CN112697308B - Subway bearing temperature early warning method - Google Patents
Subway bearing temperature early warning method Download PDFInfo
- Publication number
- CN112697308B CN112697308B CN202011486948.4A CN202011486948A CN112697308B CN 112697308 B CN112697308 B CN 112697308B CN 202011486948 A CN202011486948 A CN 202011486948A CN 112697308 B CN112697308 B CN 112697308B
- Authority
- CN
- China
- Prior art keywords
- temperature
- bearing
- subway
- alarm prompt
- early warning
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Sliding-Contact Bearings (AREA)
- Rolling Contact Bearings (AREA)
Abstract
The invention discloses a subway bearing temperature early warning method, which comprises the following steps: s1: collecting the temperature of a subway bearing to obtain a set X; s2: the temperature of the subway bearing is processed to obtain a relative temperature set Y of the subway bearing: relative temperature of the metro bearing = temperature of the metro bearing-ambient temperature; s3: calculating the mean value m and standard deviation S of the relative temperature set Y of the subway bearings at the same time point d Skewness f and kurtosis q; s4: if F is greater than the temperature skewness threshold F or Q is greater than the kurtosis threshold Q, executing a first early warning mode; if F is less than or equal to F or Q is less than or equal to Q, executing a second early warning mode; s5: detecting the running time T of the subway bearing, and executing a third early warning mode when T is larger than the preset running time T; when T is less than or equal to T, the temperature detection device is in a dormant state. The relative temperature threshold and the temperature differential threshold are set to calculate and early warn the temperature of the subway bearing, so that early warn precision is improved.
Description
Technical Field
The invention relates to the technical field of electronic control, in particular to a subway bearing temperature early warning method.
Background
The subway bearing is a key part of a train, and the running state of the subway bearing can directly influence the running state and the service performance of the subway. The working environment of the train is bad, when the bearing is defective or fails, the vibration of the axle box bearing is aggravated, the noise is increased, meanwhile, the running stability of the train can be directly influenced along with the increase of the temperature of the bearing, even the running safety of the train is influenced, and huge life and property losses can be brought if the running safety of the train is not monitored and prevented.
Through carrying out on-line monitoring to the subway bearing, but real-time supervision is to the temperature data of each bearing of subway, can judge the running state of bearing through data analysis and data synthesis, has improved stability and the security of subway operation, prevents to be ill in the future to through the analysis of the bearing running state, reasonable arrangement bearing maintenance cycle has reduced maintenance cost.
The traditional alarm strategy is that the bearing and the environment relative temperature or the absolute temperature of the bearing exceeds a threshold value to alarm, and has the following defects:
(1) Bearing temperature differences caused by processing errors, installation accuracy and installation positions among the subway axle box bearings can cause false alarms;
(2) Before the temperature of the bearing exceeds a threshold value, alarming is carried out when the temperature change rate of the bearing is too large, so that alarming is not timely;
(3) The full life cycle of the bearing comprises a running-in period, a stable running period, a fatigue failure period and the like, the change condition of the temperature of the bearing in each stage is different, and the traditional method does not consider the different temperatures of the bearing in each state period, so that false alarm and missing report are caused;
(4) Temperature prediction is not carried out by utilizing bearing temperature historical data, so that early warning is realized.
Disclosure of Invention
Aiming at the problem of low temperature early warning accuracy of the subway bearing in the prior art, the invention provides the temperature early warning method of the subway bearing, which carries out calculation early warning on the temperature of the subway bearing by setting a relative temperature threshold value and a temperature differential threshold value, eliminates false alarm caused by the difference of temperature changes of the subway bearing in different time periods and improves the early warning accuracy.
In order to achieve the above object, the present invention provides the following technical solutions:
a subway bearing temperature early warning method specifically comprises the following steps:
s1: each temperature detection device is fixed on the subway bearing in an average sectional manner through bolts, and the temperatures of the subway bearings are collected to obtain a set X (X) 1 ,X 2 ,...,X i ...,X n ),X i Representing the temperature of the subway bearing of the ith section, X n The temperature of the nth section of subway bearing is represented;
s2: the temperature of the subway bearing is processed to obtain a relative temperature set Y of the subway bearing: relative temperature of the metro bearing = temperature of the metro bearing-ambient temperature;
s3: calculating the mean value m and standard deviation S of the relative temperature set Y of the subway bearings at the same time point d Skewness f and kurtosis q;
s4: if F is greater than the temperature skewness threshold F or Q is greater than the kurtosis threshold Q, executing a first early warning mode; if F is less than or equal to F and Q is less than or equal to Q, executing a second early warning mode;
s5: detecting the running time T of the subway bearing, and executing a third early warning mode when T is larger than the preset running time T; when T is less than or equal to T, the temperature detection device is in a dormant state.
