CN111523253B - Method for determining suction time threshold of railway relay based on load fusion data - Google Patents
Method for determining suction time threshold of railway relay based on load fusion data Download PDFInfo
- Publication number
- CN111523253B CN111523253B CN202010545563.4A CN202010545563A CN111523253B CN 111523253 B CN111523253 B CN 111523253B CN 202010545563 A CN202010545563 A CN 202010545563A CN 111523253 B CN111523253 B CN 111523253B
- Authority
- CN
- China
- Prior art keywords
- fusion
- data
- suction time
- load
- relay
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000013178 mathematical model Methods 0.000 claims abstract description 7
- 238000007499 fusion processing Methods 0.000 claims abstract description 6
- 230000009467 reduction Effects 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for determining a suction time threshold of a railway relay based on load fusion data. The method for determining the suction time threshold of the railway relay based on the load fusion data comprises the following steps: and 6 kinds of relevant parameter data of all samples of the railway relay in the accelerated life test are arranged, the dimension reduction processing is carried out on the initial data after the initial data are arranged, the fusion processing is carried out on the parameter threshold values, the mathematical model of the life prediction of the railway relay is determined, the fusion result is input into the mathematical model, the time when the result reaches the failure threshold value is the life of the railway relay, the suction time is input into the life prediction mathematical model for training, and the corresponding time when the result reaches the life of the railway relay is the suction time threshold value. The accuracy of the life prediction of the railway relay is improved by utilizing the load fusion data, and a good basis is provided for determining the suction time threshold value of the railway relay.
Description
Technical Field
The invention relates to the technical field of reliability, in particular to a method for determining a suction time threshold of a railway relay based on load fusion data.
Background
The railway relay is an important basic component in the railway signal equipment system, is an irreplaceable part, and the working reliability of the railway relay also affects the safe operation of the whole railway system, and monitors various parameters of the railway relay in operation, wherein the threshold value of the suction time of the railway relay is not accurately fixed, and the determination of the suction time threshold value is an important basis for judging whether the railway relay fails.
The traditional method for predicting the life of the railway relay mostly achieves the purpose of predicting the life of the railway relay through analysis and prediction of single parameters. Researches prove that the life prediction and evaluation of the single parameter to the relay are not accurate enough, and in order to break through the defect, the method for researching the load fusion data predicts the life of the railway relay, and has higher accuracy than the traditional method.
In the literature (Miao Jianwei, wang Wenjun, li) intelligent prediction analysis of the service life of a low-voltage relay [ J ]. Electric appliance and energy efficiency management technology, 2018 (04): 61-65.) a method for testing the service life of the relay is designed by taking the suction time as a main characteristic parameter, a BP neural network algorithm and a gray theory algorithm are selected to perform prediction analysis on the service life of the relay, prediction performance of the two intelligent algorithms is evaluated through a prediction result, and a prediction idea is shown in figure 2. The relay has complex performance, and obviously, the method of predicting and analyzing the service life of the relay by only using one parameter is not perfect, and a predicted result may have larger error.
The invention provides a method for determining the suction time threshold of a railway relay based on load fusion data, which is used for determining the suction time threshold of the relay.
Disclosure of Invention
Parameters monitored after the end of every 20 thousands of experiments in the accelerated life test process include the parameters of a movable joint pressure, a movable break joint pressure, an absolute gap, a pull-in voltage, a release voltage and a contact resistance, and the change of each parameter reflects the performance parameter degradation process of the relay.
When the degradation performance of the railway relay is analyzed, only one parameter change cannot be concerned, and each parameter which has influence on the service life of the railway relay is comprehensively considered. The parameters for representing the performance of the relay are many, but the prediction analysis of the service life of the relay by only using a certain parameter is not accurate enough, and the service life of the relay cannot be comprehensively estimated. The suction time threshold of the railway relay is difficult to determine in actual use, and the suction time is an effective basis for detecting whether the railway relay fails.
