CN105045983A - Axle ageing analysis method of high speed train on the basis of axle temperature data - Google Patents
Axle ageing analysis method of high speed train on the basis of axle temperature data Download PDFInfo
- Publication number
- CN105045983A CN105045983A CN201510390862.4A CN201510390862A CN105045983A CN 105045983 A CN105045983 A CN 105045983A CN 201510390862 A CN201510390862 A CN 201510390862A CN 105045983 A CN105045983 A CN 105045983A
- Authority
- CN
- China
- Prior art keywords
- axle temperature
- data
- axle
- time
- 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
- 230000032683 aging Effects 0.000 title claims abstract description 65
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 48
- 230000007704 transition Effects 0.000 claims description 45
- 230000008569 process Effects 0.000 claims description 37
- 230000009194 climbing Effects 0.000 claims description 32
- 238000005070 sampling Methods 0.000 claims description 26
- 101100442582 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) spe-1 gene Proteins 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 12
- 230000001502 supplementing effect Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000000630 rising effect Effects 0.000 claims description 8
- 241001269238 Data Species 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 230000002277 temperature effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract 1
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 14
- 238000009499 grossing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000003679 aging effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses an axle ageing analysis method of a high speed train on the basis of axle temperature data. The axle ageing analysis method is implemented according to the following steps: 1) preprocessing train speed and the axle temperature data; 2) carrying out smooth processing on the axle temperature data preprocessed in the step 1); 3) calculating a rise rate of the axle temperature of the train; and 4) carrying out ageing analysis on the axle by the rise rate of the axle temperature obtained in the step 3). The axle ageing analysis method solves the problems of time consumption and low precision of axle fault detection in the prior art.
Description
Technical field
The invention belongs to fault diagnosis technology field, be specifically related to a kind of bullet train axletree aging analysis method based on axle temperature data.
Background technology
Along with the fast development of high ferro, guarantee motor train unit running order and improve the security of motor train unit, reliability is subject to extensive concern.Axletree is the crucial load bearing component of rolling stock bogie, be the strength member affecting traffic safety, if axletree occurs Aging Damage and expands, derail will be caused because of off-axis, the consequence of bringing on a disaster property, therefore its safe handling direct relation the safety in production of transportation by railroad.What current axle failures detected mainly comprises two aspects, namely based on axle temperature threshold value with based on artificial maintenance.
First method is, by expertise, and the corresponding axle temperature threshold point of setting train faults such as hot box, warm axle in the process of walking.On this basis, the axletree temperature in temperature sensor Real-Time Monitoring train travelling process is adopted.When axle temperature reaches each threshold point, then take the corresponding measure such as warning, reduction of speed or parking.The features such as, operational speed range far away relative to the operating range of bullet train is large, the maximum defect of the method is, fail to take into full account the impact of the factor such as environment temperature and travelling speed on axletree temperature, and the health status of unpredictable axletree, to the aging effect waiting unsafe condition can not play early warning of axletree.
Second method is, after Train Stopping, assigns experienced service worker by beaing, the abrasion condition of the mode determination axletree such as observation, and whether there is the unsafe conditions such as slight crack.The maximum defect of the method is, the inherent attribute display aging due to axletree is difficult to detect, thus causes the aging conditions of axletree to be difficult to judge, and the uncertainty of desk checking.
Summary of the invention
The object of this invention is to provide a kind of bullet train axletree aging analysis method based on axle temperature data, solve the axle failures that exists in prior art and detect the consuming time and problem that precision is low.
The technical solution adopted in the present invention is, a kind of bullet train axletree aging analysis method based on axle temperature data, specifically implements according to following steps:
Step 1, pre-service is carried out to train speed and axle temperature data;
Step 2, pretreated axle temperature data are carried out to step 1 carry out smooth treatment;
Step 3, calculating train axle temperature climbing speed;
Step 4, the axle temperature climbing speed utilizing step 3 to obtain carry out the aging analysis of axletree.
Feature of the present invention is also,
Step 1 is specifically implemented according to following steps:
Supplementing of step (1.1), shortage of data point:
Gather train speed spe (i) and axle temperature zw (i), wherein i is corresponding sampling time point, and span is 1 ~ n, searches and processes respectively to train speed spe (i) collected and axle temperature zw (i) all values, if 2≤i≤n, i ∈ Z
+, Z
+represent positive integer, if the i-th-1 point is non-null value point, and i-th point is null value point, i.e. zw (i-1) ≠ null, zw (i)=null, and processing procedure is as follows:
If zw (i) is isolated missing point, i.e. zw (i-1) ≠ null, zw (i)=null, zw (i+1) ≠ null, then the value of the i-th-1 is assigned to i-th value, namely carries out the operation of zw (i)=zw (i-1) assignment;
If there is continuous print missing point in former data, its number is m (m>2), i.e. zw (i+1), zw (i+2) ..., the average of zw (i+m-1) is null, zw (i+m) ≠ null, then according to m≤n or m>n, a point situation is discussed, as follows:
(1) if m>n, then represent that data are imperfect, analyze and stop;
(2) if m≤n, then carry out linear interpolation processing, detailed process is as follows:
Step a: order
Step b: interpolation operation is carried out to all continuous print missing points, namely
zw (i+j)=zw (i-1)+(j+1) × delta,
zw(i)＝zw(i-1)+delta,
zw(i+1)＝zw(i-1)+2×delta,
.
.
