CN109708890A - Each part life period quantitative Diagnosis scheme in automobile speed variator bearing - Google Patents
Each part life period quantitative Diagnosis scheme in automobile speed variator bearing Download PDFInfo
- Publication number
- CN109708890A CN109708890A CN201811588388.6A CN201811588388A CN109708890A CN 109708890 A CN109708890 A CN 109708890A CN 201811588388 A CN201811588388 A CN 201811588388A CN 109708890 A CN109708890 A CN 109708890A
- Authority
- CN
- China
- Prior art keywords
- speed changer
- bearing
- test
- bearings
- test speed
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 63
- 230000001133 acceleration Effects 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 230000004927 fusion Effects 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 13
- 230000009467 reduction Effects 0.000 claims abstract description 13
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 7
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 239000000523 sample Substances 0.000 claims description 22
- 230000010355 oscillation Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 14
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound 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 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 9
- 229910000831 Steel Inorganic materials 0.000 claims description 6
- 239000010959 steel Substances 0.000 claims description 6
- 239000000725 suspension Substances 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000002245 particle Substances 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000002405 diagnostic procedure Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 241000606643 Anaplasma centrale Species 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 2
- 230000007257 malfunction Effects 0.000 abstract description 2
- 238000004088 simulation Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 230000006378 damage Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 description 1
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- G01M13/045—Acoustic or vibration analysis
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Each part life period quantitative Diagnosis scheme in a kind of present invention relates particularly to simulation effects good, the accurate automobile speed variator bearing of accident analysis.The vibration acceleration signal of bearing passes through the decomposition and reconstruction of EMD method, can effectively inhibit to the noise in automobile speed variator bearing signal, enhance and highlight the useful component in signal；Signal after EMD noise reduction carries out Alpha Stable distritation respectively and extracts with multi-fractal features and sufficiently combined Alpha Stable distritation and the respective advantage of multi-fractal using core principle component analysis progress Fusion Features, improves the precision and efficiency of fault diagnosis；The test gearbox of different faults degree bearing related data in testing stand as training sample establishes PSO-LSSVM model, the related data of tested gearbox can be brought into trained PSO-LSSVM model, to which analysis obtains the malfunction of the position of bearings and bearing broken down in tested gearbox, diagnosis efficiency is high and accuracy is high.
Description
The application be application No. is: 201710678357.9, the applying date: 2017-08-09, patent name " a kind of pair of vapour
The divisional application of the patent of invention of the method for vehicle transmission bearing failure progress quantitative Diagnosis ".
Technical field
The present invention relates to automotive transmission fault diagnosis technologies, in particular to each part life week in automobile speed variator bearing
Phase quantitative Diagnosis scheme.
Background technique
There are many rolling bearing type used in automotive transmission, and quantity is more, such as deep groove ball bearing, taper roller
Bearing, bicylindrical roller bearing etc., the various bearings in speed changer usually continue in the bad working environments of speed change, heavy duty and high temperature
, easily there is fatigue damage in operation.If these damages are handled not in time, will lead to bearing function it is entirely ineffective so that cause one
The chain reaction of series gently then causes serious economic loss so that entire automobile cisco unity malfunction, heavy then can lead to disaster
The casualties of property.Currently, the nuisance fault such as spot corrosion, crackle or scratch etc. due to automobile speed variator bearing fail to send out in time
Accident is commonplace caused by existing, therefore it is very necessary that automobile speed variator bearing failure, which is monitored and is diagnosed,.
In the prior art, based on vibration analysis, common fault signature mentions the research of automobile speed variator bearing fault diagnosis
Method such as the methods of statistical parameter, wavelet transformation, the distribution of Tomi Ungerer Willie is taken to have the shortcomings that respective, if being applied to practical work
Journey, when and to will lead to diagnostic result unstable and generate " mistaken diagnosis is failed to pinpoint a disease in diagnosis " phenomenon of failure；Secondly, existing research method is most
Number does not consider the factors during automobile actual travel, such as guideway irregularity, load variation, velocity variations to automobile change
The influence of fast device bearing vibration signal causes the on-line monitoring effect of automobile speed variator bearing undesirable.Therefore, it is necessary to design one
Kind can accurate simulated automotive actual travel condition testing stand, and use suitable analysis and diagnosis method, to test data into
Row analysis, to improve the precision of bearing failure diagnosis.
Summary of the invention
In view of the above-mentioned problems, a kind of it is an object of the present invention to provide simulation effects good, the accurate automotive transmission of accident analysis
Each part life period quantitative Diagnosis scheme in bearing.