In order to solve the above problems and achieve the objective of prediction, the present invention provides a method for determining a suction time threshold of a railway relay based on load fusion data, where the method for determining the suction time threshold of the railway relay based on the load fusion data is as follows:
6 kinds of relevant parameter data of the accelerated life test railway relay are firstly arranged.
And performing dimension reduction processing and fusion on the parameters, and performing fusion processing on the threshold values of the parameters. Firstly, carrying out dimensionless treatment on the original data to obtain standardized data:
for each sequence X:
wherein m is 6 parameters, n is the data quantity selected by each parameter;
normalized equation (for the first column), add 1 successively from 1 to n to i to obtain the sequence y i1 ：
Wherein:
similarly, calculate y i2 ，y i3 ，...y im ；
Finally, the transformed sequence Y is obtained:
the covariance matrix is calculated for the new matrix obtained, and covariance cov (x, y) is defined as follows:
cov(x，y)＝E[(x-μ x )(y-μ y )]
wherein E (x) =μ x ，E(y)＝μ y ；
Thus, for a matrix
The covariance matrix is obtained as follows:
the eigenvalue lambda of the covariance matrix is obtained from |Y- λE|=0 i (i=1, 2, …, m) and feature vector e i (i=1, 2,., m), and the feature vectors are arranged in order of feature value.
The ratio of each element and the cumulative ratio are calculated by the characteristic value:
cumulative ratio of:
the elements with the accumulated occupation ratio of large and 90% are selected for the next calculation.
The benefit of performing dimension reduction processing re-fusion on the original data is that the above process can effectively reduce the dimension of the original data and lose as little information of the original data as possible.
According to the calculation result, calculating element load:
wherein e ij Is a value in the feature vector.
The load matrix is as follows:
the load matrix represents the load of each parameter at the corresponding element. And fusing the original data through the obtained load matrix and the occupation ratio of each element. The number of elements obtained after the dimension reduction processing is the same as the number of the categories of the original parameters, namely m elements, and the cumulative occupation ratio of p (p < m) elements before is assumed to be greater than or equal to 90%, and the fusion process is as follows.
The load of each original parameter in the corresponding element is multiplied by the original data respectively, and then the original data are added to obtain a new matrix as follows:
the ratio of each element is different, and the above fused matrixes can be fused again. The corresponding ratio lambda of each element i (i < p) total occupancy ratio lgx of selected elements p Multiplying the specific gravity of (1) by the corresponding fusion result rh i The method comprises the following steps:
the selected parameters have fixed thresholds, and the thresholds are respectively fused into rhyz according to the processing 1 ，rhyz 2 ，…，rhyz p And eventually fused to zrhyz.
The process for establishing the life prediction model of the railway relay is as follows:
s1: from the original data sequence x 0 ＝{x 0 (1)，x 0 (2)，…x 0 (n) } cumulatively generating x 1 ＝{x 0 (1)，x 0 (2)，…x 0 (n) } to generate the sequence x 1 Satisfy first order ordinary differential equation
Unknown;
s2: establishing matrix B, Y n ，Y n =bu, wherein:
s3: inversion matrix (B) T B) -1 ；
S4: according to
Evaluate->
And->
S5: the results obtained are taken into the equation:
when k=1, 2, …, n-1, calculated from the above formula
Is a fitting value; />
When k is more than or equal to n,
for the forecast value。
S6: and (3) precision inspection and prediction, inputting the fusion result into a prediction model for prediction, and judging that the railway relay reaches the service life when the result reaches a set threshold value. When the error is between 0.8 and 0.95 and the ratio is between 0.35 and 0.45, the prediction result is qualified.
And the service life of the railway relay obtained by data fusion prediction is input into a prediction model by the suction time of the existing railway relay, and when the service life of the railway relay is reached, the corresponding data is the threshold value of the suction time.