.
zw(i+m-1)＝zw(i-1)+(m-1)×delta
In like manner, carry out as above same operation according to above step to train speed data spe (i), thus supplement complete by all shortage of datas point, the axle temperature after supplementing and speed data are designated as zw1 (i) and spe1 (i) respectively;
The elimination of step (1.2), isolated zero point:
Whether axle temperature data zw1 (i) that determining step (1.1) obtains and speed data spe1 (i) are that isolated zero point is gone forward side by side row relax, and concrete operations are as follows:
If i-th axle temperature data is not 0, i.e. zw1 (i) ≠ 0, then do not carry out any operation;
If i-th axle temperature data is 0, i.e. zw1 (i)=0, then continue to judge whether its adjacent data zw1 (i-1) and zw1 (i+1) is also zero point, as follows:
(1) if the i-th-1 axle temperature data and the i-th+1 axle temperature data have and only have one to be 0, namely zw1 (i-1)=0 or zw1 (i+1)=0, be then considered as normal data by zw1 (i)=0, do not carry out any operation;
(2) if the i-th-1 axle temperature data are not 0 and the i-th+1 axle temperature data are not 0 yet, namely zw1 (i-1) ≠ 0 and zw1 (i+1) ≠ 0, be then considered as isolated zero point, now by zw1 (i)
In like manner, according to above step, also identical estimation & disposing is carried out to speed data spe1 (i), processed by all isolated zero point, the axle temperature data obtained after eliminating isolated point are designated as zw2 (i), and the speed data obtained is designated as spe2 (i).
Step 2 is specifically implemented according to following steps:
Carry out pretreated axle temperature data zw2 (i) to step 1 and carry out TIME layer scattering wavelet transformation, TIME layer scattering wavelet transformation detailed process is as follows:
Step a: array variable data is set, and make data=zw2 (i); Intermediate variable time=0 is set;
Step b: data in step a is upgraded according to following formula:
and intermediate variable time is carried out adding 1 operation, i.e. time=time+1, wherein, H (k) represents low-pass filter, K represents the length of H (k), and j represents array data length
namely
Step c: if time<TIME, then return step b, if time >=TIME, then completes the smooth treatment of data, and the axle temperature data after smooth treatment are designated as array DATA (i), even DATA (i)=data;
Be eliminated by the noise signal in above-mentioned conversion process axle temperature data, make axle temperature curve more level and smooth, the first transition for temperature data obtains and provides basis.
In the step b of step 2, the length K=length (data) of H (k), represents identical with axle temperature data data length.
In the step c of step 2, TIME ∈ Z
+.
Step 3 is specifically implemented according to following steps:
The extraction of step (3.1), axle temperature first transition:
To the axle temperature data after described step 2 processes, carry out the extraction of first transition, specific as follows: the axle temperature data after step 2 being processed take turns doing difference, difference is designated as φ, i.e. φ=DATA (i)-DATA (i+1), if during φ >0, this axle temperature interval [i is described, i+1] axle temperature not at ascent stage, may be in decline or not change, then continue to do difference and extract; If during φ <0, this axle temperature interval [i, i+1] is axle temperature first transition, stores starting point i and the terminal i+1 of the sampled point of first transition, and exists in new array up;
The speed screening of step (3.2), axle temperature first transition:
If threshold speed is V, if each first transition starting point i in described step (3.1) and terminal j, corresponding sampling time point is i × 2
tIMEwith j × 2
tIME, then corresponding velocity amplitude spe2 (i × 2
tIME) and spe2 (j × 2
tIME), if spe2 (i × 2
tIME) <V and spe2 (j × 2
tIME) <V, then illustrate that this ascent stage [i, j] is shutdown phase, the train axle temperature under ambient temperature effect heats up, then do not retain this axle temperature first transition; If spe2 (i × 2
tIME)>=V and spe2 (j × 2
tIME)>=V, then illustrate axle temperature first transition when this ascent stage [i, j] is train operation, retains and continue to judge;
The calculating of step (3.3), axle temperature climbing speed:
Carry out climbing speed calculating to the axle temperature data after step (3.2) process, computation process is as follows:
Step (3.3.1), the axle temperature difference of each for axle temperature first transition is designated as fz, corresponding each rise time is designated as t, and the average of each ascending velocity is designated as v, and the computing formula of fz, t, v is as follows respectively:
fz＝DATA(j)-DATA(i)，
t＝(j-i)×2
TIME，
wherein i and j is respectively starting point and the terminal of axle temperature first transition;
Step (3.3.2), axle temperature climbing speed is set as the computing formula of SSJSL, SSJSL to be
the ratio of axle temperature summation and speed average summation is designated as SSSSV, and its computing formula is
In step (3.2), threshold speed is V=2.
Step 4 is specifically implemented according to following steps:
Step (4.1), calculate the high ferro axle temperature climbing speed SSJSL of in described step 3 n days
i(i=1,2 ... n), computing formula is
wherein m is i-th day axle temperature data point number;
Step (4.2), the high ferro axle temperature climbing speed SSJSL of n days will obtained in step (4.1)
i(i=1,2 ... n) with this axletree axle temperature rising reference speed rate SSJSL
0compare, axletree axle temperature rising reference speed rate SSJSL
0computing formula is
k is reference speed rate sampling number of days, k=100, and the judgement that axletree is aging with foundation is:
(1) as α >=a, train axle is slightly aging,
(2) as α >=b, train axle severe is aging,
Wherein a<b, a, b ∈ R, a are slight aging coefficients, and a=1.1, b are severe aging coefficients, b=2.5.
The invention has the beneficial effects as follows, a kind of bullet train axletree aging analysis method based on axle temperature data, high ferro train data is analyzed, realize the automatic calculating of axle temperature rate of change, and axletree aging analysis can be realized based on data, use wavelet transform, after data are processed, make axle temperature data trend more obvious, be convenient to the climbing speed calculating data, good by data continuity after pre-service, directly can judge first transition by difference, be convenient to automatically extract first transition, calculate climbing speed etc., in conjunction with train speed, set up temperature rate-of-rise computing method, new method is more suitable for the calculating of high ferro axle temperature climbing speed.