Preferably, the mean value m and the standard deviation S d The calculation formula of (2) is as follows:
in the formula (1), m represents the average value of relative temperature sets Y of the metro bearings, n represents the number of metro bearing segments and Y i Representing the relative temperature of the subway bearing of the ith section, S d The standard deviation of the subway bearing relative temperature set Y is represented;
the calculation formulas of the skewness f and the kurtosis q are as follows:
in the formula (2), f represents the skewness of the metro bearing relative to the temperature set Y, and q represents the kurtosis of the metro bearing relative to the temperature set Y.
Preferably, the first early warning mode is:
a. when Y is i More than T3, corresponding alarm array A i =1, send out alarm prompt, Y i Representing the relative temperature of the subway bearing of the ith section, A i An alarm array representing the ith section of subway bearing, T3 representing a preset third relative temperature threshold valueThe method comprises the steps of carrying out a first treatment on the surface of the If Y i T3 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation b;
b. when Y is i Calculating a relative temperature change rate D according to a formula (3), wherein T2 represents a preset second relative temperature threshold; if D > G2, then corresponding A i =1, sending an alarm prompt, G2 representing a preset second temperature differential threshold; if D is less than or equal to G2, then corresponding A i =0, no alarm prompt is sent; when Y is i T2 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation c;
D＝(Y i -Y i-1 )/T (3)
in the formula (3), Y i Representing the relative temperature of the subway bearing of the ith section, Y i-1 The relative temperature of the i-1 th section of subway bearing is represented, and T represents the preset running time of the subway bearing;
c. predicting subway bearing predicted temperature K i When K is i At > T3, corresponding A i =1, send out alarm prompt, when K i T3 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
Preferably, in the step S4, the second early warning mode is:
d. when Y is i More than T2, corresponding alarm array A i =1, sending out an alarm prompt; if Y i T2 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation e;
e. when Y is i Calculating a relative temperature change rate D according to a formula (3), wherein T1 represents a preset first relative temperature threshold; if D > G1, then corresponding A i =1, sending an alarm prompt, G1 representing a preset first temperature differential threshold; if D is less than or equal to G1, then corresponding A i =0, no alarm prompt is sent; when Y is i T1 is not more than, corresponding to A i =0, not sending an alarm prompt, executing operation f;
f. predicting iron bearing predicted temperature K i When K is i At > T3, corresponding A i =1, send out alarm prompt, when K i T3 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
Preferably, in the step S5, the third early warning mode is:
g. when Y is i > T1, then corresponding A i =1, sending out an alarm prompt; if Y i T1 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation h;
h. when Y is i Calculating the relative temperature change rate D through a formula (3) according to the temperature change rate T1; if D > G1, then corresponding A i =1, sending out an alarm prompt; if D is less than or equal to G1, then corresponding A i =0, does not send out alarm prompt, and simultaneously judges Y i Whether or not m > 2D is true, if Y i -m > 2D, then corresponding A i =1, sending out an alarm prompt; if Y i -m.ltoreq.2D, then corresponding A i =0, no alarm prompt is sent out, and operation j is executed;
j. predicting subway bearing predicted temperature K i When K is i At > T1, corresponding A i =1, send out alarm prompt, when K i T1 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
Preferably, the subway bearing predicts the temperature K i The calculation method of (1) is as follows:
A1. selecting all historical temperature data sets XH (XH 1 ,XH 2 ,...,XH L ),XH L Representing the L-th historical temperature data, namely, the length of the collection XH is L, entering A2 when L is less than or equal to N, entering A3 when L is more than N, and N represents the length threshold value, namely, the number of the historical temperature data;
A2. calculating predicted temperature K of subway bearing i The formula of (2) is as follows:
K i ＝2XH L -XH L-1 ，XH L represents the L-th historical temperature data XH L-1 Represents the L-1 th historical temperature data.
In summary, due to the adoption of the technical scheme, compared with the prior art, the invention has at least the following beneficial effects:
according to the method, the relative temperature threshold and the temperature differential threshold are set to calculate and early warn the temperature of the subway bearing, so that false alarms caused by the difference of the temperature changes of the subway bearing in different time periods are eliminated, and the early warn precision is improved. Meanwhile, the subway bearing temperature is predicted, early warning is achieved, and safety is improved.
Description of the drawings:
fig. 1 is a schematic flow chart of a subway bearing temperature early warning method according to an exemplary embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to examples and embodiments. It should not be construed that the scope of the above subject matter of the present invention is limited to the following embodiments, and all techniques realized based on the present invention are within the scope of the present invention.
In the description of the present invention, it should be understood that the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
As shown in fig. 1, the invention provides a subway bearing temperature early warning method, which comprises the following steps:
s1: and (3) uniformly fixing each temperature detection device on the subway bearing in a segmented manner through bolts, and collecting the temperature of the subway bearing to obtain a set X.
In this embodiment, the metro bearings are long, so that an average sectional installation of a temperature detecting device (temperature sensor) is required to detect the temperature of the corresponding metro bearing. For example, the subway bearing is divided into n sections equally, and the collected temperature set of the iron bearing is X (X 1 ,X 2 ,...,X i ...,X n ),X i Representing the ith section of subway shaftTemperature of the bearing, X n The temperature of the nth section of subway bearing is represented, and the sampling method is to sample through time intervals, wherein the time intervals are 1min.
S2: and processing the temperature of the subway bearing to obtain a relative temperature set Y of the subway bearing.
In this embodiment, in the process of acquiring the temperature data of the metro bearing, because of the noise caused by electromagnetic interference or abnormal temperature, the temperature data has interference data, so that the existing smooth filtering method is required to process the temperature X of the metro bearing.
The relative temperature Y of the metro bearing = the temperature X of the metro bearing-the ambient temperature T.
S3: calculating the mean value m and standard deviation S of the relative temperature set Y of the subway bearings at the same moment d Skewness f and kurtosis q.
Mean value m and standard deviation S of subway bearing relative temperature set Y at same moment d The calculation formula of (2) is as follows:
in the formula (1), m represents the average value of relative temperature sets Y of the metro bearings, n represents the number of metro bearing segments and Y i Representing the relative temperature of the subway bearing of the ith section, S d And the standard deviation of the subway bearing relative to the temperature set Y is shown.
The calculation formulas of the skewness f and the kurtosis q of the subway bearing relative to the temperature set Y at the same moment are as follows:
in the formula (2), f represents the skewness of the metro bearing relative to the temperature set Y, and q represents the kurtosis of the metro bearing relative to the temperature set Y.
S4: if F is greater than either one of the temperature deviation threshold F or Q is greater than the kurtosis threshold Q, executing a first early warning mode; if F is less than or equal to F and Q is less than or equal to Q, executing a second early warning mode.
In this embodiment, each subway bearing corresponds to an alarm array A n An alarm array representing the nth section of subway bearing, when A n =1, sending out an alarm prompt; when A is n =0, and no alarm prompt is issued. Due to the large change of the ambient temperature in one year, the absolute temperature threshold is adopted for alarming: the absolute temperature threshold is determined by considering environmental factors, and false alarms caused by low temperature rise of the subway bearing due to overhigh environmental temperature are also considered. Therefore, the invention adopts the relative temperature threshold, the relative temperature threshold adopts the three-section temperature threshold (T1, T2 and T3, and T1 is less than T2 and less than T3), and the relative temperature threshold is timely selected according to different operation stages of the subway bearing. T1 is an early warning temperature threshold, T2 is an alarm temperature threshold, and T3 is an emergency stop temperature threshold.
The first early warning mode is as follows:
a. when Y is i > T3, then corresponding A i =1, send out alarm prompt, Y i Representing the relative temperature of the subway bearing of the ith section, A i An alarm array for representing the ith section of subway bearing; if Y i T3 is not more than, corresponding to A i =0, no alarm prompt is issued, operation b is performed, and let i=i+1, calculation is continued until i=n.
b. When Y is i Calculating the relative temperature change rate D according to the formula (3) and if D > G2, corresponding A i =1, sending out an alarm prompt; if D is less than or equal to G2, then corresponding A i =0, and no alarm prompt is issued. When Y is i T2 is not more than, corresponding to A i =0, no alarm prompt is issued, operation c is performed, and let i=i+1, calculation is continued until i=n.
In this embodiment, the conventional alarm method only considers the temperature threshold, and alarms when the real-time temperature exceeds the temperature threshold. However, calculation of the temperature differential before the real-time temperature does not exceed the temperature threshold is not considered, the temperature differential can be used for numerical solution of the predicted temperature value according to the historical value, and early warning is performed when the temperature differential value exceeds the threshold (for example, the first temperature differential threshold G1 and the second temperature differential threshold G2), so that timeliness and safety of early warning are improved.
D＝(Y i -Y i-1 )/T (3)
In the formula (3), Y i Representing the relative temperature of the subway bearing of the ith section, Y i-1 And (5) representing the relative temperature of the subway bearing of the i-1 th section, and T representing the preset running time of the subway bearing.
c. Subway bearing prediction temperature K using prediction algorithm i When K is i At > T3, corresponding A i =1, send out alarm prompt, when K i T3 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
The second early warning mode is as follows:
d. when Y is i > T2, then corresponding A i =1, send out alarm prompt, Y i Representing the relative temperature of the subway bearing of the ith section, A i An alarm array for representing the ith section of subway bearing; if Y i T2 is not more than, corresponding to A i =0, no alarm prompt is issued, operation e is performed, and let i=i+1, calculation is continued until i=n.
e. When Y is i Calculating the relative temperature change rate D according to the formula (4) and if D > G1, corresponding A i =1, sending out an alarm prompt; if D is less than or equal to G1, then corresponding A i =0, and no alarm prompt is issued. When Y is i T1 is not more than, corresponding to A i =0, no alarm prompt is issued, operation f is performed, and let i=i+1, calculation is continued until i=n.
D＝(Y i -Y i-1 )/T (4)
In the formula (4), Y i Representing the relative temperature of the subway bearing of the ith section, Y i-1 And (5) representing the relative temperature of the subway bearing of the i-1 th section, and T representing the preset running time of the subway bearing.
f. Subway bearing prediction temperature K using prediction algorithm i When K is i At > T3, corresponding A i =1, send out alarm prompt, when K i T3 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
S5: detecting the running time T of the subway bearing, and executing a third early warning mode when T is larger than the preset running time T; when T is less than or equal to T, the temperature detection device is in a dormant state.
The third early warning mode is:
g. when Y is i > T1, then corresponding A i =1, send out alarm prompt, Y i Representing the relative temperature of the subway bearing of the ith section, A i An alarm array for representing the ith section of subway bearing; if Y i T1 is not more than, corresponding to A i =0, no alarm prompt is issued, operation h is performed, and let i=i+1, calculation is continued until i=n.
h. When Y is i Calculating the relative temperature change rate D through a formula (5) according to the temperature change rate T1; if D > G1, then corresponding A i =1, sending out an alarm prompt; if D is less than or equal to G1, then corresponding A i =0, does not send out alarm prompt, and simultaneously judges Y i Whether or not m > 2D is true, if Y i -m > 2D, then corresponding A i =1, sending out an alarm prompt; if Y i -m.ltoreq.2D, then corresponding A i =0, no alarm prompt is issued, operation j is performed, and let i=i+1, calculation is continued until i=n.
D＝(Y i -Y i-1 )/T (5)
In the formula (5), Y i Representing the relative temperature of the subway bearing of the ith section, Y i-1 And (5) representing the relative temperature of the subway bearing of the i-1 th section, and T representing the preset running time of the subway bearing.
j. Subway bearing prediction temperature K using prediction algorithm i
When K is i At > T1, corresponding A i =1, send out alarm prompt, when K i T1 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
According to the method, different prediction algorithms are adopted to respectively predict the temperatures according to the lengths of the historical temperature data of the subway bearing, namely, when the lengths of the historical temperature data of the subway bearing are not smaller than Yu Dingchang N (which can be understood as the number threshold value of the historical temperature data of the subway bearing), a prediction method based on wavelet transformation and autoregressive processes is adopted, and when the lengths of the historical temperature data of the subway bearing are smaller than a fixed length N, a temperature prediction method based on differentiation is adopted.
And carrying out two-layer wavelet decomposition on the fixed-length historical temperature data based on a prediction method of wavelet transformation and autoregressive processes to obtain wavelet coefficients D1, D2 and C2. And respectively establishing an AR (p) model for the wavelet coefficients D1, D2 and C2, solving respective parameters, and respectively predicting to obtain predicted wavelet coefficients ND1, ND2 and NC2. Using the predicted wavelet coefficients ND1, ND2, NC2, performing wavelet reconstruction to obtain a predicted temperature value K i 。
Temperature prediction method based on differentiation, and linear prediction is performed by using current differentiation to obtain predicted temperature K i 。
Predicting absolute temperature K of subway bearing using prediction algorithm i The specific method of (2) is as follows:
A1. selecting all historical temperature data sets XH (XH 1 ,XH 2 ,...,XH L ),XH L The L-th historical temperature data is represented, namely the length of the collection XH is L, A2 is entered when L is less than or equal to N, A3 is entered when L is more than N, and N represents the length threshold value, namely the number of the historical temperature data.
A2. Calculating predicted temperature K of subway bearing i The formula of (2) is as follows:
K i ＝2XH L -XH L-1 ，XH L represents the L-th historical temperature data XH L-1 Represents the L-1 th historical temperature data;
A3. taking N data from the historical temperature data set XH before the time point to be tested results in a set XR (XH L ,XH L-1 ,...,XH L-N+1 ) Selecting db2 wavelet, performing two-layer wavelet decomposition on the set XR according to the wavelet analysis method of the following formula to obtain wavelet coefficients D1, D2 and C2, and entering A4;
wherein a is a scale factor, b is a time shift factor,
representing the conjugate function of ψ (t) < f (t) & ψ a,b (t) > represents the inner product.
A4. Respectively establishing an AR (P) model for wavelet coefficients D1, D2 and C2; predicting 2 values by using an AR (P) model of D1 to obtain predicted wavelet coefficients ND1 and ND2; predicting 1 value by using an AR (P) model of D2 to obtain a predicted wavelet coefficient ND3; 1 value is predicted using the AR (P) model of C2, resulting in predicted wavelet coefficient NC1.
The AR model is obtained by performing prediction algorithm on time sequence through the existing wavelet coefficient data, and mainly solving by using the form of Yule-Walker equation of autocorrelation method, wherein the AR coefficient (such as ND 1) and autocorrelation function phi xx The equation (m) can be expressed by the Yule-Walker equation:
wherein E [ x (n) w (n+m)]＝D 1 2
A5. Carrying out wavelet reconstruction according to the existing db8 wavelet analysis method by using the predicted wavelet coefficients ND1, ND2 and NC2 to obtain a predicted temperature data set NXR= { ND1, ND2, ND3 and NC1};
a6, calculating a predicted temperature
Wherein Mean calculates the Mean function, i.e. taking the Mean of the four data after NXR as the predicted temperature data.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples of carrying out the invention and that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (5)
1. The subway bearing temperature early warning method is characterized by comprising the following steps of:
s1: each temperature detection device is fixed on the subway bearing in an average sectional manner through bolts, and the ground is collectedThe temperature of the iron bearing is obtained as set X (X 1 ,X 2 ,...,X i ...,X n ),X i Representing the temperature of the subway bearing of the ith section, X n The temperature of the nth section of subway bearing is represented;
s2: the temperature of the subway bearing is processed to obtain a relative temperature set Y of the subway bearing: relative temperature of the metro bearing = temperature of the metro bearing-ambient temperature;
s3: calculating the mean value m and standard deviation S of the relative temperature set Y of the subway bearings at the same time point d Skewness f and kurtosis q;
s4: if F is greater than the temperature skewness threshold F or Q is greater than the kurtosis threshold Q, executing a first early warning mode; if F is less than or equal to F and Q is less than or equal to Q, executing a second early warning mode;
the first early warning mode is as follows:
a. when Y is i More than T3, corresponding alarm array A i =1, send out alarm prompt, Y i Representing the relative temperature of the subway bearing of the ith section, A i An alarm array of the ith section of subway bearing is represented, and T3 represents a preset third relative temperature threshold; if Y i T3 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation b;
b. when Y is i Calculating a relative temperature change rate D according to a formula (3), wherein T2 represents a preset second relative temperature threshold; if D > G2, then corresponding A i =1, sending an alarm prompt, G2 representing a preset second temperature differential threshold; if D is less than or equal to G2, then corresponding A i =0, no alarm prompt is sent; when Y is i T2 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation c;
D＝(Y i -Y i-1 )/T (3)
in the formula (3), Y i Representing the relative temperature of the subway bearing of the ith section, Y i-1 The relative temperature of the i-1 th section of subway bearing is represented, and T represents the preset running time of the subway bearing;
c. predicting subway bearing predicted temperature K i When K is i At > T3, corresponding A i =1, send out alarm prompt, when K i T3 or lessCorresponding A i =0, not sending out alarm prompt, and letting i=i+1, continuing to calculate until i=n;
s5: detecting the running time T of the subway bearing, and executing a third early warning mode when T is larger than the preset running time T; when T is less than or equal to T, the temperature detection device is in a dormant state.
2. The subway bearing temperature early warning method according to claim 1, wherein in the step S3, the mean value m and the standard deviation S d The calculation formula of (2) is as follows:
in the formula (1), m represents the average value of relative temperature sets Y of the metro bearings, n represents the number of metro bearing segments and Y i Representing the relative temperature of the subway bearing of the ith section, S d The standard deviation of the subway bearing relative temperature set Y is represented;
the calculation formulas of the skewness f and the kurtosis q are as follows:
in the formula (2), f represents the skewness of the metro bearing relative to the temperature set Y, and q represents the kurtosis of the metro bearing relative to the temperature set Y.
3. The subway bearing temperature early warning method according to claim 1, wherein in the step S4, the second early warning mode is as follows:
d. when Y is i More than T2, corresponding alarm array A i =1, sending out an alarm prompt; if Y i T2 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation e;
e. when Y is i Calculating a relative temperature change rate D according to a formula (3), wherein T1 represents a preset first relative temperature threshold; if D > G1, then corresponding A i =1, send out reportAlert, G1 represents a preset first temperature differential threshold; if D is less than or equal to G1, then corresponding A i =0, no alarm prompt is sent; when Y is i T1 is not more than, corresponding to A i =0, not sending an alarm prompt, executing operation f;
f. predicting subway bearing predicted temperature K i When K is i At > T3, corresponding A i =1, send out alarm prompt, when K i T3 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
4. The subway bearing temperature early warning method according to claim 1, wherein in the step S5, the third early warning mode is as follows:
g. when Y is i > T1, then corresponding A i =1, sending out an alarm prompt; if Y i T1 is not more than, corresponding to A i =0, not sending out an alarm prompt, executing operation h;
h. when Y is i Calculating the relative temperature change rate D through a formula (3) according to the temperature change rate T1; if D > G1, then corresponding A i =1, sending out an alarm prompt; if D is less than or equal to G1, then corresponding A i =0, does not send out alarm prompt, and simultaneously judges Y i Whether or not m > 2D is true, if Y i -m > 2D, then corresponding A i =1, sending out an alarm prompt; if Y i -m.ltoreq.2D, then corresponding A i =0, no alarm prompt is sent out, and operation j is executed;
j. predicting subway bearing predicted temperature K i When K is i At > T1, corresponding A i =1, send out alarm prompt, when K i T1 is not more than, corresponding to A i =0, no alarm prompt is issued, and let i=i+1, continue calculation until i=n.