For achieving the above object, the technical scheme adopted by the invention is that: each zero in a kind of automobile speed variator bearing
Part life cycle quantitative Diagnosis scheme, the automotive transmission include test speed changer and tested speed changer, test speed changer
Mountable on bearing test-bed with tested speed changer, the bearing test-bed includes pedestal, is arranged on pedestal liftable
Three-coordinate type electromagnetic oscillation device, setting is clamped by the truss-like that multiple channel steels or rectangle steel are spliced to form on electromagnetic oscillation device
Tooling, position, size and the vertical stiffness of the installation bolt hole of corresponding position setting on clamping tooling and the peace of test speed changer
It fills bolt hole to be adapted, the structure of the test speed changer is consistent with tested automotive transmission structure, and internal multiple setting axis
The position held has one or more faulty bearings；
It is connected between the pedestal and electromagnetic oscillation device by air spring, vertical damper, the air inlet of air spring
Mouth, gas outlet are connect with air intake control valve, gas bleeder valve respectively, and the air intake control valve is connect with electric air pump, the air
The vertical stiffness of spring is consistent with the vertical stiffness of tested automotive suspension, the damped coefficient of the vertical damper and tested
The vertical damped coefficient of automotive suspension is consistent；
The input shaft of the test speed changer and the output end of torque loading device connect, and torque loading device includes electronic
Machine, the output end of motor are successively connect with torque sensor, fixed tooth than the input terminal of retarder, and fixed tooth is than retarder
The input axis connection of output end and test speed changer；Speed probe is also set up on the output end of the motor；
The output shaft of the test speed changer is connect with inertia load device, and inertia load device includes mutually only with pedestal
The auxiliary support set is erected, driving gear set is installed, driving gear set is by a pair of of spur gear wheel or a pair of of circle on auxiliary support
Bevel gear is constituted, and the driving gear of driving gear set is mounted on the output shaft of test speed changer, the driven tooth of driving gear set
Wheel is connect by jackshaft with rotating wheel, and rotating wheel is mounted on auxiliary support by bearing, is also set up and is revolved on auxiliary support
The adaptable hydraulic brake caliper of runner size；
Paste vibration acceleration sensor in the outer ring for the multiple bearings installed in the test speed changer；The central processing
Device respectively with the hydraulic cylinder control valve of hydraulic brake caliper, speed probe, torque sensor, motor, test speed changer
Gearshift controller, multiple vibration acceleration sensors, air intake control valve, gas bleeder valve, electric air pump, electromagnetic oscillation device communication link
It connects；
It is characterized by: the diagnostic method the following steps are included:
Faulty bearings are set by the bearing for testing one or more positions in speed changer, vibration is pasted in the outer ring of faulty bearings
Dynamic acceleration transducer, then sequentially follows the steps below:
A. the central processing unit control electromagnetic oscillation device generates specific amplitude and vibration frequency；Central processing simultaneously
Device control motor, gearshift controller make the output shaft output specific rotation speeds for testing speed changer；The output shaft for testing speed changer is defeated
Out while specific rotation speeds, central processing unit controls brake caliper and applies braking moment to rotating wheel, makes to test the defeated of speed changer
Shaft is by specific load torque；The vibration acceleration signal sample of vibration acceleration sensor acquisition faulty bearings；It will adopt
The sample collected carries out EMD adaptive decomposition as training sample, to the vibration acceleration signal x (t) in training sample, point
Solution method is as follows:
N is the number of the IMF component decomposited in above formula；CjRepresent j-th of IMF component, j=1,2,3 ..., n；rnIt is residual
Remaining component；
B. it decomposes to obtain n C by step ajAfter component, each C is calculated separatelyjThe kurtosis value of (j=1,2,3 ..., n),
Choose two C of kurtosis value maximum and kurtosis value time greatlyjCarry out linear superposition, it is obtaining that the feature after EMD noise reduction highlights plus
Speed signal, the acceleration signal that the feature that then will acquire highlights are equally divided into m sections according to time span, by different duration sections
Signal be denoted as S1-Sm；
C. Alpha Stable distritation parameter Estimation is carried out respectively to each section of the S1-Sm in step b and calculate its probability density letter
Number extracts characteristic index α (0 α≤2 <), symmetric parameter β (- 1≤β≤1), coefficient of dispersion γ (γ > 0), location parameter δ (- ∞
≤ δ≤∞) and probability density function extreme value h (h > 0) totally 5 Alpha Stable distritation features；
D. multi-fractal is carried out respectively to each section of the S1-Sm in step b and remove trend fluction analysis, extract S1-Sm respectively
5 multi-fractal features: the singular index α of maximum fluctuationmax, the singular index α of minimal ripplemin, multifractal spectra spectrum width
Δ α=αmax-αmin, the corresponding singular index α of multifractal spectra extreme point0(fmax=f (α0), α0∈[αmin, αmax]), multiple point
Shape composes probability subset fractal dimension difference Δ f=f (αmax)-f(αmin)；
E. the respective 5 Alpha Stable distritations feature of the S1-Sm being calculated according to step c, step d, 5 multiple point
Shape feature carries out serial combination, obtains the respective assemblage characteristic collection of S1-Sm (α, beta, gamma, δ, h, α0, αmin, αmax, Δ α, Δ f)；
F. using radial base as kernel function, the assemblage characteristic collection in step e is carried out using core principle component analysis method (KPCA)
Dimensionality reduction fusion accumulates contribution rate according to variance and is greater than or equal to 95% selection core pivot, obtains new pivot fusion feature collection；
G. integrated using the pivot fusion feature obtained in step f as input sample, using particle swarm optimization algorithm to minimum two
Two core parameters (regularization parameter λ and kernel parameter σ) for multiplying support vector machines optimize, with the optimized parameter of acquisition
Establish PSO-LSSVM model；
H. test speed changer is changed to speed changer to be measured, speed changer domestic demand to be measured one or more to be tested is to be measured
Vibration acceleration sensor is pasted in the outer ring of bearing, then repeats step a to step f, and vibrations one or more in step f are added
The respective pivot fusion feature collection of S1-Sm of the collected bearing to be measured of velocity sensor is brought into trained PSO-
State classification is carried out in LSSVM model；Diagnosis terminates.