Accompanying drawing explanation
Fig. 1 is a kind of bullet train axletree aging analysis method flow diagram based on axle temperature data of the present invention;
Fig. 2 is that a kind of supplementing based on shortage of data point in the bullet train axletree aging analysis method of axle temperature data of the present invention eliminates process flow diagram with isolated zero point;
Fig. 3 is a kind of process flow diagram based on TIME layer scattering wavelet transformation in the bullet train axletree aging analysis method of axle temperature data of the present invention;
To be that the present invention is a kind of judge first transition process flow diagram based in the bullet train axletree aging analysis method of axle temperature data to Fig. 4;
To be that the present invention is a kind of judge to meet the requirements first transition calculate total speed process flow diagram based in the bullet train axletree aging analysis method of axle temperature data to Fig. 5;
To be that the present invention is a kind of calculate axle temperature and average velocity process flow diagram based in the bullet train axletree aging analysis method of axle temperature data to Fig. 6;
Fig. 7 is that the present invention is a kind of based on axle temperature signal curve schematic diagram initial in the bullet train axletree aging analysis method of axle temperature data;
Fig. 8 is that the present invention is a kind of based on the axle temperature signal curve schematic diagram after interpolation in the bullet train axletree aging analysis method of axle temperature data;
Fig. 9 is that the present invention is a kind of based on the axle temperature data and curves schematic diagram after TIME layer scattering wavelet transformation decomposition in the bullet train axletree aging analysis method of axle temperature data.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
A kind of bullet train axletree aging analysis method based on axle temperature data of the present invention, process flow diagram as shown in Figure 1, is specifically implemented according to following steps:
Step 1, pre-service is carried out to train speed and axle temperature data, as shown in Figure 2:
Supplementing of step (1.1), shortage of data point:
Gather train speed spe (i) and axle temperature zw (i), wherein i is corresponding sampling time point, and span is 1 ~ n, searches and processes respectively to train speed spe (i) collected and axle temperature zw (i) all values, if 2≤i≤n, i ∈ Z
+, Z
+represent positive integer, if the i-th-1 point is non-null value point, and i-th point is null value point, i.e. zw (i-1) ≠ null, zw (i)=null, and processing procedure is as follows:
If zw (i) is isolated missing point, i.e. zw (i-1) ≠ null, zw (i)=null, zw (i+1) ≠ null, then the value of the i-th-1 is assigned to i-th value, namely carries out the operation of zw (i)=zw (i-1) assignment;
If there is continuous print missing point in former data, its number is m (m>2), i.e. zw (i+1), zw (i+2) ..., the average of zw (i+m-1) is null, zw (i+m) ≠ null, then according to m≤n or m>n, a point situation is discussed, as follows:
(1) if m>n, then represent that data are imperfect, analyze and stop;
(2) if m≤n, then carry out linear interpolation processing, detailed process is as follows:
Step a: order
Step b: interpolation operation is carried out to all continuous print missing points, namely
zw (i+j)=zw (i-1)+(j+1) × delta,
zw(i)＝zw(i-1)+delta,
zw(i+1)＝zw(i-1)+2×delta,
.
.
.
zw(i+m-1)＝zw(i-1)+(m-1)×delta
In like manner, carry out as above same operation according to above step to train speed data spe (i), thus supplement complete by all shortage of datas point, the axle temperature after supplementing and speed data are designated as zw1 (i) and spe1 (i) respectively;
The elimination of step (1.2), isolated zero point:
Whether axle temperature data zw1 (i) that determining step (1.1) obtains and speed data spe1 (i) are that isolated zero point is gone forward side by side row relax, and concrete operations are as follows:
If i-th axle temperature data is not 0, i.e. zw1 (i) ≠ 0, then do not carry out any operation;
If i-th axle temperature data is 0, i.e. zw1 (i)=0, then continue to judge whether its adjacent data zw1 (i-1) and zw1 (i+1) is also zero point, as follows:
(1) if the i-th-1 axle temperature data and the i-th+1 axle temperature data have and only have one to be 0, namely zw1 (i-1)=0 or zw1 (i+1)=0, be then considered as normal data by zw1 (i)=0, do not carry out any operation;
(2) if the i-th-1 axle temperature data are not 0 and the i-th+1 axle temperature data are not 0 yet, namely zw1 (i-1) ≠ 0 and zw1 (i+1) ≠ 0, be then considered as isolated zero point, now by zw1 (i)
In like manner, according to above step, also identical estimation & disposing is carried out to speed data spe1 (i), processed by all isolated zero point, the axle temperature data obtained after eliminating isolated point are designated as zw2 (i), and the speed data obtained is designated as spe2 (i);
Step 2, pretreated axle temperature data carried out to described step 1 carry out smooth treatment:
Pretreated axle temperature data zw2 (i) is carried out to step 1 and carries out TIME layer scattering wavelet transformation, as shown in Figure 3, TIME ∈ Z
+, concrete value is determined according to actual conditions.TIME layer scattering wavelet transformation detailed process is as follows:
Step a: array variable data is set, and make data=zw2 (i); Intermediate variable time=0 is set;
Step b: data in step a is upgraded according to following formula:
and intermediate variable time is carried out adding 1 operation, i.e. time=time+1, wherein, H (k) represents low-pass filter, K represents the length of H (k), the length K=length (data) of H (k), represent identical with axle temperature data data length, and j represents array data length
namely
Step c: if time<TIME, then return step b, if time >=TIME, then completes the smooth treatment of data, and the axle temperature data after smooth treatment are designated as array DATA (i), even DATA (i)=data;
Be eliminated by the noise signal in above-mentioned conversion process axle temperature data, make axle temperature curve more level and smooth, the first transition for temperature data obtains and provides basis;
Step 3, calculating train axle temperature climbing speed:
The extraction of step (3.1), axle temperature first transition:
To the axle temperature data after step 2 processes, carry out the extraction of first transition, as shown in Figure 4, specific as follows: the axle temperature data after step 2 being processed take turns doing difference, and difference is designated as φ, i.e. φ=DATA (i)-DATA (i+1), if during φ >0, illustrate that the axle temperature in this axle temperature interval [i, i+1] is not at ascent stage, may be in decline or not change, then continue to do difference and extract; If during φ <0, this axle temperature interval [i, i+1] is axle temperature first transition, stores starting point i and the terminal i+1 of the sampled point of first transition, and exists in new array up;