5. The subway bearing temperature early warning method according to claim 1, wherein the subway bearing predicted temperature K i The calculation method of (1) is as follows:
A1. selecting all historical temperature data sets X of any section of subway bearing before a time point to be testedH(XH 1 ,XH 2 ,...,XH L ),XH L Representing the L-th historical temperature data, i.e., the length of the collection XH is L;
A2. calculating predicted temperature K of subway bearing i The formula of (2) is as follows:
K i ＝2XH L -XH L-1 ，XH L represents the L-th historical temperature data XH L-1 Represents the L-1 th historical temperature data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011486948.4A CN112697308B (en) | 2020-12-16 | 2020-12-16 | Subway bearing temperature early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011486948.4A CN112697308B (en) | 2020-12-16 | 2020-12-16 | Subway bearing temperature early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112697308A CN112697308A (en) | 2021-04-23 |
| CN112697308B true CN112697308B (en) | 2023-05-30 |
Family
ID=75508389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011486948.4A Active CN112697308B (en) | 2020-12-16 | 2020-12-16 | Subway bearing temperature early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112697308B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930819B (en) * | 2023-09-18 | 2023-12-08 | 云南电网有限责任公司 | Current terminal strip temperature on-line monitoring method and system based on thermal imaging |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268416A (en) * | 2014-09-30 | 2015-01-07 | 北京农业信息技术研究中心 | Temperature monitoring method and temperature monitoring system for cold-chain logistics car |
| CN110187679A (en) * | 2019-04-29 | 2019-08-30 | 新奥数能科技有限公司 | A kind of alarm method and device of SCADA system |
| CN111539553A (en) * | 2020-03-31 | 2020-08-14 | 华北电力大学 | Wind turbine generator fault early warning method based on SVR algorithm and skewness |
| CN111829693A (en) * | 2020-07-30 | 2020-10-27 | 成都运达科技股份有限公司 | Bearing temperature detection method and system based on LSTM model of time and space dimensions |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7160593B2 (en) * | 2018-08-08 | 2022-10-25 | 東海旅客鉄道株式会社 | Temperature anomaly detection system and temperature anomaly detection method |
-
2020
- 2020-12-16 CN CN202011486948.4A patent/CN112697308B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268416A (en) * | 2014-09-30 | 2015-01-07 | 北京农业信息技术研究中心 | Temperature monitoring method and temperature monitoring system for cold-chain logistics car |
| CN110187679A (en) * | 2019-04-29 | 2019-08-30 | 新奥数能科技有限公司 | A kind of alarm method and device of SCADA system |
| CN111539553A (en) * | 2020-03-31 | 2020-08-14 | 华北电力大学 | Wind turbine generator fault early warning method based on SVR algorithm and skewness |
| CN111829693A (en) * | 2020-07-30 | 2020-10-27 | 成都运达科技股份有限公司 | Bearing temperature detection method and system based on LSTM model of time and space dimensions |
Non-Patent Citations (2)
| Title |
|---|
| 基于NSET的风力发电机后轴承温度预警方法;李大中等;《科学技术与工程》;20160908;第16卷(第24期);第205-209页 * |
| 基于温度参数的风电机组异常识别;邢月等;《可再生能源》;20190516;第37卷(第05期);摘要 2 风电机组异常识别模型 3 实例分析 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112697308A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| CN111351664B (en) | Bearing temperature prediction and alarm diagnosis method based on LSTM model | |
| US8566070B2 (en) | Apparatus abnormality monitoring method and system | |
| CN108069308A (en) | A kind of electric staircase failure diagnosis method based on sequential probability | |
| BR112021013786A2 (en) | METHOD AND SYSTEM TO DETECT ANOMALIES OR PREMATURE INDICATIONS OF EQUIPMENT FAILURE | |
| CN112697308B (en) | Subway bearing temperature early warning method | |
| CN108257365B (en) | Industrial alarm design method based on global uncertainty evidence dynamic fusion | |
| CN111122191B (en) | Equipment health alarm threshold setting method based on EWMA control | |
| CN116105802B (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
| CN112861350B (en) | Temperature overheating defect early warning method for stator winding of water-cooled steam turbine generator | |
| JP4431163B2 (en) | Abnormality detection system for moving body and abnormality detection method for moving body | |
| CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
| CN115577860B (en) | Intelligent maintenance method and system for rail transit based on adaptive control | |
| CN111457958A (en) | Port machine equipment situation monitoring method and device, computer equipment and storage medium | |
| CN115358647A (en) | Hydrogen energy industry chain risk monitoring system and monitoring method based on big data | |
| CN106021759B (en) | Transformer fault recognition methods and system | |
| CN112288126B (en) | Sampling data abnormal change online monitoring and diagnosing method | |
| CN117262944A (en) | Elevator remote monitoring fault alarm system based on internet | |
| CN117171621A (en) | Gate health assessment method and device based on single chip microcomputer and storage medium | |
| Sarda et al. | A comparison of envelope and statistical analyses for bearing diagnosis in hot steel rolling mill lines | |
| CN112811275A (en) | Elevator maintenance-on-demand period measuring and calculating system and method based on Internet of things | |
| CN116767089B (en) | Method and device for identifying abnormal water temperature of automobile and monitoring alarm | |
| CN114997759B (en) | Heat supply pipeline support and hanger stability early warning method and system | |
| Elango et al. | Machine learning techniques for fault detection of induction motor bearings | |
| CN112660199A (en) | Data storage and pre-alarming method for monitoring rail transit traction motor bearing state |
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 |