As described above, the present invention has the advantages that:
(1) The invention breaks through the traditional method for predicting the service life of a relay by using a single parameter, and provides a method for predicting the service life of the relay based on load fusion data.
(2) The method for reducing the dimensionality of the original data and then fusing the original data can effectively reduce the dimensionality of the original data, and can retain most of original information of the original data.
(3) The invention considers the load of each parameter in a certain element in the fusion process, and considers the weight of a certain element in all selected elements, thereby improving the reliability.
(4) According to the invention, the parameters affecting the service life of the railway relay are utilized to carry out data fusion, the service life of the railway relay is predicted, the influence of all the parameters is comprehensively considered, and after the predicted service life of the railway relay is obtained, the service life prediction model is utilized again to determine the threshold value of the suction time of the railway relay.
Drawings
Fig. 1 is a schematic diagram of a structure for determining a suction time threshold of a railway relay in the prior art.
Fig. 2 is a prediction process for predicting the life of the relay with the suction time.
FIG. 3 is a schematic diagram of a life prediction model according to the present invention.
Fig. 4 railway relay life prediction curves.
Fig. 5 railway relay suction time prediction curve.
Detailed Description
The following provides a specific implementation of the present invention.
In the test process of 0 to 200 ten thousand times of accelerated life test of the railway relay at constant temperature, parameters are measured once every 20 ten thousand times of actions, and 11 times of data are obtained. And (3) finishing 6 parameters of the pressure movement of a movable joint, the pressure of a breaking joint, an absolute gap, an attracting voltage, a releasing voltage and a joint resistance of one railway relay. Carrying out standardization processing on the original data to obtain standardized data:
table 1 data table after normalization of parameters
| -0.6444 | 1.6370 | 1.2103 | -1.7566 | -0.4567 | -0.7910 |
| 1.5366 | 0.4753 | 0.4624 | -1.6503 | 0.0864 | -0.4691 |
| 0.9914 | -0.1056 | 2.4070 | 0.3707 | 0.6294 | -0.7584 |
| 1.5366 | 1.0561 | -0.4352 | -0.8171 | 0.901 | -0.8307 |
| -1.1896 | 1.0561 | -0.7343 | -0.3384 | 0.7652 | -0.5064 |
| 0.4461 | 0.4753 | -1.0335 | 0.4770 | 0.5616 | -0.4084 |
| -0.6444 | -1.2674 | -0.2856 | 0.9557 | 1.444 | -0.8983 |
| -0.0991 | -0.6865 | -0.4352 | 1.0266 | -0.1173 | 0.2074 |
| -0.6444 | -0.6865 | -0.4352 | 0.6720 | -0.5924 | 1.4718 |
| -0.0991 | -0.6865 | -0.2856 | 0.3529 | -1.4749 | 1.4858 |
| -1.1896 | -1.2674 | -0.4352 | 0.7075 | -1.7464 | 1.4974 |
The covariance matrix of the normalized data matrix is found as shown in table 2:
table 2 covariance matrix of normalized data
| 1 | 0.3052 | 0.3114 | -0.3704 | 0.3462 | -0.4138 |
| 0.3052 | 1 | 0.1927 | -0.8209 | 0.3137 | 0.5976 |
| 0.3114 | 0.1927 | 1 | -0.3307 | 0.0546 | -0.3394 |
| -0.3704 | -0.8209 | -0.3307 | 1 | -0.0729 | 0.4465 |
| 0.3462 | 0.3137 | 0.0546 | -0.0729 | 1 | -0.8522 |
| -0.4138 | 0.5976 | -0.3394 | 0.4465 | -0.8522 | 1 |
Eigenvalues and eigenvectors of the covariance matrix are obtained from |y- λe|=0, and the vectors are arranged in order of magnitude of the eigenvalues.
