follows:
And then the quantity and failure rate function of spare part needed for obtaining the domestic bearing of a machine tool are respectively as follows:
The quantity and failure rate function of spare part needed for a machine tool imported bearing similarly are can be obtained respectively as follows:
As c=1, i.e., when not considering environment covariant, the quantity and failure rate letter of spare part needed for a machine tool bearing
Number are as follows:
The present embodiment gives consideration covariant as shown in Figure 6 and does not consider failure rate function in the case where covariant
The comparison diagram of required spare part quantity in the case that comparison diagram and consideration as shown in Figure 7 consider covariant and do not consider covariant；
From fig. 6 it can be seen that considering that the failure rate of the bearing of environment covariant will be apparently higher than does not consider environment covariant
Situation under amount；The failure rate of domestic spare part will be apparently higher than the failure rate of import spare part in section at the same time simultaneously.
Spare part quantity needed for considering environment covariant as can be seen from Figure 7 will it is obvious it is extra do not consider it is required standby when environment covariant
Number of packages amount；The predicted quantity of domestic spare part is also apparently higher than the predicted quantity of import spare part on the machine tool of equal number.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify to technical solution documented by previous embodiment, or some or all of the technical features are equal
Replacement；And these are modified or replaceed, model defined by the claims in the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (4)
1. a kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance, it is characterised in that: the following steps are included:
Step 1, extract main shaft of numerical control machine tool historical failure data and influence part life operation covariant correlation because
Element, method particularly includes:
The interval time of machine tool chief axis failure is collected, and the time between failures is ranked up；To machine tool chief axis
Movement is analyzed, while according to the summary of experience of fault in production data and maintenance personal, primarily determining influence main shaft failure
Operation covariant factor, and it is run covariant factor carry out quantitative expression；
When the machine tool chief axis fault data includes that main shaft of numerical control machine tool breaks down, when collected main shaft failure occurs for the first time
Between, as the fault data of numerical value calculating；
The operation covariant factor, the factor that the reliability of components has an impact when for equipment operation, for different
The influence factor of machinery equipment institute collection analysis is not also identical, and specific equipment will specifically divide according in the true working order of lathe
Analysis；
Step 2, the influence for considering running environment covariant factor, use ratio risk model establish spare part needed for equipment component
Reliability model；
Step 3, according to the characteristics of fault data and operation covariant influence, verifying using proportional hazards regression models establish
The correctness of the reliability model of spare part needed for equipment component, while covariant is screened based on Data Analysis Software SPSS, and
Determine the regression coefficient value of final covariant；
Step 4, using renewal process model, calculate components that the fault data of unrepairable is independently distributed in special time period
Interior number of faults, and then obtain the predicted quantity of spare part needed for components.
2. a kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance according to claim 1, feature
It is: the step 2 method particularly includes:
Shown in the following formula of Reliability Function for considering the proportional hazard model of running environment covariant factor:
Wherein, ziFor the mean value of each covariant relevant to equipment component, n is to influence the high association of component failure correlation
Variable number；βiThe regression parameter of reliability model is influenced to define each covariant, passes through the maximization of Partial likelihood
Obtain βiThe estimation of parameter；R (t, z) is the Reliability Function for considering the proportional hazard model of covariant, R0It (t) is equipment zero
The basic reliability of part, t are the interval time before equipment component breaks down；
The failure rate function for considering the proportional hazard model of running environment covariant factor, shown in following formula:
Wherein, λ (t, z) is the failure rate function for considering the proportional hazard model of covariant, λ0It (t) is the basic of equipment component
Failure rate indicates the covariant coefficient of discharge and the covariant mean value sum of products that influence reliability.
3. a kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance according to claim 1, feature
Be: the reliability model of spare part needed for equipment component is established in the verifying described in step 3 using proportional hazards regression models
Correctness, verified using trend test and the serial correlation method of inspection；The trend test is by drawing components
The relational graph of accumulative failure frequency and accumulative fault time judges；The serial correlation, which is upchecked, draws components
The relational graph of the d-1 times time between failures and the d times time between failures judges；
The regression coefficient value of the screening covariant and determining final covariant method particularly includes: processing covariant data
When, all covariant quantized value and fault time value are input in analysis software SPSS, with proportion risk regression mould
Type analysis obtains covariant regression coefficient table, then carries out significance test respectively to each covariant, and it is significant to observe each covariant
Property whether meet 0.1 significance test, screen covariant and determine the regression coefficient value of final covariant.
4. a kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance according to claim 2, feature
It is: the step 4 method particularly includes:
For can not Awaiting Parts take the maintenance mode directly replaced, using renewal process model calculate special time period in
Number of faults；For the renewal process of non-repair system, if equipment component operating time t is too long, in operation between
Equipment component several times is inside needed replacing, then considers the desired value H for the equipment component update times that covariant influencess(t), such as
Shown in lower formula:
Wherein, E (N (t)) is the desired value of fault data, and N (t) is that the equipment component occurred in specific operation time t updates
Number, and assume stochastic variable Xi′, i ' > 1 is there are out-of-service time when covariant, and variable is independent and has
Common distribution F (t), Fn′(t) be F (t) n ' times of convolution,For the average time between failures that can not repair spare part, σ (T) is
The standard deviation of time between failures；
The average time between failures that spare part can not be repairedWith the following formula institute of calculating of the standard deviation sigma (T) of fault time
Show:
Wherein, α and β is respectively the dimensional parameters and form parameter for considering the reliability model of covariant, andβ=
β0, α0And β0Do not consider the dimensional parameters and form parameter of the reliability model of the benchmark of covariant respectively,
The time span range of the equipment component operating time t is very big, and according to central-limit theorem, N (t) is obeying approximation just
State distribution, then in operation between required spare part quantitative value N in ttShown in following formula:
Wherein, φ-1It (p) is the inverse function of normal function, p is spare part fraction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009454.XA CN109086945A (en) | 2018-08-31 | 2018-08-31 | A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009454.XA CN109086945A (en) | 2018-08-31 | 2018-08-31 | A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109086945A true CN109086945A (en) | 2018-12-25 |
Family
ID=64840494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811009454.XA Pending CN109086945A (en) | 2018-08-31 | 2018-08-31 | A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086945A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543615A (en) * | 2019-09-05 | 2019-12-06 | 国网湖南省电力有限公司 | Risk factor interaction analysis method based on SPSS explanation structure model |
| CN112528510A (en) * | 2020-12-17 | 2021-03-19 | 中国航空工业集团公司成都飞机设计研究所 | Method for predicting repairable aviation material spare parts based on life-extinction process model |
| CN112580812A (en) * | 2019-09-27 | 2021-03-30 | 北京国双科技有限公司 | Model training method, inventory safety early warning method, device, equipment and medium |
| CN113345525A (en) * | 2021-06-03 | 2021-09-03 | 谱天（天津）生物科技有限公司 | Analysis method for reducing influence of covariates on detection result in high-throughput detection |
| CN116861218A (en) * | 2023-07-25 | 2023-10-10 | 上海华菱电站成套设备股份有限公司 | Mine winder key equipment state monitoring early warning system |
| CN117111589A (en) * | 2023-10-23 | 2023-11-24 | 中国机械总院集团云南分院有限公司 | Fault diagnosis method for numerical control machine tool control system based on Petri network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2003216757A1 (en) * | 2002-04-04 | 2003-10-20 | Licentia Oy | A method for gene mapping from genotype and phenotype data |
| CN102179722A (en) * | 2010-12-20 | 2011-09-14 | 西安瑞特快速制造工程研究有限公司 | Estimation method for operational reliability of numerical control machine based on proportional hazards model |
| CN108241917A (en) * | 2016-12-26 | 2018-07-03 | 北京天源科创风电技术有限责任公司 | The appraisal procedure and device of part reliability |
-
2018
- 2018-08-31 CN CN201811009454.XA patent/CN109086945A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2003216757A1 (en) * | 2002-04-04 | 2003-10-20 | Licentia Oy | A method for gene mapping from genotype and phenotype data |
| CN102179722A (en) * | 2010-12-20 | 2011-09-14 | 西安瑞特快速制造工程研究有限公司 | Estimation method for operational reliability of numerical control machine based on proportional hazards model |
| CN108241917A (en) * | 2016-12-26 | 2018-07-03 | 北京天源科创风电技术有限责任公司 | The appraisal procedure and device of part reliability |
Non-Patent Citations (1)
| Title |
|---|
| 王晓燕: "基于故障相关性分析的主轴系统关键备件需求预测研究", 《中国博士学位论文全文数据库 工程科技I辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543615A (en) * | 2019-09-05 | 2019-12-06 | 国网湖南省电力有限公司 | Risk factor interaction analysis method based on SPSS explanation structure model |
| CN112580812A (en) * | 2019-09-27 | 2021-03-30 | 北京国双科技有限公司 | Model training method, inventory safety early warning method, device, equipment and medium |
| CN112528510A (en) * | 2020-12-17 | 2021-03-19 | 中国航空工业集团公司成都飞机设计研究所 | Method for predicting repairable aviation material spare parts based on life-extinction process model |
| CN112528510B (en) * | 2020-12-17 | 2022-05-27 | 中国航空工业集团公司成都飞机设计研究所 | Method for predicting repairable aviation material spare parts based on life-extinction process model |
| CN113345525A (en) * | 2021-06-03 | 2021-09-03 | 谱天（天津）生物科技有限公司 | Analysis method for reducing influence of covariates on detection result in high-throughput detection |
| CN116861218A (en) * | 2023-07-25 | 2023-10-10 | 上海华菱电站成套设备股份有限公司 | Mine winder key equipment state monitoring early warning system |
| CN117111589A (en) * | 2023-10-23 | 2023-11-24 | 中国机械总院集团云南分院有限公司 | Fault diagnosis method for numerical control machine tool control system based on Petri network |
| CN117111589B (en) * | 2023-10-23 | 2024-01-02 | 中国机械总院集团云南分院有限公司 | Fault diagnosis method for numerical control machine tool control system based on Petri network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086945A (en) | A kind of machine tool chief axis spare part prediction technique based on operation analysis of covariance | |
| Zhang et al. | Equipment energy consumption management in digital twin shop-floor: A framework and potential applications | |
| US20170243122A1 (en) | Analysis apparatus and analysis system | |
| Lv et al. | An investigation into methods for predicting material removal energy consumption in turning | |
| Sun et al. | Enhancing cutting tool sustainability based on remaining useful life prediction | |
| CN102848266B (en) | Machine tool spindle accuracy prediction method | |
| US20170139398A1 (en) | Abnormality analysis system and analysis apparatus | |
| CN108614522B (en) | Numerically-controlled machine tool military service process axis system energy efficiency on-line monitoring method | |
| Cai et al. | Task-oriented energy benchmark of machining systems for energy-efficient production | |
| CN104281090A (en) | Power modeling method for numerical control machine tool system | |
| CN103817153B (en) | A kind of iron and steel enterprise bar steel rolling roller management System and method for | |
| CN105955198B (en) | Lathe work step energy-consumption monitoring method based on least-squares iteration algorithm | |
| CN112526931B (en) | Quality control method for boring process of marine diesel engine body hole system | |
| Seevers et al. | Automatic time series segmentation as the basis for unsupervised, non-intrusive load monitoring of machine tools | |
| CN113126563A (en) | Numerical control machine tool data management system and method | |
| Sachin et al. | Six sigma methodology for improving manufacturing process in a foundry industry | |
| Kianinejad et al. | Investigation into energy efficiency of outdated cutting machine tools and identification of improvement potentials to promote sustainability | |
| CN112559591B (en) | Outlier detection system and detection method for cold roll manufacturing process | |
| Lv et al. | Comparison of different approaches for predicting material removal power in milling process | |
| Cao et al. | A reuse-oriented redesign method of used machine tool based on matter-element theory | |
| Willoughby et al. | A holistic approach to quantifying and controlling the accuracy, performance and availability of machine tools | |
| Masalimov | A machine learning based approach to autogenerate diagnostic models for CNC machines | |
| CN207953178U (en) | One kind remanufacturing vertical machining centre | |
| Ding et al. | Development of an innovative ERWC approach to sustainable manufacturing with application to design of an energy-resource efficient CNC centreless grinding | |
| Johansson et al. | Context driven remaining useful life estimation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |
|
| RJ01 | Rejection of invention patent application after publication |