It, can be with the beneficial effects of the present invention are the decomposition and reconstruction that: the vibration acceleration signal of bearing passes through EMD method
Effectively the noise in automobile speed variator bearing signal is inhibited, enhances and highlight the useful component in signal；It is dropped through EMD
Signal after making an uproar is carried out Alpha Stable distritation respectively and extracts with multi-fractal features and melted using core principle component analysis progress feature
It closes, can sufficiently combine Alpha Stable distritation and the respective advantage of multi-fractal, maximize the validity of feature, improve event
Hinder diagnosis precision and efficiency, with various different faults types, different faults degree bearing test gearbox in testing stand
The related data of middle acquisition establishes basis PSO-LSSVM model, and tested gearbox acquires related data in testing stand and is brought into
In the PSO-LSSVM model built up, so that analysis obtains the position of bearings broken down in tested gearbox and bearing
Fault degree, diagnosis efficiency is high and accuracy is high.
Detailed description of the invention
Fig. 1 is bearing test-bed structure principle chart；
Fig. 2 is bearing test-bed control circuit schematic diagram；
Fig. 3 is to carry out EMD noise reduction flow chart to vibration acceleration signal；
Fig. 4 is that Alpha Stable distritation parameter Estimation and more is carried out to feature highlights after EMD noise reduction acceleration signal
Ten feature schematic diagrames that point shape goes trend fluction analysis to extract again；
Fig. 5 is the work flow diagram that bearing fault quantitative Diagnosis is carried out using bearing test-bed.
Specific embodiment
Liftable Three-coordinate type electricity is arranged on pedestal 1 for a kind of bearing test-bed as Figure 1-Figure 2, including pedestal 1
The truss-like clamping tooling 3 being spliced to form by multiple channel steels or rectangle steel, folder are arranged on electromagnetic oscillation device 2 for magnetic vibration device 2
Hold position, size and the vertical stiffness of the installation bolt hole that corresponding position in tooling 3 is arranged and the installation bolt of test speed changer 4
Hole is adapted；The structure of the test speed changer 4 is consistent with tested automotive transmission structure, and the position of internal multiple setting bearings
Setting has one or more faulty bearings；
It is connected between the pedestal 1 and electromagnetic oscillation device 2 by air spring 11, vertical damper 12, air spring
11 air inlet, gas outlet are connect with air intake control valve 13, gas bleeder valve 14 respectively, the air intake control valve 13 and electronic gas
15 connection of pump；Before being tested, central processing unit 5 controls air intake control valve 13, gas bleeder valve 14, electric air pump 15, makes air
The vertical stiffness of spring 11 is consistent with the vertical stiffness of tested automotive suspension, and adjusts the damping system of vertical damper 12
Number, keeps damped coefficient consistent with the vertical damped coefficient of tested automotive suspension；The damped coefficient of vertical damper 12 can be by
It manually adjusts, active vertical damper 12 also can be set, by 5 adjust automatically of central processing unit；
The input shaft of the test speed changer 4 and the output end of torque loading device connect, and torque loading device includes electricity
Motivation 71, the output end of motor 71 are successively connect with torque sensor 72, fixed tooth than the input terminal of retarder 73, fixed tooth
Than the output end of retarder 73 and the input axis connection of test speed changer 4；Revolving speed is also set up on the output end of the motor 71
Sensor 74；
The output shaft of the test speed changer 4 is connect with inertia load device, and inertia load device includes mutual with pedestal 1
The auxiliary support 81 being independently arranged installs driving gear set 82 on auxiliary support 81, and driving gear set 82 is by a pair of of cylindrical straight gear
Wheel or a pair of of conical gear are constituted, and the driving gear of driving gear set 82 is mounted on the output shaft of test speed changer 4, driving cog
The driven gear of wheel group 82 is connect by jackshaft with rotating wheel 83, and rotating wheel 83 is mounted on auxiliary support 81 by bearing,
The hydraulic brake caliper 84 being adapted with 83 size of rotating wheel is also set up on auxiliary support 81,
It pastes vibration and accelerates in the outer ring that the one or more installed in the test speed changer 4 has faulty faulty bearings
Spend sensor 41；The central processing unit 5 respectively with the hydraulic cylinder control valve of hydraulic brake caliper 84, speed probe 74, turn round
Square sensor 72, motor 71, the gearshift controller 42 for testing speed changer 4, multiple vibration acceleration sensors 41, air inlet control
Valve 13, gas bleeder valve 14, electric air pump 15, electromagnetic oscillation device 2 communicate to connect；
It is as shown in Figure 5, each part life period quantitative Diagnosis scheme in automobile speed variator bearing the following steps are included:
Faulty bearings are set by the bearing for testing one or more positions in speed changer 4, the outer ring of faulty bearings is pasted
Different abort situation and fault degree, such as fault bit can be set in vibration acceleration sensor 41, the faulty bearings
Setting can be outer ring, inner ring, roller, retainer respectively, and the fault degree of faulty bearings can be early stage, mid-term, advanced stage respectively；
Then it sequentially follows the steps below:
A. central processing unit 5 controls electromagnetic oscillation device 2 and generates specific amplitude and vibration frequency, electromagnetic oscillation device 2
Vertical direction vibration can only be applied, also can according to need and horizontal and vertical vibration is provided；Central processing unit 5 also controls simultaneously
Motor 71, gearshift controller 42 make the output shaft output specific rotation speeds for testing speed changer 4, and speed probe 74 detects motor
The output revolving speed of 71 output revolving speed guarantee test speed changer 4 is correct；Test the same of the output shaft output specific rotation speeds of speed changer 4
When central processing unit 5 control brake caliper 84 to rotating wheel 83 apply braking moment, make test speed changer 4 output shaft by spy
Fixed load torque；Torque sensor 72 detects the braking torque that brake caliper 84 applies, and guarantee test speed changer 4 is subject to negative
It is correct to carry torque；Actual track can also be imported central processing unit 5, by central processing unit 5 according to real road situation, respectively