Eigenvalue lambda i (i=1, 2, …, 6) is λ in order from the larger to the smaller 1 ＝3.0102，λ 2 ＝1.2307，λ 3 ＝0.9312，λ 4 ＝0.6516，λ 5 ＝0.1292，λ 6 =0.0470, the corresponding eigenvectors are:
table 3 each element obtained by arranging the corresponding eigenvectors of each eigenvalue from large to small:
| element one | Element two | Element three | Element four | Element five | Element six |
| -1.8355 | -1.7725 | -0.5530 | -1.2793 | -0.0189 | -0.1613 |
| -1.8744 | -0.8838 | 0.3435 | 0.9675 | -0.6295 | 0.0829 |
| -1.4148 | 0.2063 | 2.2951 | -0.6403 | 0.4122 | 0.0668 |
| -2.0381 | 0.3210 | -0.4245 | 1.1789 | 0.0882 | 0.0235 |
| -0.5557 | 0.4134 | -1.6621 | -0.8455 | 0.1703 | 0.2005 |
| -0.3204 | 0.9431 | -0.7117 | 0.6798 | 0.4373 | -0.2253 |
| 0.3070 | 2.1976 | 0.2272 | -0.7345 | -0.6274 | -0.0015 |
| 1.0592 | 0.7021 | 0.2153 | 0.1794 | 0.1627 | -0.2474 |
| 1.9275 | -0.2400 | -0.0450 | 0.1102 | 0.1567 | 0.4828 |
| 1.8919 | -1.0372 | 0.2613 | 0.5847 | 0.0685 | -0.0037 |
| 2.8534 | -0.8500 | 0.0539 | -0.2008 | -0.2202 | -0.2173 |
Calculating the ratio of each element by the obtained characteristic value
Gx in turn 1 ＝50.1703％，gx 2 ＝20.5123％，gx 3 ＝15.5194％，gx 4 ＝10.8597，gx 5 ＝2.1541％，gx 5 ＝0.7841％。
After the occupation ratio of each element is obtained, the element accumulated occupation ratio is obtained by sequentially accumulating
In turn lgx 1 ＝50.1703％，lgx 2 ＝70.8626％，lgx 3 ＝86.202％，lgx 4 ＝97.0618％，lgx 5 ＝99.216％，lgx 6 =100%. And lgx 4 > 90%, so that in subsequent calculations the selected element is element one to element four. The selection method can effectively reduce the dimension of the original data, and simultaneously retain most of information of the original data.
After obtaining these data, the data is represented by the formula
Obtaining a load matrix:
table 4 load matrix
| Element one | Element two | Element three | Element four | Element five | Element six | |
| Pressure of movable joint | -0.3601 | 0.0157 | 0.4229 | 0.8230 | 0.0958 | -0.0686 |
| Dynamic break junction pressure | -0.4648 | -0.2789 | -0.4488 | -0.0470 | 0.7081 | 0.0343 |
| Absolute gap | -0.2670 | -0.2956 | 0.7429 | -0.4962 | 0.1387 | 0.1552 |
| Pull-in voltage | 0.4271 | 0.5191 | 0.2538 | -0.0490 | 0.6537 | -0.2324 |
| Releasing voltage | -0.3738 | 0.6700 | -0.0512 | -0.0916 | -0.0506 | 0.6307 |
| Contact resistance | 0.5107 | -0.3410 | 0.0284 | 0.2520 | 0.2008 | 0.7199 |
The original data is fused according to the above data, and the original data is fused according to the following manner, and the fusion result is shown in table 5:
rh 1 ＝I 11 *X 1 +I 21 *X 2 +…+I 61 *X 6
rh 2 ＝I 12 *X 1 +I 22 *X 2 +…+I 62 *X 6
rh 3 ＝I 13 *X 1 +I 23 *X 2 +…+I 63 *X 6
rh 4 ＝I 14 *X 1 +I 24 *X 2 +…+I 64 *X 6
TABLE 5 fusion results
| rh 1 | rh 2 | rh 3 | rh 4 |
| -227.2213 | -57.1155 | 31.1934 | 260.4732 |
| -229.0615 | -54.3835 | 44.1525 | 277.7655 |
| -225.1479 | -52.0378 | 44.6286 | 273.4453 |
| -232.0051 | -54.9074 | 41.9331 | 277.1356 |