The speed screening of step (3.2), axle temperature first transition, as shown in Figure 5:
If threshold speed is V, threshold speed is V=2, in a practical situation, owing to there is the difference of vehicle and bearing, so the value of threshold speed is not limited in V=2, and can also value threshold speed V=N
+, N
+for positive natural number, if sampling time point corresponding to each first transition starting point i in step (3.1) and terminal j is for i × 2
tIMEwith j × 2
tIME, then corresponding velocity amplitude spe2 (i × 2
tIME) and spe2 (j × 2
tIME), if spe2 (i × 2
tIME) <V and spe2 (j × 2
tIME) <V, then illustrate that this ascent stage [i, j] is shutdown phase, the train axle temperature under ambient temperature effect heats up, then do not retain this axle temperature first transition, if spe2 (i × 2
tIME)>=V and spe2 (j × 2
tIME)>=V, then illustrate axle temperature first transition when this ascent stage [i, j] is train operation, retains and continue to judge;
The calculating of step (3.3), axle temperature climbing speed, as shown in Figure 6:
Carry out climbing speed calculating to the axle temperature data after step (3.2) process, computation process is as follows:
Step (3.3.1), the axle temperature difference of each for axle temperature first transition is designated as fz, corresponding each rise time is designated as t, and the average of each ascending velocity is designated as v, and the computing formula of fz, t, v is as follows respectively:
fz＝DATA(j)-DATA(i)，
t＝(j-i)×2
TIME，
wherein i and j is respectively starting point and the terminal of axle temperature first transition;
Step (3.3.2), axle temperature climbing speed is set as the computing formula of SSJSL, SSJSL to be
the ratio of axle temperature summation and speed average summation is designated as SSSSV, and its computing formula is
Step 4, the axle temperature climbing speed utilizing described step 3 to obtain carry out the aging analysis of axletree:
The high ferro axle temperature climbing speed SSJSL of n days in step (4.1), calculation procedure 3
i(i=1,2 ... n), computing formula is
wherein m is i-th day axle temperature data point number;
Step (4.2), the high ferro axle temperature climbing speed SSJSL of n days will obtained in step (4.1)
i(i=1,2 ... n) with this axletree axle temperature rising reference speed rate SSJSL
0compare, axletree axle temperature rising reference speed rate SSJSL
0computing formula is
k is reference speed rate sampling number of days, k=100, and the judgement that axletree is aging with foundation is:
(1) as α >=a, train axle is slightly aging;
(2) as α >=b, train axle severe is aging,
Wherein a<b, a, b ∈ R, a are slight aging coefficients, and a=1.1, b are severe aging coefficients, b=2.5.
In the inventive method, slight aging coefficient a and severe aging coefficient b, threshold speed is V, different according to vehicle, also difference numerically can be there is in bearing difference, but with regard to the art, the empirical value under a corresponding practical operation situation understood by corresponding vehicle and bearing, but no matter this slight aging coefficient and severe aging coefficient and threshold speed are that the value of V is specifically how many, the judgement bullet train axletree aging analysis method proposed in the application is still equally effective and feasible, so, although slight aging coefficient a=1.1 in the application, severe aging coefficient b=2.5, threshold speed is V=2, but in like manner can contain the congeniality patent that any in this way analysis bullet train axletree is aging.
A kind of bullet train axletree aging analysis method based on axle temperature data of the present invention, accurately to grasp the aging performance of train axle, for the fault pre-alarming of train axle provides foundation, based on the service data of train, by carrying out pre-service and slickness process to data, then the ascent stage Origin And Destination of each axletree temperature is found out, and the mistiming of correspondence, finally calculate axle temperature climbing speed, and formulate the aging decision rule of axletree, whole method, according to clear, make observation more blunt, contributes to bullet train operational management.
Embodiment
A kind of bullet train axletree aging analysis method based on axle temperature data of the present invention, specifically implement according to following steps:
Step 1, pre-service is carried out to train speed and axle temperature data:
Supplementing of step (1.1), shortage of data point:
Gather train speed spe (i) and axle temperature zw (i), wherein i is corresponding sampling time point, and i=20, as shown in Table 1 and Table 2, draws initial axle temperature signal curve schematic diagram,
Table 1: the sampled data of axle temperature zw (i)
| Sampling time point | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
| Axle temperature | 28.67249 | 30.28081 | 30.28081 | 30.28081 | 31.88913 | 31.88913 | 0 | |
| Sampling time point | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 |
| Axle temperature | 33.49745 | 35.10577 | 35.10577 | 36.71409 | 36.71409 | 36.71409 | 38.32241 | 38.32241 |
| Sampling time point | 17 | 18 | 19 | 20 | ||||
| Axle temperature | 39.93074 | 39.93074 | 41.53906 | 41.53906 |
The sampled data of table 2: speed spe (i)
| Sampling time point | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
| The speed of a motor vehicle | 0.445477 | 2.545584 | 8.893636 | 23.88076 | 44.89775 | 76.57436 | 111.6239 | |
| Sampling time point | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 |
| The speed of a motor vehicle | 136.0297 | 161.0719 | 171.5724 | 183.7116 | 193.369 | 200.7352 | 213.3359 | 217.2815 |
| Sampling time point | 17 | 18 | 19 | 20 | ||||
| The speed of a motor vehicle | 0 | 268.8455 | 265.8067 | 259.0291 |
Respectively to train speed spe (i) collected and axle temperature zwi) all values searches and processes, as can be seen from Table 1, zw (5) is isolated missing point, i.e. zw (4) ≠ null, zw (5)=null, zw (6) ≠ null, then the value of the 4th is assigned to the 5th value, namely zw (5)=zw (4) assignment operation is carried out, in like manner, according to above step, as above same operation is carried out to train speed data spe (i), thus all shortage of datas point is supplemented complete, axle temperature after supplementing and speed data are designated as zw1 (i) and spe1 (i) respectively, as shown in Table 3 and Table 4,
Table 3: supplemented train axle temperature zw1 (i) after shortage of data point
| Sampling time point | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