Control electromagnetic oscillation device 2, motor 71, brake caliper 84, make ambient vibration parameter, test 4 output shaft of speed changer speed,
The load torque of output shaft matches with actual conditions, keeps test result more acurrate；
The vibration acceleration signal sample of the acquisition faulty bearings of vibration acceleration sensor 41；Using collected sample as
Training sample carries out EMD adaptive decomposition to the vibration acceleration signal x (t) in training sample, and decomposition method is as follows:
N is the number of the IMF component decomposited in above formula；CjRepresent j-th of IMF component, j=1,2,3 ..., n；rnIt is residual
Remaining component；
B. it decomposes to obtain n C by step ajAfter component, each C is calculated separatelyjThe kurtosis value of (j=1,2,3 ..., n),
Choose two C of kurtosis value maximum and kurtosis value time greatlyjCarry out linear superposition, it is obtaining that the feature after EMD noise reduction highlights plus
Speed signal, the acceleration signal that the feature that then will acquire highlights are equally divided into m sections according to time span, by different duration sections
Signal be denoted as S1-Sm；
C. Alpha Stable distritation parameter Estimation is carried out respectively to each section of the S1-Sm in step b and calculate its probability density letter
Number extracts characteristic index α (0 α≤2 <), symmetric parameter β (- 1≤β≤1), coefficient of dispersion γ (γ > 0), location parameter δ (- ∞
≤ δ≤∞) and probability density function extreme value h (h > 0) totally 5 Alpha Stable distritation features；
D. multi-fractal is carried out respectively to each section of the S1-Sm in step b and remove trend fluction analysis, extract S1-Sm respectively
5 multi-fractal features: the singular index α of maximum fluctuationmax, the singular index α of minimal ripplemin, multifractal spectra spectrum width
Δ α=αmax-αmin, the corresponding singular index α of multifractal spectra extreme point0(fmax=f (α0), α0∈[αmin, αmax]), multiple point
Shape composes probability subset fractal dimension difference Δ f=f (αmax)-f(αmin)；
E. the respective 5 Alpha Stable distritations feature of the S1-Sm being calculated according to step c, step d, 5 multiple point
Shape feature carries out serial combination, obtains each section of S1-Sm of assemblage characteristic collection (α, beta, gamma, δ, h, α0, αmin, αmax, Δ α, Δ f)；
F. using radial base as kernel function, the assemblage characteristic collection in step e is carried out using core principle component analysis method (KPCA)
Dimensionality reduction fusion accumulates contribution rate according to variance and is greater than or equal to 95% selection core pivot, obtains new pivot fusion feature collection；
G. integrated using the pivot fusion feature obtained in step f as input sample, using particle swarm optimization algorithm to minimum two
Two core parameters (regularization parameter λ and kernel parameter σ) for multiplying support vector machines optimize, with the optimized parameter of acquisition
Establish PSO-LSSVM model；
H. will test speed changer 4 be changed to speed changer to be measured, by speed changer domestic demand to be measured it is to be tested with test speed changer 4
Vibration acceleration sensor 41 is pasted in the outer ring of the identical one or more bearing to be measured in middle faulty bearings position, then repeats to walk
Rapid a to step f, by step f, each section of S1-Sm of one or more collected bearings to be measured of vibration acceleration sensor 41
Pivot fusion feature collection be brought into trained PSO-LSSVM model and carry out state classification；Diagnosis terminates.
The example carried out according to above-mentioned diagnostic method is as follows: will test the axis of a specific position in speed changer 4 several times
It holds and replaces with outer ring failure (point early stage, 3 kinds of mid-term, advanced stage degree of injury), inner ring failure (early stage, mid-term, advanced stage), rolling
Sub- failure (early stage, mid-term, advanced stage), retainer failure (early stage, mid-term, advanced stage) faulty bearings, every time replacement after, test become
All only one faulty bearings in fast device 4；Test speed changer 4 is mounted on testing stand respectively, carries out step a to step b, it will
The acceleration signal that the vibration acceleration sensor 41 pasted on faulty bearings obtains is equally divided into 5 sections according to the period, accelerates
The total duration for spending signal is 0.3s, and the when a length of 0.06s of every segment signal carries out step c to step f for this 5 segment signal respectively；
Pivot fusion feature calculated in step f is integrated as input sample, using particle swarm optimization algorithm to minimum two
Two core parameters (regularization parameter λ and kernel parameter σ) for multiplying support vector machines optimize, with the optimized parameter of acquisition
Establish PSO-LSSVM model；
Then there are the measured bearings of unknown failure for same position placement one in tested speed changer, by tested speed changer
It is mounted on testing stand, re-starts step a to step b, the EMD noise reduction effect of the step b is as shown in Figure 3；
Acceleration signal after the EMD noise reduction that will acquire is equally divided into 5 sections according to the period, when the measurement of acceleration signal
Between be 0.3s, then a length of 0.06s when every segment signal of mean allocation, is denoted as S1-S5 for the signal of different duration sections, for this 5
Segment signal carries out step c to step f；Alpha Stable distritation parameter is carried out to the S1-S5 that feature highlights after EMD noise reduction to estimate
Meter, and process such as Fig. 4 institute that multi-fractal removes trend fluction analysis is carried out to the S1-S5 that feature highlights after EMD noise reduction
Show；
Wherein S1-S5 calculated assemblage characteristic collection in step e is as shown in table 1:
The assemblage characteristic collection parameter of 1 S1-S5 of table
In step f, merged with assemblage characteristic collection of the core principle component analysis to S1-S5, and accumulated according to variance
Contribution rate is greater than or equal to 95% and chooses core pivot, and obtained core pivot fusion feature is as shown in table 2:
The core pivot fusion feature of 2 S1-S5 of table
Then the pivot fusion feature collection of S1-S5 calculated in step f is brought into trained PSO-LSSVM
State classification is carried out to it in model；Five dimension core pivot fusion features shown in table 2 are input to established PSO-LSSVM
Classify in classifier, classification results are as shown in table 3.