| -222.1646 | -55.6412 | 31.4548 | 256.9094 |
| -224.8146 | -53.9298 | 40.1576 | 269.5854 |
| -215.2607 | -48.9747 | 42.7000 | 261.4813 |
| -216.8588 | -52.0375 | 42.7196 | 266.5798 |
| -212.3495 | -54.1149 | 40.7119 | 263.8469 |
| -214.1503 | -54.2404 | 42.7965 | 267.9928 |
| -208.0968 | -52.9399 | 40.8583 | 260.0092 |
The ratio of each element is known, and the ratio lambda is corresponding to each element i (i < p) total occupancy ratio lgx of selected elements 4 The specific gravity of (2) multiplied by the corresponding fusion result, the final fusion result matrix is shown in table 6:
table 6 results in a final fused matrix
| zrh |
| -95.3947 |
| -91.7615 |
| -89.6501 |
| -93.8193 |
| -92.8262 |
| -91.0245 |
| -85.5386 |
| -86.4386 |
| -85.1736 |
| -85.3338 |
| -83.1329 |
The threshold values of the parameters are fused according to the obtained element occupation ratio and the load matrix, and the result after threshold value fusion is shown in table 7:
TABLE 7 results after threshold fusion
| rhyz 1 | rhyz 2 | rhyz 3 | rhyz 4 |
| -128.4512 | -44.0991 | 44.2942 | 209.9117 |
And combining the results with the element ratios to obtain zrhyz= -45.1467.
And inputting the fusion result of the obtained original data into a mathematical model for prediction, modifying the number of predictions, and judging that the railway relay fails when the prediction result reaches the threshold fusion result. As shown in FIG. 2, the predicted life of the railway relay is 1220 ten thousand times by multiplying the number of times corresponding to the predicted result by 20 ten thousand times, which is the predicted life of the railway relay, by taking the parameters corresponding to the parameters with the abscissa of 62 as the predicted life of the railway relay as the used parameters are every 20 ten thousand times of test data.
The error is more than 0.8 and less than 0.8182 and less than 0.95, the ratio is more than 0.35 and less than 0.4231 and less than 0.45, and the test result is qualified.
According to the predicted result, the suction time measured in the test process is input into a life prediction model of the railway relay, the predicted times are input, and the numerical value corresponding to the predicted times is the threshold value of the suction time. The error is more than 0.8 and less than 0.9052 and less than 0.95, the ratio is more than 0.35 and less than 0.4138 and less than 0.45, and the inspection result is qualified. The predicted curve is shown in fig. 3, and the threshold values of the suction time obtained by the mathematical model are shown in table 8:
table 8 railway relay life and suction time threshold obtained by mathematical model
| Predicted lifetime | Suction time threshold |
| 1220 ten thousand times | 227.71ms |
The above results indicate that: the invention can effectively predict the suction time threshold of the railway relay.