| Axle temperature | 28.67249 | 30.28081 | 30.28081 | 30.28081 | 30.28081 | 31.88913 | 31.88913 | 0 |
| Sampling time point | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 |
| Axle temperature | 33.49745 | 35.10577 | 35.10577 | 36.71409 | 36.71409 | 36.71409 | 38.32241 | 38.32241 |
| Sampling time point | 17 | 18 | 19 | 20 | ||||
| Axle temperature | 39.93074 | 39.93074 | 41.53906 | 41.53906 |
Table 4: supplemented train speed spe1 (i) after shortage of data point
| Sampling time point | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
| The speed of a motor vehicle | 0.445477 | 2.545584 | 8.893636 | 23.88076 | 44.89775 | 44.89775 | 76.57436 | 111.6239 |
| Sampling time point | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 |
| The speed of a motor vehicle | 136.0297 | 161.0719 | 171.5724 | 183.7116 | 193.369 | 200.7352 | 213.3359 | 217.2815 |
| Sampling time point | 17 | 18 | 19 | 20 | ||||
| The speed of a motor vehicle | 0 | 268.8455 | 265.8067 | 259.0291 |
The elimination of step (1.2), isolated zero point:
Whether axle temperature data zw1 (i) that determining step (1.1) obtains and speed data spe1 (i) are that isolated zero point is gone forward side by side row relax, and concrete operations are as follows:
8th axle temperature data are 0, i.e. zw1 (8)=0, then continue to judge whether its adjacent data zw1 (7) and zw1 (9) is also zero point, as follows:
7th axle temperature data are not 0 and the 9th axle temperature data are not 0 yet, and namely zw1 (7) ≠ 0 and zw1 (9) ≠ 0, be then considered as isolated zero point by zw1 (8), now
In like manner, according to above step, also identical estimation & disposing is carried out to speed data spe1 (i), all isolated zero point is processed, the axle temperature data obtained after eliminating isolated point are designated as zw2 (i), the speed data obtained is designated as spe2 (i), as shown in table 5 and table 6:
Table 5: eliminate train axle temperature zw2 (i) after isolated zero point
Table 6: eliminate train speed spe2 (i) after isolated zero point
| Sampling time point | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
| The speed of a motor vehicle | 0.445477 | 2.545584 | 8.893636 | 23.88076 | 44.89775 | 44.89775 | 76.57436 | 111.6239 |
| Sampling time point | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 |
| The speed of a motor vehicle | 136.0297 | 161.0719 | 171.5724 | 183.7116 | 193.369 | 200.7352 | 213.3359 | 217.2815 |
| Sampling time point | 17 | 18 | 19 | 20 | ||||
| The speed of a motor vehicle | 243.0635 | 268.8455 | 265.8067 | 259.0291 |
Step 2, pretreated axle temperature data carried out to step 1 carry out smooth treatment:
Carry out pretreated axle temperature data zw2 (i) to step 1 and carry out TIME layer scattering wavelet transformation, in the present embodiment, TIME=1, TIME layer scattering wavelet transformation detailed process is as follows:
Step a: array variable data is set, and make data=zw2 (i); Intermediate variable time=0 is set;
Step b: data in step a is upgraded according to following formula:
and intermediate variable time is carried out adding 1 operation, i.e. time=time+1, wherein, H (k) represents low-pass filter, K represents the length of H (k), the length K=length (data) of H (k), represents identical with axle temperature data data length, namely K=20, j represent array data length
namely
Step c: if time<TIME, then return step b, if time >=TIME, then completes the smooth treatment of data, and the axle temperature data after smooth treatment are designated as array DATA (i), even DATA (i)=data;
Be eliminated by the noise signal in above-mentioned conversion process axle temperature data, make axle temperature curve more level and smooth, the first transition for temperature data obtains and provides basis, and train axle temperature DATA (i) after smoothing processing is as shown in table 7:
Train axle temperature DATA (i) after table 7 smoothing processing
Step 3, calculating train axle temperature climbing speed:
The extraction of step (3.1), axle temperature first transition:
To the axle temperature data after step 2 processes, carry out the extraction of first transition, specific as follows: the axle temperature data after step 2 being processed take turns doing difference, and difference is designated as φ, i.e. φ=DATA (i)-DATA (i+1), obtains result as shown in table 8:
Table 8 axle temperature difference table
| DATA(i)-DATA(i+1) | DATA(1)-DATA(2) | DATA(3)-DATA(2) | DATA(4)-DATA(3) |
| Axle temperature difference | -1.1372 | -1.1373 | -1.7059 |
| DATA(i)-DATA(i+1) | DATA(5)-DATA(4) | DATA(6)-DATA(5) | DATA(7)-DATA(6) |
| Axle temperature difference | -2.8431 | -2.2745 | -1.1373 |
| DATA(i)-DATA(i+1) | DATA(8)-DATA(7) | DATA(9)-DATA(8) | DATA(10)-DATA(9) |
| Axle temperature difference | -2.2745 | -2.2745 | -2.2745 |
Do difference as can be seen from table 8 axle temperature, difference is all less than 0, then all belong to ascent stage, then starting point and the terminal of the corresponding sampling time ascent stage point risen by axle temperature exist in new array up, now up=[1,10];
The speed screening of step (3.2), axle temperature first transition:
If threshold speed is V, threshold speed is V=2, to the array obtained in step (3.1), calculate first transition [2,20], corresponding speed spe2 (2)=2.545584 and spe2 (20)=259.0291 is found from table 6, spe2 (2) >=2 can be found out and spe2 (20) >=2, then axle temperature first transition when this ascent stage is train operation is described, now, array up=[1,10];
The calculating of step (3.3), axle temperature climbing speed:
Carry out climbing speed calculating to the axle temperature data after step (3.2) process, computation process is as follows:
Step (3.3.1), the axle temperature difference of each for axle temperature first transition is designated as fz, corresponding each rise time is designated as t, and the average of each ascending velocity is designated as v, and the computing formula of fz, t, v is as follows respectively:
fz
1＝DATA(j)-DATA(i)＝58.7451-41.6863＝17.0588,
t
1＝(j-i)×2
TIME＝9×2＝18，
Step (3.3.2), axle temperature climbing speed is set as the computing formula of SSJSL, SSJSL to be
the ratio of axle temperature summation and speed average summation is designated as SSSSV, and its computing formula is
Step 4, the axle temperature climbing speed utilizing described step 3 to obtain carry out the aging analysis of axletree:
By high ferro axle temperature climbing speed SSJSL and this axletree axle temperature rising reference speed rate SSJSL
0compare, axletree axle temperature rising reference speed rate SSJSL
0for SSJSL
0=0.8299, the judgement that axletree is aging with foundation is:
Due to a=1.1, b=2.5, then a< α <b, can find out that train axle belongs to slightly aging, according to actual conditions, along with train long-play, axle temperature climbing speed increases gradually.
Because data in embodiment are above less, cause the curve visual effect drawn out and not obvious, in order to a kind of visual effect of the best can be reached, axle temperature image data amount is expanded as more than 70,000 sampled point, draw initial axle temperature signal curve schematic diagram, as Fig. 7, after data in Fig. 7 are carried out interpolation, axle temperature signal curve schematic diagram as shown in Figure 8, TIME layer scattering wavelet transformation is carried out to the axle temperature data in pretreated Fig. 8, axle temperature data and curves schematic diagram after TIME layer scattering wavelet transformation decomposes as shown in Figure 9, TIME is set to 6 smoothing process here.
Claims (8)
1., based on a bullet train axletree aging analysis method for axle temperature data, it is characterized in that, specifically implement according to following steps:
Step 1, pre-service is carried out to train speed and axle temperature data;
Step 2, pretreated axle temperature data are carried out to described step 1 carry out smooth treatment;
Step 3, calculating train axle temperature climbing speed;
Step 4, the axle temperature climbing speed utilizing described step 3 to obtain carry out the aging analysis of axletree.
2. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 1, it is characterized in that, described step 1 is specifically implemented according to following steps:
Supplementing of step (1.1), shortage of data point:
Gather train speed spe (i) and axle temperature zw (i), wherein i is corresponding sampling time point, and span is 1 ~ n, searches and processes respectively to train speed spe (i) collected and axle temperature zw (i) all values, if 2≤i≤n, i ∈ Z
+, Z
+represent positive integer, if the i-th-1 point is non-null value point, and i-th point is null value point, i.e. zw (i-1) ≠ null, zw (i)=null, and processing procedure is as follows:
If zw (i) is isolated missing point, i.e. zw (i-1) ≠ null, zw (i)=null, zw (i+1) ≠ null, then the value of the i-th-1 is assigned to i-th value, namely carries out the operation of zw (i)=zw (i-1) assignment;
If there is continuous print missing point in former data, its number is m (m > 2), i.e. zw (i+1), zw (i+2) ..., the average of zw (i+m-1) is null, zw (i+m) ≠ null, then according to m≤n or m > n, a point situation is discussed, as follows:
(1) if m > is n, then represent that data are imperfect, analyze and stop;
(2) if m≤n, then carry out linear interpolation processing, detailed process is as follows:
Step a: order
Step b: interpolation operation is carried out to all continuous print missing points, namely
zw (i+j)=zw (i-1)+(j+1) × delta,
zw(i)＝zw(i-1)+delta,
zw(i+1)＝zw(i-1)+2×delta,
.
.
.
zw(i+m-1)＝zw(i-1)＋(m-1)×delta
In like manner, carry out as above same operation according to above step to train speed data spe (i), thus supplement complete by all shortage of datas point, the axle temperature after supplementing and speed data are designated as zw1 (i) and spe1 (i) respectively;
The elimination of step (1.2), isolated zero point:
Judge that whether axle temperature data zw1 (i) that described step (1.1) obtains and speed data spe1 (i) be that isolated zero point is gone forward side by side row relax, concrete operations are as follows:
If i-th axle temperature data is not 0, i.e. zw1 (i) ≠ 0, then do not carry out any operation;
If i-th axle temperature data is 0, i.e. zw1 (i)=0, then continue to judge whether its adjacent data zw1 (i-1) and zw1 (i+1) is also zero point, as follows:
(1) if the i-th-1 axle temperature data and the i-th+1 axle temperature data have and only have one to be 0, namely zw1 (i-1)=0 or zw1 (i+1)=0, be then considered as normal data by zw1 (i)=0, do not carry out any operation;
(2) if the i-th-1 axle temperature data are not 0 and the i-th+1 axle temperature data are not 0 yet, namely zw1 (i-1) ≠ 0 and zw1 (i+1) ≠ 0, be then considered as isolated zero point, now by zw1 (i)
In like manner, according to above step, also identical estimation & disposing is carried out to speed data spe1 (i), processed by all isolated zero point, the axle temperature data obtained after eliminating isolated point are designated as zw2 (i), and the speed data obtained is designated as spe2 (i).
3. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 1, it is characterized in that, described step 2 is specifically implemented according to following steps:
Carry out pretreated axle temperature data zw2 (i) to described step 1 and carry out TIME layer scattering wavelet transformation, TIME layer scattering wavelet transformation detailed process is as follows:
Step a: array variable data is set, and make data=zw2 (i); Intermediate variable time=0 is set;
Step b: data in described step a is upgraded according to following formula:
and intermediate variable time is carried out adding 1 operation, i.e. time=time+1, wherein, H (k) represents low-pass filter, and j represents array data length
namely
Step c: if time < is TIME, then return step b, if time >=TIME, then complete the smooth treatment of data, and the axle temperature data after smooth treatment are designated as array DATA (i), even DATA (i)=data;
Be eliminated by the noise signal in above-mentioned conversion process axle temperature data, make axle temperature curve more level and smooth, the first transition for temperature data obtains and provides basis.
4. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 3, it is characterized in that, in the step b of described step 2, the length K=length (data) of H (k), represents identical with axle temperature data data length.
5. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 3, is characterized in that, in the step c of described step 2, and TIME ∈ Z
+.
6. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 1, it is characterized in that, described step 3 is specifically implemented according to following steps:
The extraction of step (3.1), axle temperature first transition:
To the axle temperature data after described step 2 processes, carry out the extraction of first transition, specific as follows: the axle temperature data after step 2 being processed take turns doing difference, difference is designated as φ, i.e. φ=DATA (i)-DATA (i+1), if during φ > 0, this axle temperature interval [i is described, i+1] axle temperature not at ascent stage, may be in decline or not change, then continue to do difference and extract; If during φ < 0, this axle temperature interval [i, i+1] is axle temperature first transition, stores starting point i and the terminal i+1 of the sampled point of first transition, and exists in new array up;
The speed screening of step (3.2), axle temperature first transition:
If threshold speed is V, if sampling time point corresponding to each first transition starting point i in described step (3.1) and terminal j is for i × 2
tIMEwith j × 2
tIME, then corresponding velocity amplitude spe2 (i × 2
tIME) and spe2 (j × 2
tIME).If spe2 (i × 2
tIME) < V and spe2 (j × 2
tIME) < V, then illustrate that this ascent stage [i, j] may be shutdown phase, the train axle temperature under ambient temperature effect heats up, then do not retain this axle temperature first transition; If spe2 (i × 2
tIME)>=V and spe2 (j × 2
tIME)>=V, then illustrate axle temperature first transition when this ascent stage [i, j] is train operation, retains and continue to judge;
The calculating of step (3.3), axle temperature climbing speed:
Carry out climbing speed calculating to the axle temperature data after step (3.2) process, computation process is as follows:
Step (3.3.1), the axle temperature difference of each for axle temperature first transition is designated as fz, corresponding each rise time is designated as t, and the average of each ascending velocity is designated as v, and the computing formula of fz, t, v is as follows respectively:
fz＝DATA(j)-DATA(i)，
t＝(j-i)×2
TIME，
wherein i and j is respectively starting point and the terminal of axle temperature first transition;
Step (3.3.2), axle temperature climbing speed is set as the computing formula of SSJSL, SSJSL to be
the ratio of axle temperature summation and speed average summation is designated as SSSSV, and its computing formula is
7. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 6, it is characterized in that, in described step (3.2), threshold speed is V=2.
8. a kind of bullet train axletree aging analysis method based on axle temperature data according to claim 1, it is characterized in that, described step 4 is specifically implemented according to following steps:
Step (4.1), calculate the high ferro axle temperature climbing speed SSJSL of in described step 3 n days
i(i=1,2 ... n), computing formula is
wherein m is i-th day axle temperature data point number;
Step (4.2), the high ferro axle temperature climbing speed SSJSL of n days will obtained in described step (4.1)
i(i=1,2 ... n) with this axletree axle temperature rising reference speed rate SSJSL
0compare, axletree axle temperature rising reference speed rate SSJSL
0computing formula is
K is reference speed rate sampling number of days, k=100, and the judgement that axletree is aging with foundation is:
(1) as α >=a, train axle is slightly aging;
(2) as α >=b, train axle severe is aging,
Wherein a < b, a, b ∈ R, a is slight aging coefficient, and b is severe aging coefficient, a=1.1, b=2.5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510390862.4A CN105045983B (en) | 2015-07-06 | 2015-07-06 | A kind of bullet train axletree aging analysis method based on axle temperature data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510390862.4A CN105045983B (en) | 2015-07-06 | 2015-07-06 | A kind of bullet train axletree aging analysis method based on axle temperature data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105045983A true CN105045983A (en) | 2015-11-11 |
| CN105045983B CN105045983B (en) | 2018-02-02 |
Family
ID=54452526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510390862.4A Active CN105045983B (en) | 2015-07-06 | 2015-07-06 | A kind of bullet train axletree aging analysis method based on axle temperature data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105045983B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976578A (en) * | 2016-07-21 | 2016-09-28 | 西安理工大学 | High-speed train axle temperature dynamic alarm threshold setting method based on monitoring data |
| CN106528940A (en) * | 2016-10-13 | 2017-03-22 | 中车长春轨道客车股份有限公司 | A method for evaluation and early warning for train axle properties based on mathematical models |
| CN106828106A (en) * | 2016-12-29 | 2017-06-13 | 北京交通大学 | A kind of fault early warning method towards EMUs traction electric machine |
| CN107255560A (en) * | 2017-07-04 | 2017-10-17 | 西安理工大学 | A kind of failure modes of high-speed train braking pipe and diagnostic method based on pressure data |
| CN107527140A (en) * | 2017-07-28 | 2017-12-29 | 西安理工大学 | A kind of bullet train operating condition based on fuzzy membership determines method |
| CN107560848A (en) * | 2017-08-03 | 2018-01-09 | 北京交通大学 | Axle temperature variation model construction method and module, bearing health monitor method and system |
| CN109086832A (en) * | 2018-08-20 | 2018-12-25 | 西安理工大学 | A kind of train magnanimity monitoring big data visualization trend discrimination method |
| CN110210174A (en) * | 2019-06-21 | 2019-09-06 | 西南交通大学 | A kind of EMU axle box bearing temperature predicting method based on multilayer LSTM |
| CN111024416A (en) * | 2018-10-09 | 2020-04-17 | 株洲中车时代电气股份有限公司 | Fault diagnosis method and system for train traction system |
| CN111537230A (en) * | 2020-04-27 | 2020-08-14 | 中车青岛四方机车车辆股份有限公司 | Train bearing temperature early warning method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101181901A (en) * | 2007-12-03 | 2008-05-21 | 北京康拓红外技术有限公司 | Hotbox distinguishing method for train infrared shaft-temperature detecting system |
| CN102455220A (en) * | 2010-10-27 | 2012-05-16 | 北京南车时代信息技术有限公司 | Rail temperature monitoring method and device |
| KR101387018B1 (en) * | 2013-10-31 | 2014-04-18 | 한국철도공사 | Axle temperature measuring device in hbd electric rack and method thereof |
-
2015
- 2015-07-06 CN CN201510390862.4A patent/CN105045983B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101181901A (en) * | 2007-12-03 | 2008-05-21 | 北京康拓红外技术有限公司 | Hotbox distinguishing method for train infrared shaft-temperature detecting system |
| CN102455220A (en) * | 2010-10-27 | 2012-05-16 | 北京南车时代信息技术有限公司 | Rail temperature monitoring method and device |
| KR101387018B1 (en) * | 2013-10-31 | 2014-04-18 | 한국철도공사 | Axle temperature measuring device in hbd electric rack and method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 刘涛: "高速铁路列车轴温探测***的研究与设计", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 曹源 等: "基于DTW的车辆轴温监测方法", 《交通运输工程学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976578A (en) * | 2016-07-21 | 2016-09-28 | 西安理工大学 | High-speed train axle temperature dynamic alarm threshold setting method based on monitoring data |
| CN106528940B (en) * | 2016-10-13 | 2019-04-02 | 中车长春轨道客车股份有限公司 | The method that evaluation and early warning are carried out to train axle performance based on mathematical model |
| CN106528940A (en) * | 2016-10-13 | 2017-03-22 | 中车长春轨道客车股份有限公司 | A method for evaluation and early warning for train axle properties based on mathematical models |
| CN106828106A (en) * | 2016-12-29 | 2017-06-13 | 北京交通大学 | A kind of fault early warning method towards EMUs traction electric machine |
| CN107255560A (en) * | 2017-07-04 | 2017-10-17 | 西安理工大学 | A kind of failure modes of high-speed train braking pipe and diagnostic method based on pressure data |
| CN107527140A (en) * | 2017-07-28 | 2017-12-29 | 西安理工大学 | A kind of bullet train operating condition based on fuzzy membership determines method |
| CN107560848B (en) * | 2017-08-03 | 2019-11-22 | 北京交通大学 | Axis temperature variation model construction method and module, bearing health monitor method and system |
| CN107560848A (en) * | 2017-08-03 | 2018-01-09 | 北京交通大学 | Axle temperature variation model construction method and module, bearing health monitor method and system |
| CN109086832A (en) * | 2018-08-20 | 2018-12-25 | 西安理工大学 | A kind of train magnanimity monitoring big data visualization trend discrimination method |
| CN109086832B (en) * | 2018-08-20 | 2021-11-16 | 西安理工大学 | Visual trend discrimination method for mass monitoring big data of train |
| CN111024416A (en) * | 2018-10-09 | 2020-04-17 | 株洲中车时代电气股份有限公司 | Fault diagnosis method and system for train traction system |
| CN111024416B (en) * | 2018-10-09 | 2021-08-10 | 株洲中车时代电气股份有限公司 | Fault diagnosis method and system for train traction system |
| CN110210174A (en) * | 2019-06-21 | 2019-09-06 | 西南交通大学 | A kind of EMU axle box bearing temperature predicting method based on multilayer LSTM |
| CN111537230A (en) * | 2020-04-27 | 2020-08-14 | 中车青岛四方机车车辆股份有限公司 | Train bearing temperature early warning method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105045983B (en) | 2018-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105045983A (en) | Axle ageing analysis method of high speed train on the basis of axle temperature data | |
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| US11066087B2 (en) | Maintenance assistance system and maintenance assistance method for railroad ground equipment | |
| CN105241660A (en) | High-speed rail large-scale bridge performance evaluation method based on health monitoring data | |
| CN103278771B (en) | Identification method for abnormal state of three-phase asynchronous motor at industrial site | |
| CN108515984B (en) | Wheel damage detection method and device | |
| CN111046564A (en) | Method for predicting residual life of two-stage degraded product | |
| CN103018601B (en) | Primary fault diagnosis method of converter in wind turbine system | |
| CN103544389A (en) | Fault tree and fuzzy neural network based automobile crane fault diagnosis method | |
| CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
| CN106650122B (en) | A kind of equipment variable parameter operation methods of risk assessment | |
| CN105923014B (en) | A kind of track transition Amplitude Estimation method based on evidential reasoning rule | |
| CN107272651B (en) | A kind of Robust Detection Method of Braking System for Multiple Units interval multiplying property sensor fault | |
| CN111071291B (en) | Train wheel set monitoring system and train wheel set monitoring method | |
| CN107403139A (en) | A kind of municipal rail train wheel flat fault detection method | |
| CN107776606B (en) | Fault detection method for shaft temperature monitoring system | |
| CN106546924A (en) | A kind of dynamic prediction method of automobile lithium battery performance | |
| CN107228769B (en) | Energy-saving effect monitoring and evaluating method and system based on vehicle oil consumption | |
| CN114330096B (en) | Rail transit motor bearing fault degree classification model construction method based on deep learning | |
| CN107782548B (en) | Rail vehicle part detection system | |
| CN114781657A (en) | Power equipment maintenance system and method based on artificial intelligence | |
| CN113032907A (en) | Method and system for correcting vehicle shaking disease data deviation based on waveform correlation | |
| CN104143158A (en) | Method for monitoring reliability of power system element under condition of multiple meteorological factors | |
| CN106649951A (en) | Axle speed measurement-based train speed calculation method | |
| CN109211556B (en) | Rail vehicle spare part detecting system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20240204 Address after: 518000 1002, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province Patentee after: Shenzhen Wanzhida Technology Co.,Ltd. Country or region after: China Address before: 710048 No. 5 Jinhua South Road, Shaanxi, Xi'an Patentee before: XI'AN University OF TECHNOLOGY Country or region before: China |
|
| TR01 | Transfer of patent right |