3 classification results of table
According to classification results shown in table 3 it is found that this 5 segment signal of S1-S5 all prompts the test bearing in tested gearbox
Failure mode be bearing outer ring there is earlier damage, according to the above process it is found that test speed changer 4 in be put into inner ring
The bearing of failure, roller failure or retainer failure repeats step a to step g, then can use trained PSO-LSSVM
Model accurately detects the state of each bearing in gearbox to be measured.
Claims (1)
1. each part life period quantitative Diagnosis scheme in a kind of automobile speed variator bearing, the automotive transmission includes test
Speed changer (4) and tested speed changer, test speed changer (4) and tested speed changer is mountable on bearing test-bed, bearing test
Platform includes pedestal (1), is arranged liftable Three-coordinate type electromagnetic oscillation device (2) on pedestal (1), on electromagnetic oscillation device (2)
The truss-like clamping tooling (3) being spliced to form by multiple channel steels or rectangle steel is set, and corresponding position is arranged on clamping tooling (3)
The installation bolt hole of position, size and the vertical stiffness and test speed changer (4) of installing bolt hole is adapted, the test speed change
The structure of device (4) is consistent with tested automotive transmission structure, and the position of internal multiple setting bearings has one or more events
Hinder bearing；
It is connect between the pedestal (1) and electromagnetic oscillation device (2) by air spring (11), vertical damper (12), air
The air inlet of spring (11), gas outlet are connect with air intake control valve (13), gas bleeder valve (14) respectively, the air intake control valve
(13) it is connect with electric air pump (15), the vertical stiffness of the air spring (11) and the vertical stiffness one of tested automotive suspension
It causes, the damped coefficient of the vertical damper (12) is consistent with the vertical damped coefficient of tested automotive suspension；
The input shaft of test speed changer (4) and the output end of torque loading device connect, and torque loading device includes electronic
Machine (71), the output end of motor (71) are successively connect with torque sensor (72), fixed tooth than the input terminal of retarder (73),
Fixed tooth is than the output end of retarder (73) and the input axis connection of test speed changer (4)；The output end of the motor (71)
On also set up speed probe (74)；
The output shaft of test speed changer (4) is connect with inertia load device, and inertia load device includes mutual with pedestal (1)
The auxiliary support (81) being independently arranged installs driving gear set (82) on auxiliary support (81), and driving gear set (82) is by a pair
Spur gear wheel or a pair of of conical gear are constituted, and the driving gear of driving gear set (82) is mounted on the defeated of test speed changer (4)
On shaft, the driven gear of driving gear set (82) is connect by jackshaft with rotating wheel (83), and rotating wheel (83) passes through bearing
It is mounted on auxiliary support (81), the hydraulic brake caliper being adapted with rotating wheel (83) size is also set up on auxiliary support (81)
(84),
The one or more outer rings for having faulty faulty bearings of installation are pasted vibration acceleration and are passed in test speed changer (4)
Sensor (41)；Central processing unit (5) respectively with the hydraulic cylinder control valve of hydraulic brake caliper (84), speed probe (74), turn round
Square sensor (72), motor (71), gearshift controller (42), the multiple vibration acceleration sensors for testing speed changer (4)
(41), air intake control valve (13), gas bleeder valve (14), electric air pump (15), electromagnetic oscillation device (2) communication connection；
It is characterized by: the diagnostic method the following steps are included:
Faulty bearings are set by the bearing for testing one or more positions in speed changer (4), vibration is pasted in the outer ring of faulty bearings
Different abort situation and fault degree is arranged in dynamic acceleration transducer (41), the faulty bearings, and abort situation is respectively
Outer ring, inner ring, roller, retainer, the fault degree of faulty bearings are early stage, mid-term, advanced stage respectively；Then it sequentially carries out following
Step:
A. central processing unit (5) control electromagnetic oscillation device (2) generates specific amplitude and vibration frequency；Central processing unit simultaneously
(5) motor (71) are controlled, gearshift controller (42) makes the output shaft output specific rotation speeds for testing speed changer (4)；Test speed change
While the output shaft of device (4) exports specific rotation speeds, central processing unit (5) controls brake caliper (84) and applies to rotating wheel (83)
Braking moment makes the output shaft for testing speed changer (4) by specific load torque；Vibration acceleration sensor (41) acquisition event
Hinder the vibration acceleration signal sample of bearing；Using collected sample as training sample, the vibration in training sample is accelerated