Claims (5)
1. A method for determining a railway relay suction time threshold based on load fusion data, the method for determining the railway relay suction time threshold based on load fusion data comprising the steps of:
s1: 6 relevant parameter data of a relay of a specific model in an accelerated life test are arranged;
s2: performing dimension reduction processing and fusion on the parameters, and performing fusion processing on the threshold values of the parameters; firstly, carrying out dimensionless treatment on the original data to obtain standardized data:
for each sequence X:
wherein m is 6 parameters, n is the data quantity selected by each parameter;
finally, the transformed sequence y is obtained:
s3: solving covariance matrix of the new matrix, and simultaneously solving eigenvalue lambda of covariance matrix i And feature vector e i Wherein i=1, 2, …, m, and the eigenvectors are arranged in eigenvalue size;
calculating the occupation ratio and the accumulated occupation ratio of each element, and selecting the elements with the accumulated occupation ratio more than 90% to perform the next calculation;
by means of
Calculating an element load matrix:
The load matrix represents the load amount of each parameter on the corresponding element;
performing added fusion according to the obtained result;
s4: the element number obtained after the dimension reduction processing is the same as the original parameter category number, namely m elements, and the accumulated occupation ratio of the p elements is greater than or equal to 90%, wherein p is smaller than m, and the fusion process is as follows: multiplying each original parameter by the original data respectively at the load of the corresponding element, and adding to obtain a new matrix;
s5: the occupation ratio of each element is different, the fused matrixes can be fused again, and the occupation ratio lambda corresponding to each element i A total occupancy ratio lgx of the selected elements p Multiplying the specific gravity of (2) by the corresponding fusion result rhi, and adding to obtain zrh, wherein i is less than p;
the selected parameters have fixed thresholds, and the thresholds are respectively fused into rhyz1, rhyz2, … and rhyzp, and finally fused into zrhyz;
s6: determining a mathematical model for predicting the service life of the railway relay, wherein the modeling process is as follows:
from the original data sequence X 0 ＝{X 0 (1),X 0 (2),…X 0 (n) } cumulatively generating X 1 ＝{X 0 (1),X 0 (2),…X 0 (n) } to generate the sequence X (1) Satisfy first order ordinary differential equation
a, u is unknown;
establishing matrix B, Y n ，Y n =bu, wherein:
inversion matrix (B) T B) -1 ；
According to
Evaluate->
And->
Substituting the obtained result into equation
When k=1, 2, …, n-1, calculated from the above formula
Is a fitting value;
when k is more than or equal to n,
is a forecast value;
the precision test and prediction are carried out, the fusion result is input into a prediction model for prediction, and when the prediction result reaches a set threshold value, the railway relay is judged to reach the service life; when the error is between 0.8 and 0.95 and the ratio is between 0.35 and 0.45, the prediction result is qualified;
s7: the existing test data of the suction time are input into a prediction model, and when the test data reach the service life of the railway relay, the corresponding time is the threshold value of the suction time.
2. The method for determining a railway relay suction time threshold based on load fusion data according to claim 1, wherein the standard transformation formula in step S2 is:
wherein:
3. the method for determining a suction time threshold of a railway relay based on load fusion data according to claim 1, wherein the calculation formula of the occupation ratio of each element and the accumulated occupation ratio through the feature values in the step S3 is as follows:
cumulative ratio of:
4. the method for determining a suction time threshold of a railway relay based on load fusion data according to claim 1, wherein the fusion formula in step S4 is:
rh 1 ＝I 11 *X 1 +I 21 *X 2 +…+I m1 *X m
rh 2 ＝I 12 *X 1 +I 22 *X 2 +…+I m2 *X m
rh p ＝I 1p *X 1 +I 2p *X 2 +…+I mp *X m 。
5. the method for determining a railway relay suction time threshold based on load fusion data according to claim 1, wherein the re-fusion formula in step S5 is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545563.4A CN111523253B (en) | 2020-06-16 | 2020-06-16 | Method for determining suction time threshold of railway relay based on load fusion data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545563.4A CN111523253B (en) | 2020-06-16 | 2020-06-16 | Method for determining suction time threshold of railway relay based on load fusion data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111523253A CN111523253A (en) | 2020-08-11 |