It spends signal x (t) and carries out EMD adaptive decomposition, decomposition method is as follows:
N is the number of the IMF component decomposited in above formula；CjRepresent j-th of IMF component, j=1,2,3 ..., n；rnIt is remnants points
Amount；
B. it decomposes to obtain n C by step ajAfter component, each C is calculated separatelyjThe kurtosis value of (j=1,2,3 ..., n) is chosen high and steep
Two C of angle value maximum and kurtosis value time greatlyjLinear superposition is carried out, the acceleration letter that feature highlights after EMD noise reduction is obtained
Number, the acceleration signal that the feature that then will acquire highlights is equally divided into m sections according to time span, by the signal of different duration sections
It is denoted as S1-Sm；
C. Alpha Stable distritation parameter Estimation is carried out respectively to each section of the S1-Sm in step b and calculate its probability density function,
Characteristic index α is extracted, wherein 0 α≤2 <, symmetric parameter β, wherein -1≤β≤1, coefficient of dispersion γ, wherein γ > 0, position are joined
Number δ, wherein the extreme value h of-∞≤δ≤∞ and probability density function, wherein totally 5 Alpha Stable distritation features of h > 0；
D. multi-fractal is carried out respectively to each section of the S1-Sm in step b and remove trend fluction analysis, extract S1-Sm respective 5
Multi-fractal features: the singular index α of maximum fluctuationmax, the singular index α of minimal ripplemin, multifractal spectra spectrum width Δ α=
αmax-αmin, the corresponding singular index α of multifractal spectra extreme point0, fmax=f (α0), α0∈[αmin, αmax], multifractal spectra is general
Rate subset fractal dimension difference Δ f=f (αmax)-f(αmin)；
E. the respective 5 Alpha Stable distritations feature of the S1-Sm being calculated according to step c, step d, 5 multi-fractal spies
Sign carries out serial combination, obtains the respective assemblage characteristic collection of S1-Sm (α, beta, gamma, δ, h, α0, αmin, αmax, Δ α, Δ f)；
F. using radial base as kernel function, dimensionality reduction is carried out to the assemblage characteristic collection in step e using core principle component analysis method (KPCA)
Fusion accumulates contribution rate according to variance and is greater than or equal to 95% selection core pivot, obtains new pivot fusion feature collection；
G. integrated using the pivot fusion feature obtained in step f as input sample, using particle swarm optimization algorithm to least square branch
The two core parameter regularization parameter λ and kernel parameter σ for holding vector machine are optimized, and establish PSO- with the optimized parameter of acquisition
LSSVM model；
H. test speed changer (4) is changed to speed changer to be measured, by speed changer domestic demand to be measured one or more to be tested and event
Vibration acceleration sensor (41) are pasted in the outer ring for hindering the identical bearing to be measured in position of bearings, then repeat step a to step f,
By in step f, the respective pivot of the S1-Sm of one or more collected bearings to be measured of vibration acceleration sensor (41) is merged
Feature set is brought into trained PSO-LSSVM model and carries out state classification；Diagnosis terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811588388.6A CN109708890B (en) | 2017-08-09 | 2017-08-09 | Method for detecting the condition of bearings in a motor vehicle transmission |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811588388.6A CN109708890B (en) | 2017-08-09 | 2017-08-09 | Method for detecting the condition of bearings in a motor vehicle transmission |
| CN201710678357.9A CN107271187B (en) | 2017-08-09 | 2017-08-09 | The method that a kind of pair of automobile speed variator bearing failure carries out quantitative Diagnosis |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710678357.9A Division CN107271187B (en) | 2017-08-09 | 2017-08-09 | The method that a kind of pair of automobile speed variator bearing failure carries out quantitative Diagnosis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109708890A true CN109708890A (en) | 2019-05-03 |
| CN109708890B CN109708890B (en) | 2020-10-30 |
Family
ID=60077043
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811588388.6A Active CN109708890B (en) | 2017-08-09 | 2017-08-09 | Method for detecting the condition of bearings in a motor vehicle transmission |
| CN201710678357.9A Active CN107271187B (en) | 2017-08-09 | 2017-08-09 | The method that a kind of pair of automobile speed variator bearing failure carries out quantitative Diagnosis |
| CN201811597766.7A Active CN109668734B (en) | 2017-08-09 | 2017-08-09 | Quantitative diagnosis method for parts in automobile transmission bearing |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710678357.9A Active CN107271187B (en) | 2017-08-09 | 2017-08-09 | The method that a kind of pair of automobile speed variator bearing failure carries out quantitative Diagnosis |
| CN201811597766.7A Active CN109668734B (en) | 2017-08-09 | 2017-08-09 | Quantitative diagnosis method for parts in automobile transmission bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN109708890B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046476A (en) * | 2019-06-05 | 2019-07-23 | 厦门大学 | The ternary two of rolling bearing fault is into the sparse diagnostic method of Fractal Wavelet |
| CN110159428A (en) * | 2019-06-05 | 2019-08-23 | 西华大学 | Engine carbon-deposits the cylinder diagnostic device and diagnostic method |
| CN112749453A (en) * | 2020-12-16 | 2021-05-04 | 安徽三禾一信息科技有限公司 | Complex equipment residual service life prediction based on improved SVR |
| CN113408371A (en) * | 2021-06-01 | 2021-09-17 | 武汉理工大学 | Early fault diagnosis method and device |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108105081B (en) * | 2018-02-05 | 2023-10-27 | 中国石油化工股份有限公司 | Water injection pump unit fault diagnosis method and device |
| CN108498106B (en) * | 2018-02-08 | 2021-10-29 | 陕西师范大学 | CNV electroencephalogram lie detection method based on multi-fractal elimination trend fluctuation analysis |
| CN108460429B (en) * | 2018-05-03 | 2019-03-05 | 武汉理工大学 | Application method of the multiple regression LSSVM model in the diagnosis of mechanical concurrent fault |
| CN109374293B (en) * | 2018-10-29 | 2020-07-24 | 珠海市华星装备信息科技有限公司 | Gear fault diagnosis method |
| CN109827777B (en) * | 2019-04-01 | 2020-12-18 | 哈尔滨理工大学 | Rolling bearing fault prediction method based on partial least square method extreme learning machine |
| CN111120348A (en) * | 2019-12-25 | 2020-05-08 | 中国石化销售股份有限公司华南分公司 | Centrifugal pump fault early warning method based on support vector machine probability density estimation |
| CN111767891A (en) * | 2020-07-09 | 2020-10-13 | 南京工程学院 | Fault diagnosis method for rolling bearing |
| CN112037500A (en) * | 2020-07-21 | 2020-12-04 | 江苏国茂减速机股份有限公司 | Speed reducer capable of automatically judging fault, elevator and fault automatic judging method |
| CN112597958B (en) * | 2020-12-29 | 2023-04-07 | 哈工大机器人（合肥）国际创新研究院 | Automatic identification method and system for rolling bearing fault |
| CN113804470B (en) * | 2021-04-14 | 2023-12-01 | 山东省计算中心（国家超级计算济南中心） | Fault detection feedback method for plug seedling production line |
| CN113246175B (en) * | 2021-05-07 | 2024-05-03 | 配天机器人技术有限公司 | Robot terminal vibration classification method, robot and storage medium |
| CN113281035B (en) * | 2021-05-31 | 2022-12-09 | 重庆长安汽车股份有限公司 | Method for testing locking abnormal sound of automatic transmission |
| CN113628175B (en) * | 2021-07-22 | 2024-02-20 | 上海交通大学 | Image quality score distribution prediction method, system, terminal and medium |
| CN115266905B (en) * | 2022-08-02 | 2024-05-07 | 山东申正汽车拆解有限公司 | Crack detection method and equipment for recycling and remanufacturing engine crankshaft of heavy-duty commercial vehicle |
| CN117330941B (en) * | 2023-11-29 | 2024-02-02 | 珠海智锐科技有限公司 | Performance test method and related device for new energy BMS printed circuit board |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050022600A1 (en) * | 2003-07-15 | 2005-02-03 | Minebea Co., Ltd. | Method and device to determine the natural frequencies of a bearing system having a shaft arranged on bearings |
| CN105172511A (en) * | 2015-07-15 | 2015-12-23 | 西南交通大学 | Automobile suspension shock absorber control system and method |
| CN106017879A (en) * | 2016-05-18 | 2016-10-12 | 河北工业大学 | Universal circuit breaker mechanical fault diagnosis method based on feature fusion of vibration and sound signals |
| CN106441861A (en) * | 2015-08-10 | 2017-02-22 | 中国石油天然气股份有限公司 | Automatic transmission oil transmission efficiency detection device and automatic transmission oil transmission efficiency detection method |
| CN206074255U (en) * | 2016-07-20 | 2017-04-05 | 西南交通大学 | A kind of bullet train axle box bearing testing stand based on rolling vibration |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564756B (en) * | 2010-12-31 | 2015-06-03 | 中国科学院沈阳自动化研究所 | Automobile transmission vibration analysis testing method and device |
| CN102539151B (en) * | 2012-01-18 | 2014-05-14 | 北京工业大学 | Intelligent online quality detection method for automobile transmission |
| JP6133112B2 (en) * | 2013-04-11 | 2017-05-24 | Ntn株式会社 | Rolling bearing diagnostic device and rolling bearing diagnostic method |
| US9841352B2 (en) * | 2014-06-19 | 2017-12-12 | United Technologies Corporation | System and method for monitoring gear and bearing health |
| CN104697787B (en) * | 2015-03-20 | 2019-03-26 | 山东大学 | A kind of gearbox test-bed and its detection method based on multi-information fusion |
| JP6714806B2 (en) * | 2015-08-06 | 2020-07-01 | 日本精工株式会社 | Status monitoring device and status monitoring method |
| CN106092310A (en) * | 2016-04-21 | 2016-11-09 | 重庆理工大学 | A kind of automotive transmission vibration noise off-line test method |
| CN105784361B (en) * | 2016-05-30 | 2018-01-16 | 吉林大学 | Dynamic power machine closed loop tilting polygon exciting gear box test table |
| CN106053072A (en) * | 2016-07-20 | 2016-10-26 | 西南交通大学 | High-speed train axle box bearing test bench based on vibration rolling |
| CN106840651A (en) * | 2017-01-16 | 2017-06-13 | 广州汽车集团股份有限公司 | Speed changer heat examination platform |
-
2017
- 2017-08-09 CN CN201811588388.6A patent/CN109708890B/en active Active
- 2017-08-09 CN CN201710678357.9A patent/CN107271187B/en active Active
- 2017-08-09 CN CN201811597766.7A patent/CN109668734B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050022600A1 (en) * | 2003-07-15 | 2005-02-03 | Minebea Co., Ltd. | Method and device to determine the natural frequencies of a bearing system having a shaft arranged on bearings |
| CN105172511A (en) * | 2015-07-15 | 2015-12-23 | 西南交通大学 | Automobile suspension shock absorber control system and method |
| CN106441861A (en) * | 2015-08-10 | 2017-02-22 | 中国石油天然气股份有限公司 | Automatic transmission oil transmission efficiency detection device and automatic transmission oil transmission efficiency detection method |
| CN106017879A (en) * | 2016-05-18 | 2016-10-12 | 河北工业大学 | Universal circuit breaker mechanical fault diagnosis method based on feature fusion of vibration and sound signals |
| CN206074255U (en) * | 2016-07-20 | 2017-04-05 | 西南交通大学 | A kind of bullet train axle box bearing testing stand based on rolling vibration |
Non-Patent Citations (1)
| Title |
|---|
| 熊庆 等: ""基于MF-DFA与PSO优化LSSVM的滚动轴承故障诊断方法"", 《振动与冲击》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046476A (en) * | 2019-06-05 | 2019-07-23 | 厦门大学 | The ternary two of rolling bearing fault is into the sparse diagnostic method of Fractal Wavelet |
| CN110159428A (en) * | 2019-06-05 | 2019-08-23 | 西华大学 | Engine carbon-deposits the cylinder diagnostic device and diagnostic method |
| CN110046476B (en) * | 2019-06-05 | 2020-10-16 | 厦门大学 | Ternary binary fractal wavelet sparse diagnosis method for rolling bearing faults |
| CN110159428B (en) * | 2019-06-05 | 2024-03-12 | 西华大学 | Device and method for diagnosing carbon deposit in engine cylinder |
| CN112749453A (en) * | 2020-12-16 | 2021-05-04 | 安徽三禾一信息科技有限公司 | Complex equipment residual service life prediction based on improved SVR |
| CN112749453B (en) * | 2020-12-16 | 2023-10-13 | 安徽三禾一信息科技有限公司 | Complex equipment residual service life prediction method based on improved SVR |
| CN113408371A (en) * | 2021-06-01 | 2021-09-17 | 武汉理工大学 | Early fault diagnosis method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109668734B (en) | 2020-09-04 |
| CN107271187A (en) | 2017-10-20 |
| CN109668734A (en) | 2019-04-23 |
| CN107271187B (en) | 2019-01-18 |
| CN109708890B (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107271187B (en) | The method that a kind of pair of automobile speed variator bearing failure carries out quantitative Diagnosis | |
| JP6087163B2 (en) | System for characterizing a tire uniformity machine and method of using the characterization | |
| CN108871788B (en) | A kind of method of calibration of automatic transmission shift attribute test rack | |
| CN103983460B (en) | A kind of vehicle inner walkway method | |
| CN207066742U (en) | A kind of automobile speed variator bearing testing stand | |
| EP3224589B1 (en) | Method and a device for determining the propulsion torque | |
| CN112525534A (en) | Bearing and gear damage quantitative evaluation method based on acoustic emission technology | |
| CN102441579A (en) | Online monitoring method for running state of hot continuous rolling mill | |
| CN110530639A (en) | A kind of bullet train axle box bearing failure diagnostic method | |
| CN106441861A (en) | Automatic transmission oil transmission efficiency detection device and automatic transmission oil transmission efficiency detection method | |
| CN105352726B (en) | A kind of method for diagnosing faults of gear | |
| CN112991577A (en) | Railway vehicle wheel polygon state diagnostic system | |
| CN104931262A (en) | Bearing fault diagnosis device used in cooperation with wheel set bearing running-in machine and diagnosis method thereof | |
| CN110849624A (en) | Main shaft radial loading device and machine tool main shaft performance testing method | |
| CN111458016A (en) | Method for rapidly detecting vibration of drive axle assembly | |
| CN111521399B (en) | Kurtosis index and envelope spectrum based early fault diagnosis method for space bearing | |
| CN113933074A (en) | Suspension assembly road simulation test method based on standardized load spectrum | |
| CN109940456A (en) | Machine tool chief axis method for testing performance and system | |
| CN106644483A (en) | Bearing fault detection method and system for gear box | |
| Tieng et al. | An automated dynamic-balancing-inspection scheme for wheel machining | |
| CN115931399A (en) | Method for real-time online detection of polygonal fault of high-speed train wheel | |
| CN113758720B (en) | Truck driving jitter detection method | |
| CN114755027A (en) | Finished automobile multi-axis loading test bench, test method and medium | |
| CN205538203U (en) | General adjustable chain detection device | |
| CN108225706B (en) | A kind of identification wheel intensively removes the automated diagnostic method of pitted skin failure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211116 Address after: 224006 No. 6, Yuxing Road, Zhongxing Street, Xuefu Town, Yandu District, Yancheng City, Jiangsu Province (P) Patentee after: Fuller transmission equipment Yancheng Co., Ltd Address before: 610039 Xihua University, No. 999 Jinzhou Road, Jinniu District, Chengdu, Sichuan Patentee before: Xihua University |
|
| TR01 | Transfer of patent right |