| CN111523253B true CN111523253B (en) | 2023-05-16 |
Family
ID=71912984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010545563.4A Active CN111523253B (en) | 2020-06-16 | 2020-06-16 | Method for determining suction time threshold of railway relay based on load fusion data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523253B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446157A (en) * | 2020-12-14 | 2021-03-05 | 广东省科学院智能制造研究所 | Method and device for predicting residual life of traffic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446317A (en) * | 2016-06-01 | 2017-02-22 | 河北工业大学 | Mathematic model-based sealed relay storage life prediction method |
| CN110332103A (en) * | 2019-07-29 | 2019-10-15 | 浙江鸿友压缩机制造有限公司 | Electron pressure switch with time-delay closing unloading electromagnetic valve |
-
2020
- 2020-06-16 CN CN202010545563.4A patent/CN111523253B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446317A (en) * | 2016-06-01 | 2017-02-22 | 河北工业大学 | Mathematic model-based sealed relay storage life prediction method |
| CN110332103A (en) * | 2019-07-29 | 2019-10-15 | 浙江鸿友压缩机制造有限公司 | Electron pressure switch with time-delay closing unloading electromagnetic valve |
Non-Patent Citations (4)
| Title |
|---|
| Life Prediction of Electromagnetic Relay Based on;Jiang Wenman et al.;《2018 IEEE International Conference of Safety Produce》;20190414;第340-345页 * |
| Research on life prediction based on wavelet;Qiong Yu et al.;《2009 4th IEEE Conference on Industrial Electronics and》;20090630;第1275-1280页 * |
| 航天继电器步退加速寿命试验温度应力;李文华等;《航天控制》;20181031;第36卷(第5期);第15-20、75页 * |
| 铁磁性多余物对航天继电器;李超等;《电器与能效管理技术》;20161231;第87-92、98页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111523253A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108664700B (en) | Accelerated degradation information fusion modeling method based on uncertain data envelope analysis | |
| Xiao et al. | Decentralized PCA modeling based on relevance and redundancy variable selection and its application to large-scale dynamic process monitoring | |
| Li et al. | A mutated particle filter technique for system state estimation and battery life prediction | |
| CN108535656A (en) | Lithium ion battery remaining life prediction technique and system based on PCA-NARX neural networks | |
| CN113702855B (en) | Lithium battery pack health state online prediction method based on multi-physical-field simulation and neural network method | |
| CN109409425B (en) | Fault type identification method based on neighbor component analysis | |
| Li et al. | Residual useful life estimation by a data‐driven similarity‐based approach | |
| CN109030790A (en) | A kind of method for diagnosing fault of power transformer and device | |
| CN106295858A (en) | A kind of electric energy meter non-health degree Forecasting Methodology | |
| CN110782546A (en) | Resistivity virtual measurement method of semiconductor PVD (physical vapor deposition) process based on combined tree model | |
| CN117494584B (en) | High-dimensional reliability design optimization method based on neural network anti-migration learning | |
| Lyu et al. | Reliability analysis of the multi-state system with nonlinear degradation model under Markov environment | |
| CN111523253B (en) | Method for determining suction time threshold of railway relay based on load fusion data | |
| Yuan et al. | A Bayesian approach to degradation-based burn-in optimization for display products exhibiting two-phase degradation patterns | |
| CN108830006B (en) | Linear-nonlinear industrial process fault detection method based on linear evaluation factor | |
| Mao et al. | Comparative study on prediction of fuel cell performance using machine learning approaches | |
| CN108647897A (en) | A kind of method and system of product reliability analysis | |
| CN114611067A (en) | Chemical process slow-change fault detection method based on typical variable dissimilarity analysis | |
| CN111310781A (en) | Refrigeration equipment refrigerant leakage identification method based on PCA-ANN | |
| Zhang et al. | The early prediction of lithium-ion battery remaining useful life using a novel long short-term memory network | |
| Park et al. | A study on life evaluation & prediction of railway vehicle contactor based on accelerated life test data | |
| Li | Remaining useful life prediction of bearings using fuzzy multimodal extreme learning regression | |
| Li et al. | Remaining life prediction of cores based on data-driven and physical modeling methods | |
| CN114398770A (en) | Service life prediction method for liquid particle counting sensor | |
| Huang et al. | Automatic virtual metrology system design and implementation |
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 | ||
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Shao Wenyu Document name: Notification of Conformity |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |