CN109186813B - Temperature sensor self-checking device and method - Google Patents

Temperature sensor self-checking device and method Download PDF

Info

Publication number
CN109186813B
CN109186813B CN201811236829.6A CN201811236829A CN109186813B CN 109186813 B CN109186813 B CN 109186813B CN 201811236829 A CN201811236829 A CN 201811236829A CN 109186813 B CN109186813 B CN 109186813B
Authority
CN
China
Prior art keywords
sequence
temperature difference
temperature
standard deviation
value
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
Application number
CN201811236829.6A
Other languages
Chinese (zh)
Other versions
CN109186813A (en
Inventor
刘邦繁
张慧源
李晨
孙木兰
褚金鹏
刘昕武
刘雨聪
熊敏君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhuzhou CRRC Times Electric Co Ltd
Original Assignee
Zhuzhou CRRC Times Electric Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhuzhou CRRC Times Electric Co Ltd filed Critical Zhuzhou CRRC Times Electric Co Ltd
Priority to CN201811236829.6A priority Critical patent/CN109186813B/en
Publication of CN109186813A publication Critical patent/CN109186813A/en
Application granted granted Critical
Publication of CN109186813B publication Critical patent/CN109186813B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K15/00—Testing or calibrating of thermometers
    • G01K15/007—Testing

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

The invention provides a temperature sensor self-checking device and a method, wherein a temperature data sequence of a train under a normal condition is subjected to differential processing to obtain a segmented standard deviation sequence, and an abnormal detection threshold value is obtained by performing statistical analysis on the standard deviation sequence; carrying out differential processing on the real-time input temperature data sequence to obtain a segmented standard deviation sequence; judging whether the segmented temperature difference value sequence is abnormal or not based on the threshold value and the standard difference sequence; if the standard deviation sequence of a certain segment of the segmentation is larger than or equal to the threshold value, judging that the temperature difference sequence of the segment is abnormal, and entering the next step, otherwise, judging that the sensor is normal; judging the distribution consistency of the temperature difference sequence with the abnormality in a certain section, the normal reference sequence and the temperature difference sequence in the previous adjacent time section; if the consistency exists, the sensor is judged to be normal, and if not, the sensor is abnormal. The invention can solve the technical problems that the prior art can not carry out quick and effective self-checking on the temperature sensor and can not ensure the safe and efficient operation of the train.

Description

Temperature sensor self-checking device and method
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a self-checking device and a self-checking method applied to a train temperature sensor.
Background
The temperature sensor is one of important components of each system of a train transmission, control, a running part and the like, is a core device for ensuring the safety and normal operation of equipment and is one of key indexes of the monitoring of the whole train, and is responsible for the monitoring and sensing functions of key components related to the temperature of the whole train. Generally, in most cases, those skilled in the art are concerned with the behavior of the object being monitored by the sensor, and are less concerned with the concern of the intrinsic connection between the monitor and the temperature sensor (system) itself. In fact, also as a device, the temperature sensor must have the possibility of malfunctioning. When an abnormality occurs in the temperature value measured by the sensor, it is generally not completely certain whether the abnormality is that the measured object is actually in trouble or that the sensor or the communication system is abnormal. If the real measurement object is abnormal, emergency train safety countermeasures such as power reduction or stopping for overhaul need to be taken. However, if the sensor (system) is abnormal, taking emergency countermeasures will increase the operation and maintenance cost greatly, and even may cause safety problems in some cases. Therefore, in practical applications, it is necessary to solve a problem of how to ensure the normality of the operation of the temperature sensor itself, or in other words, how to determine whether the abnormal temperature value occurred is caused by the abnormality of the sensor itself.
Based on the above problems, the key technology to be solved at present is to find out whether the temperature sensor itself is normal by using what method, which includes: how to effectively identify an abnormal source by using information and data related to the temperature sensor to realize effective early warning, and how to realize abnormal judgment by additionally installing the sensor or depending on the existing data.
At present, there are many researches and applications on checking the operation state of the sensor itself, wherein there are many detection means for detecting whether the temperature sensor is abnormal or not, there are some methods for judging the operation state of the sensor by detecting the voltage and current conditions of the sensor, some methods for judging the operation state of the sensor by setting a temperature threshold value in combination with professional knowledge, and some methods for judging the operation state of the sensor by adding a sensor at a similar position and comparing the changes of two or more temperature values. However, these conventional temperature sensor detection methods have various technical defects that the judgment result is inaccurate, the judgment is misjudged, the judgment is missed, or the judgment is performed by professional knowledge, so that the application and field are limited, or an additional device is required, so that the complexity of the system is increased, and the like.
Disclosure of Invention
In view of the above, the present invention provides a temperature sensor self-checking device and method, so as to solve the technical problem that the existing train system cannot perform quick and effective self-checking on a temperature sensor, and further cannot ensure safe and efficient operation of a train.
In order to achieve the above object, the present invention specifically provides a technical implementation scheme of a temperature sensor self-checking device, where the temperature sensor self-checking device includes:
the anomaly detection threshold calculation module is used for carrying out differential processing on a temperature data sequence T measured by a sensor under the normal running condition of the train to obtain a segmentation standard deviation sequence theta of the temperature difference sequence T and carrying out statistical analysis on the standard deviation sequence theta to obtain an anomaly detection threshold K;
the key characteristic value extraction module is used for carrying out differential processing on the temperature data sequence t input in real time and measured by the sensor to obtain a segmented standard deviation sequence η of the temperature difference sequence t;
the first anomaly detection module is used for judging whether the segmented temperature difference sequence t is abnormal or not according to the anomaly detection threshold K output by the anomaly detection threshold calculation module and the standard deviation sequence η output by the key characteristic value extraction module, judging that the segmented temperature difference sequence t is abnormal if the segmented standard deviation sequence η of a certain temperature difference sequence t is greater than or equal to the anomaly detection threshold K, outputting the temperature difference sequence t with the abnormality, and judging that the sensor is normal if the segmented standard deviation sequence is not greater than the anomaly detection threshold K;
the consistency checking module is used for carrying out distribution consistency check on the temperature difference sequence t with the abnormality output by the first abnormality detecting module, a normal reference sequence and a temperature difference sequence t in the previous adjacent time period;
and the second anomaly detection module is used for judging whether the distribution consistency detection occurrence probability P value output by the consistency detection module is smaller than a set standard, outputting an anomaly early warning signal of the sensor if the distribution consistency detection occurrence probability P value is smaller than the set standard, and otherwise, enabling the sensor to be normal.
Further, the abnormal detection threshold calculation module acquires a temperature data sequence T measured by a sensor in the running process of a certain part of the train under normal conditions, and calculates a temperature difference value sequence T according to the unit time delta T. Segmenting the temperature difference value sequence T in unit time according to the same length T1, and calculating the standard deviation theta of each temperature difference value sequence TiAnd formStandard deviation sequence Θ. Analyzing the distribution condition of the standard deviation sequence theta, calculating the mean value mu and the standard deviation sigma of the standard deviation sequence theta according to the occurrence probability
Figure GDA0002508719650000021
Figure GDA0002508719650000022
And constructing an abnormality detection threshold value K corresponding to the part of the train according to the principle of (1).
Wherein, theta is the standard deviation of the temperature difference value sequence T.
Figure GDA0002508719650000023
Figure GDA0002508719650000024
Wherein, ω isiAs weighting coefficients, here
Figure GDA0002508719650000025
xiIs the sample value, n is the number of samples.
Further, the key characteristic value extraction module obtains a temperature data sequence T measured by a real-time input sensor, calculates a temperature difference sequence T according to unit time delta T, segments the temperature difference sequence T in unit time according to the same length T2, calculates the standard deviation of each segment of the temperature difference sequence T, and forms a standard deviation sequence η.
Further, the consistency check module compares the abnormal detection threshold K with the standard deviation sequence η to find that the temperature difference sequence t in a certain section of the train running process has suspected abnormal data, and records the temperature difference sequence x in the section of the train running processtAnd obtaining the temperature difference value sequence x of the sectiontAnd the temperature difference sequence y of the previous adjacent time periodtAnd simultaneously acquiring a temperature difference sequence z1 measured by other similar position sensors of the train in the same time periodt,…,zntAnd for the sequence x of temperature differences suspected to be abnormaltRespectively of preceding adjacent time periodSequence of temperature differences ytAnd temperature difference series measured by other similar position sensors { z1t,…,zntCarry out K-S distribution test one by one.
Further, the consistency check module judges the temperature difference value sequence x to be checkedtSequence y of temperature differences from a preceding adjacent time periodtAnd temperature difference series measured by other similar position sensors { z1t,…,zntWhen the distribution is consistent, the temperature difference value sequence x is determined by checking the maximum difference value D of the empirical distribution function among the sequencestThe significance of (a). When the maximum difference value D obtained by actual calculation is greater than a certain set standard value, or the distribution probability P corresponding to the maximum difference value D is less than a certain set standard value, there is no consistency between the two temperature difference value sequences.
Wherein, the temperature difference sequence xtIs n1, sequence of temperature differences yt,z1t,…,zntThe sample size of any difference sequence is n2, F1(x) And F2(x) Respectively representing the accumulated empirical distribution functions of two samples, wherein j is the segmentation identification of the temperature difference value sequence, and x is the sample.
Note Dj＝F1(xj)-F2(xj)，
Figure GDA0002508719650000031
Figure GDA0002508719650000032
Represents DjMaximum value of absolute distance. The test statistic Z is approximated to a normal distribution, expressed as:
Figure GDA0002508719650000033
when the null hypothesis is true, the Z-dependent density distribution d converges to the K-distribution, i.e. when the samples are taken from the one-dimensional continuous distribution F,
Figure GDA0002508719650000034
Figure GDA0002508719650000035
the maximum value of the absolute distance of B (F (x)) is taken, and x is the sample.
The empirical distribution function B (t) is:
Figure GDA0002508719650000036
wherein x is an independent variable, and i is a natural number.
The invention also provides a technical implementation scheme of the temperature sensor self-checking method, and the temperature sensor self-checking method comprises the following steps:
s10) carrying out differential processing on a temperature data sequence T measured by a sensor under the normal running condition of the train to obtain a segmentation standard deviation sequence theta of the temperature difference sequence T, and carrying out statistical analysis on the standard deviation sequence theta to obtain an anomaly detection threshold value K;
s20) carrying out the same difference processing as the step S10) on the temperature data sequence t input in real time and measured by the sensor to obtain a segmented standard deviation sequence η of the temperature difference sequence t;
s30) judging whether the segmented temperature difference sequence t is abnormal or not based on the abnormal detection threshold K obtained in the step S10) and the standard deviation sequence η obtained in the step S20), if the segmented standard deviation sequence η of a certain temperature difference sequence t is more than or equal to the abnormal detection threshold K, judging that the temperature difference sequence t is abnormal, and entering the step S40), otherwise, judging that the sensor is normal;
s40) judging the distribution consistency of the temperature difference sequence t with the abnormality in the step S30) with the normal reference sequence and the temperature difference sequence t of the previous adjacent time period; if the consistency exists, the sensor is judged to be normal, and if the consistency does not exist, the sensor is judged to be abnormal.
Further, the step S10) further includes:
s11) selecting a temperature data sequence T measured by a sensor in the running process of a certain part of the train under normal conditions, and calculating a temperature difference sequence T according to the delta T in unit time;
s12) segmenting the temperature difference sequence T in unit time according to the same length T1, and calculating the standard deviation theta of each temperature difference sequence TiAnd forming a standard deviation sequence theta;
s13), analyzing the distribution condition of the standard deviation sequence theta, and calculating the mean value mu and the standard deviation sigma of the standard deviation sequence theta according to the occurrence probability
Figure GDA0002508719650000041
Constructing an abnormal detection threshold value K corresponding to the part of the train according to the principle of (1);
wherein, theta is the standard deviation of the temperature difference value sequence T.
Figure GDA0002508719650000042
Figure GDA0002508719650000043
Wherein, ω isiAs weighting coefficients, here
Figure GDA0002508719650000044
xiIs the sample value, n is the number of samples.
Further, the step S20) further includes:
s21) inputting the temperature data sequence t measured by the sensor in real time;
s22) calculating a temperature difference sequence t according to the unit time delta t;
s23) segmenting the temperature difference value sequences T in unit time according to the same length T2, calculating the standard deviation of each temperature difference value sequence T, and forming standard deviation sequences η.
Further, the step S40) further includes:
s41) comparing the abnormal detection threshold K with the standard deviation sequence η to find the data of suspected abnormality of a temperature difference sequence t in a certain section in the running process of the train, and recording the temperature difference sequence x in the sectiontAnd obtaining the information ofSequence of segment temperature differences xtAnd the temperature difference sequence y of the previous adjacent time periodt；
S42) obtaining a temperature difference value sequence z1 measured by other similar position sensors of the train in the same time periodt,…,znt；
S43) the sequence of temperature differences x for suspected abnormalitytSequence y of temperature differences respectively from a preceding adjacent time segmenttAnd temperature difference series measured by other similar position sensors { z1t,…,zntPerforming K-S distribution test one by one;
s44), when the occurrence probability P values of all the tests are smaller than the set standard, outputting an abnormal early warning signal of the sensor, otherwise, the sensor is normal.
Further, the step S43) further includes:
setting a sequence x of temperature differencestIs n1, sequence of temperature differences yt,z1t,…,zntThe sample size of any difference sequence is n2, F1(x) And F2(x) Respectively representing the accumulated empirical distribution functions of two samples, wherein j is the segmentation identification of the temperature difference value sequence, and x is the sample.
Note Dj＝F1(xj)-F2(xj)，
Figure GDA0002508719650000051
Figure GDA0002508719650000052
Represents DjMaximum value of absolute distance. The test statistic Z is approximated to a normal distribution, expressed as:
Figure GDA0002508719650000053
when the null hypothesis is true, the Z-dependent density distribution d converges to the K-distribution, i.e. when the samples are taken from the one-dimensional continuous distribution F,
Figure GDA0002508719650000054
Figure GDA0002508719650000055
the maximum value of the absolute distance of B (F (x)) is taken, and x is the sample.
The empirical distribution function B (t) is:
Figure GDA0002508719650000056
wherein x is an independent variable, and i is a natural number;
in judging the temperature difference value sequence x to be detectedtSequence y of temperature differences from a preceding adjacent time periodtAnd temperature difference series measured by other similar position sensors { z1t,…,zntWhen the distribution is consistent, the temperature difference value sequence x is determined by checking the maximum difference value D of the empirical distribution function among the sequencestThe significance of (a). When the maximum difference value D obtained by actual calculation is greater than a certain set standard value, or the distribution probability P corresponding to the maximum difference value D is less than a certain set standard value, there is no consistency between the two temperature difference value sequences.
By implementing the technical scheme of the temperature sensor self-checking device and the method provided by the invention, the following beneficial effects are achieved:
(1) compared with the technical scheme in the prior art based on other variables such as current, voltage and the like or comparing measurement results of a plurality of devices, the method can more effectively and directly find possible abnormity, and the monitoring and early warning results are more real and accurate;
(2) the invention not only utilizes the threshold index to carry out self-checking early warning, but also further detects and discovers abnormity from the angle of contrast distribution change, and compared with the prior art which only uses one or two indication indexes to analyze sensor faults, the rules and results of self-checking and early warning are more accurate and effective;
(3) the method is based on the analysis and application of a large amount of normal and abnormal data in the actual operation process, and compared with the problems of less data amount and the like in the prior art, the method has the advantages that the model result is more reliable, the considered factors are more sufficient and reasonable, and the verifiability and the practicability are stronger;
(4) the invention carries out real-time self-detection and early warning based on a large amount of temperature data measured in the running process of the train, automatically adjusts the threshold value and the distribution inspection segmentation mode based on continuously updated data, and has obvious high efficiency and intelligent level.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, from which other embodiments can be derived by a person skilled in the art without inventive effort.
FIG. 1 is a block diagram of a system configuration of an embodiment of a temperature sensor self-test apparatus of the present invention;
FIG. 2 is a schematic diagram illustrating the operational flow of a method for self-testing a temperature sensor according to an embodiment of the present invention;
FIG. 3 is a flowchart of a process for self-testing a temperature sensor according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of a K-S test in one embodiment of a method for self-testing a temperature sensor of the present invention;
in the figure: 1-an anomaly detection threshold calculation module, 2-a key characteristic value extraction module, 3-a first anomaly detection module, 4-a consistency inspection module and 5-a second anomaly detection module.
Detailed Description
For reference and clarity, the terms, abbreviations or abbreviations used hereinafter are as follows:
non-parameter testing: the present invention relates to a method for estimating a population distribution form or the like using sample data when a population variance is unknown or known to a small extent. The nonparametric test method is called a "nonparametric" test because it does not involve parameters related to the overall distribution in the inference process.
And (4) K-S test: the kolmogorov-smirnov test is based on a cumulative distribution function to test whether two empirical distributions are different or whether one empirical distribution is different from the other ideal distribution. The method is different from other methods such as t test, namely K-S test does not need to know the distribution condition of data and can be calculated as a non-parameter test method. The K-S test is a common method of analyzing two sets of data for differences in presence or absence as a non-parametric test when the sample size is small.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 4, embodiments of a self-testing device and a method for a temperature sensor according to the present invention are shown, and the present invention will be further described with reference to the drawings and the embodiments.
Example 1
Through analysis and research of a large amount of data, the temperature change of each relevant part on the train is generally a relatively slow process. That is, the possibility that the temperature change fluctuates greatly in a short time is small, and particularly, the temperature drop greatly in a very short time hardly occurs. Therefore, in consideration of this point, if it is found that a rapid fluctuation of the temperature change value occurs in a short period of time and there is a significant difference in the distribution of the change values in the similar period of time, it is considered that an abnormality is likely to occur in the corresponding temperature sensor (system). Therefore, the embodiment of the invention measures the fluctuation level through the standard deviation of the temperature difference value in unit time, and realizes the detection and comparison of the temperature difference distribution in the similar time period by combining the K-S distribution detection method, thereby comprehensively judging whether the temperature sensor is abnormal or not. The temperature sensor self-checking device described in the embodiment comprises two major functions, namely, the first part is used for determining (modeling) a temperature difference abnormity detection threshold value, and the second part is used for realizing self-checking of temperature sensor abnormity by combining the threshold value and K-S inspection.
In the aspect of determining the temperature difference anomaly detection threshold, differential processing is firstly carried out on time sequence data of various temperatures under the normal condition of a train system, then volatility (standard deviation) is calculated in a segmented mode according to the principle by using the processed temperature difference data to form a corresponding standard deviation sequence, corresponding distribution conditions are estimated by using the formed standard deviation sequence as a reference, the mean value and the standard deviation of the fluctuation sequence are calculated, and finally the anomaly detection threshold mu +3 sigma (namely the anomaly detection threshold K) is obtained by combining with a statistical distribution principle.
In the aspect of realizing the abnormal self-check of the temperature sensor by combining an abnormal detection threshold and K-S inspection, for temperature detection data input in real time, firstly, calculating a difference and a corresponding fluctuation sequence according to the same rule as a temperature difference abnormal detection threshold determining stage, then, judging the abnormal possibility of a segmented fluctuation sequence based on the obtained abnormal detection threshold, if the abnormal detection threshold is larger than or equal to the abnormal detection threshold, judging that the temperature value of the segment is suspected to be abnormal, further, deeply judging the distribution difference of the temperature difference sequence, a basic temperature difference sequence and a previous sequence, and if obvious difference exists, indicating that the sensor (system) is abnormal; otherwise, the exception is considered to be temporarily absent.
The following is a detailed description of a specific implementation of the temperature sensor self-testing device based on the above-mentioned operating principle.
As shown in fig. 1, an embodiment of a temperature sensor self-testing device specifically includes:
the abnormal detection threshold calculation module 1 is used for carrying out differential processing on a temperature data sequence T (such as oil temperature, shaft temperature, water temperature and the like) measured by a sensor under the normal running condition of a train to obtain a segmented standard deviation sequence theta of a temperature difference sequence T, and carrying out statistical analysis on the standard deviation sequence theta to obtain an abnormal detection threshold K;
the key characteristic value extraction module 2 is used for carrying out differential processing on the temperature data sequence t input in real time and measured by the sensor to obtain a segmented standard deviation sequence η of the temperature difference sequence t;
the first anomaly detection module 3 is used for judging whether the segmented temperature difference sequence t is abnormal or not according to the anomaly detection threshold K output by the anomaly detection threshold calculation module 1 and the standard deviation sequence η output by the key characteristic value extraction module 2, judging that the segmented temperature difference sequence t is abnormal if the segmented standard deviation sequence η of a certain temperature difference sequence t is greater than or equal to the anomaly detection threshold K, outputting the temperature difference sequence t with the abnormality, and judging that the sensor is normal if the segmented standard deviation sequence η of the certain temperature difference sequence t is not less than the anomaly detection threshold K;
the consistency checking module 4 is used for carrying out distribution consistency checking on the temperature difference sequence t with the abnormality output by the first abnormality detecting module 3, the normal reference sequence and the temperature difference sequence t in the previous adjacent time period;
and the second anomaly detection module 5 is used for judging whether the distribution consistency detection occurrence probability P value output by the consistency detection module 4 is smaller than a set standard, outputting a sensor anomaly early warning signal if the distribution consistency detection occurrence probability P value is smaller than the set standard, and otherwise, outputting a sensor anomaly early warning signal if the distribution consistency detection occurrence probability P value is not smaller than the set standard.
The abnormal detection threshold calculation module 1 acquires a temperature data sequence T measured by a sensor in the running process of a certain part of the train under normal conditions, and calculates a temperature difference sequence T according to unit time delta T. Segmenting the temperature difference value sequence T in unit time according to the same length T1, and calculating the standard deviation theta of each temperature difference value sequence TiAnd form the standard deviation sequence theta. Analyzing the distribution of the standard deviation sequence theta, calculating the mean value mu and the standard deviation sigma of the standard deviation sequence theta, and according to the occurrence probability (namely the distribution consistency test occurrence probability)
Figure GDA0002508719650000081
And constructing an abnormality detection threshold value K corresponding to the part of the train according to the principle of (1).
Wherein, theta is the standard deviation of the temperature difference value sequence T.
Figure GDA0002508719650000082
Figure GDA0002508719650000083
Wherein, ω isiAs weighting coefficients, here
Figure GDA0002508719650000084
xiIs the sample value, n is the number of samples.
The key characteristic value extraction module 2 obtains a temperature data sequence T measured by a real-time input sensor, calculates a temperature difference sequence T according to unit time delta T, segments the temperature difference sequence T in unit time according to the same length T2, calculates the standard deviation of each segment of the temperature difference sequence T, and forms a standard deviation sequence η.
The consistency check module 4 compares the anomaly detection threshold K with the standard deviation sequence η to find that the temperature difference sequence t in a certain section of the train running process has suspected abnormal data, and records the temperature difference sequence x in the section of the train running processtAnd obtaining the temperature difference value sequence x of the sectiontAnd the temperature difference sequence y of the previous adjacent time periodtAnd simultaneously acquiring a temperature difference sequence z1 measured by other similar position sensors of the train in the same time periodt,…,zntAnd for the sequence x of temperature differences suspected to be abnormaltSequence y of temperature differences respectively from a preceding adjacent time segmenttAnd temperature difference series measured by other similar position sensors { z1t,…,zntCarry out K-S distribution test one by one.
The consistency checking module 4 judges the temperature difference value sequence x to be checkedtSequence y of temperature differences from a preceding adjacent time periodtAnd temperature difference series measured by other similar position sensors { z1t,…,zntWhen the distribution is consistent, the temperature difference value sequence x is determined by checking the maximum difference value D of the empirical distribution function among the sequencestThe significance of (a). When the maximum difference value D obtained by actual calculation is larger than a certain set standard value, or the K-S distribution probability P value (i.e. the distribution consistency test occurrence probability P value) corresponding to the maximum difference value D is smaller thanWhen a certain standard value is set, the two temperature difference value sequences have no consistency.
Wherein, the temperature difference sequence xtIs n1, sequence of temperature differences yt,z1t,…,zntThe sample size of any difference sequence is n2, F1(x) And F2(x) Respectively representing the accumulated empirical distribution functions of two samples, wherein j is the segmentation identification of the temperature difference value sequence, and x is the sample.
Note Dj＝F1(xj)-F2(xj)，
Figure GDA0002508719650000091
Figure GDA0002508719650000092
Represents DjMaximum value of absolute distance. The test statistic Z is approximated to a normal distribution, expressed as:
Figure GDA0002508719650000093
when the null hypothesis is true, the Z-dependent density distribution d converges to the K-distribution, i.e. when the samples are taken from the one-dimensional continuous distribution F,
Figure GDA0002508719650000094
Figure GDA0002508719650000095
the maximum value of the absolute distance of B (F (x)) is taken, and x is the sample.
The empirical distribution function B (t) is:
Figure GDA0002508719650000096
wherein x is an independent variable, and i is a natural number.
Example 2
In this embodiment, since the used data is mainly time-series temperature data measured by the sensor, when performing real-time anomaly self-detection, due to the relative difference between different trains in different environments, lines and states, the determination cannot be directly performed through the temperature value, and therefore, it is necessary to perform data classification and reconstruction on the temperature sequence data, establish a differential sequence, calculate volatility in segments, and then perform anomaly detection. As shown in fig. 2 and fig. 3, an embodiment of a self-checking method for a temperature sensor specifically includes the following steps:
s10) carrying out differential processing on a temperature data sequence T measured by a sensor under the normal running condition of the train to obtain a segmentation standard deviation sequence theta of the temperature difference sequence T, and carrying out statistical analysis on the standard deviation sequence theta to obtain an anomaly detection threshold value K;
s20) carrying out the same difference processing as the step S10) on the temperature data sequence t input in real time and measured by the sensor to obtain a segmented standard deviation sequence η of the temperature difference sequence t;
s30) judging whether the segmented temperature difference sequence t is abnormal or not based on the abnormal detection threshold K obtained in the step S10) and the standard deviation sequence η obtained in the step S20), if the segmented standard deviation sequence η of a certain temperature difference sequence t is more than or equal to the abnormal detection threshold K, judging that the temperature difference sequence t is abnormal, and entering the step S40), otherwise, judging that the sensor is normal;
s40) judging the distribution consistency of the temperature difference sequence t with the abnormality in the step S30) with the normal reference sequence and the temperature difference sequence t of the previous adjacent time period; if the consistency exists, the sensor is judged to be normal, and if the consistency does not exist, the sensor is judged to be abnormal.
Step S10) further includes:
s11) selecting a temperature data sequence T measured by a sensor in the running process of a certain part of the train under normal conditions, and calculating the temperature data sequence T according to the unit time delta T (such as: 1s) calculating a temperature difference sequence T;
s12) segmenting the temperature difference sequence T in unit time according to the same length T1, and calculating the standard deviation theta of each temperature difference sequence TiAnd forming a standard deviation sequence theta;
s13) analysis of the distribution of the sequence Θ of standard deviationCalculating the mean value mu and the standard deviation sigma of the standard deviation sequence theta according to the occurrence probability
Figure GDA0002508719650000101
Constructing an abnormal detection threshold value K corresponding to the part of the train according to the principle of (1);
s14) calculating the abnormal detection threshold value K corresponding to different parts of the same train and different parts of different trains in the same way as the steps S11) to S13) and forming the abnormal self-detection threshold value matrix of the temperature sensor.
Wherein, theta is the standard deviation of the temperature difference value sequence T.
Figure GDA0002508719650000102
Figure GDA0002508719650000103
Wherein, ω isiAs weighting coefficients, here
Figure GDA0002508719650000104
xiIs the sample value, n is the number of samples.
The mean-mu is generally used herein to mean the arithmetic mean of the samples, representing the number of trends in a set of data, and is the sum of all data in a set of data divided by the number of the set of data, which is an indicator of the trends in the data set.
The standard deviation- σ is the square root of the squared sum of the mean deviations, i.e., the arithmetic square root of the variance. The standard deviation can reflect the degree of dispersion, or can also be referred to as the degree of fluctuation, of a data set. The mean is the same and the standard deviation is not necessarily the same. The standard deviation can be considered as a measure of uncertainty. For example: in the actual science of measurement, when repeated measurements are made, the standard deviation of the measured value set represents the accuracy of the measurements. When it is to be determined whether the measured values meet the predicted values, the standard deviation of the measured values plays a decisive role: if the measured average value is too far from the predicted value (and compared with the standard deviation value), the measured value and the predicted value are considered to be contradictory. Since if the measured values all fall outside a certain range of values, it is reasonable to deduce whether the predicted values are correct.
Step S20) further includes:
s21) inputting the temperature data sequence t measured by the sensor in real time;
s22) calculating a temperature difference sequence t according to the unit time delta t;
s23) segmenting the temperature difference value sequences T in unit time according to the same length T2, calculating the standard deviation of each temperature difference value sequence T, and forming standard deviation sequences η.
Since the sensor (system) abnormality is judged based on the distribution threshold of the temperature difference segmentation sequence fluctuation through the foregoing steps, there are some problems that the abnormality may be falsely reported, such as: occasionally, the jump caused by the signal problem at a certain time point does not belong to the sensor or system abnormality, but the jump is possibly judged to be the sensor (system) abnormality through the threshold judgment, so that false alarm occurs. Therefore, the judgment principle needs to be strengthened by combining the characteristics of the overall temperature difference distribution on the basis of threshold value judgment.
The reason why the accuracy of the abnormal self-checking is improved by the distribution checking is that, in general, factors influencing temperature changes at the same position of the same train cannot be changed greatly and fundamentally in a short time, so that temperature difference distribution in adjacent short times belongs to the same overall distribution and no significant distribution difference occurs unless a sensor or a system for measuring the temperature has a problem. In addition, under the condition that the parameter distribution to which the temperature difference change of different trains and different parts belongs cannot be determined, the consistency of the distribution is checked through non-parameters to better accord with the characteristic of the change of the actual data, so that the K-S two-sample distribution checking method becomes a very suitable choice in the technical scheme described in the embodiment.
For two samples from two different populations respectively, to check whether the distributions of the populations behind them are consistent, the K-S test of the two samples can be performed, the principle of which is the same as that of the K-S test of a single sample, and only the distribution of the zero hypothesis in the test statistic needs to be changed into the empirical distribution of another sample, and the specific steps are as follows.
Step S40) further includes:
s41) comparing the abnormal detection threshold K with the standard deviation sequence η to find the data of suspected abnormality of a temperature difference sequence t in a certain section in the running process of the train, and recording the temperature difference sequence x in the sectiontAnd obtaining the temperature difference value sequence x of the sectiontAnd the temperature difference sequence y of the previous adjacent time periodt；
S42) obtaining a temperature difference value sequence z1 measured by other similar position sensors of the train in the same time periodt,…,znt；
S43) the sequence of temperature differences x for suspected abnormalitytSequence y of temperature differences respectively from a preceding adjacent time segmenttAnd temperature difference series measured by other similar position sensors { z1t,…,zntPerforming K-S distribution test one by one;
s44), when the occurrence probability P values of all the tests are smaller than the set standard, outputting an abnormal early warning signal of the sensor, otherwise, outputting no abnormal early warning signal of the sensor if the sensor is normal.
Step S43) further includes:
setting a sequence x of temperature differencestIs n1, sequence of temperature differences yt,z1t,…,zntThe sample size of any difference sequence is n2, F1(x) And F2(x) Respectively representing the accumulated empirical distribution functions of two samples, wherein j is the segmentation identification of the temperature difference value sequence, and x is the sample.
Note Dj＝F1(xj)-F2(xj)，
Figure GDA0002508719650000121
Figure GDA0002508719650000122
Represents DjMaximum value of absolute distance. The test statistic Z is approximated to a normal distribution, expressed as:
Figure GDA0002508719650000123
when the null hypothesis is true, the Z-dependent density distribution d converges to the K-distribution, i.e. when the samples are taken from the one-dimensional continuous distribution F,
Figure GDA0002508719650000124
Figure GDA0002508719650000125
the maximum value of the absolute distance of B (F (x)) is taken, and x is the sample.
The empirical distribution function (i.e., Kolmogonov distribution function) b (t) is:
Figure GDA0002508719650000126
wherein x is an independent variable, and i is a natural number;
as shown in FIG. 4, the sequence x of temperature difference values to be checked is judgedtSequence y of temperature differences from a preceding adjacent time periodtAnd temperature difference series measured by other similar position sensors { z1t,…,zntWhen the distribution is consistent, the temperature difference value sequence x is determined by checking the maximum difference value D of the empirical distribution function among the sequencestThe significance of (a). When the maximum difference value D obtained by actual calculation is larger than a certain set standard value, or the K-S distribution probability P value corresponding to the maximum difference value D is smaller than a certain set standard value, the assumption that the two sequences are from the same distribution population is rejected, and the two temperature difference sequences obviously have no consistency. That is, it is reasonable to say that there is a significant difference between the two sequences, and it is not consistent with the above-mentioned assumption that the temperature difference sequence distribution does not change greatly in a short time, and it is further explained that the abnormality is caused by the temperature sensor (system).
The temperature sensor self-checking device and the method described in the specific embodiment of the invention are based on a big data platform, and a set of temperature sensor (system) abnormity self-checking device and a method are constructed by combining temperature data obtained by measuring sensors of various related components (axles, motors, transformers, converters and the like) of a train fed back on site, so that the automation and intelligent self-checking and early warning of a train sensing system are realized, and the rapid and effective self-checking of the temperature sensor by the train system can be realized by organically combining actual data with a statistical analysis algorithm, thereby ensuring the safe and efficient operation of the train. The embodiment of the invention determines the temperature difference abnormal detection threshold value with a certain probability by calculating the distribution characteristics of the fluctuation sequence of the temperature difference value, well reflects the fluctuation change of the sensor abnormal data in a short time, effectively detects the abnormal change of the measured temperature value caused by the abnormality of the sensor (system), and greatly improves the abnormal self-checking efficiency of the sensor (system). Meanwhile, the specific embodiment of the invention is based on the characteristics and the rule of the temperature change of train components, utilizes the property that the temperature difference distribution is not changed much in a short time, and combines a nonparametric inspection method to compare the difference of the temperature difference distribution among different periods, thereby greatly effectively reducing the false alarm rate of abnormal self-inspection and early warning of the sensor (system) and greatly improving the total accuracy rate of prediction.
Meanwhile, the K-S nonparametric distribution test method used in the embodiments of the present invention may also try to perform distribution diversity test by adopting a unit root test, a symbolic test, and other non-parametric tests, and the other parametric tests, and the temperature sensor self-test device and method described in the embodiments of the present invention may be implemented by adopting reference codes R and Python codes, or by adopting a series of languages such as C, MAT L AB and Java.
By implementing the technical scheme of the temperature sensor self-checking device and the method described in the specific embodiment of the invention, the following technical effects can be produced:
(1) the temperature sensor self-checking device and the method described in the specific embodiment of the invention perform self-checking and early warning based on the variation value of the temperature value measured by the sensor (system), and can more effectively and directly discover possible abnormalities and ensure more real and accurate monitoring and early warning results compared with the technical scheme in the prior art based on other variables such as current, voltage and the like or comparing the measurement results of a plurality of devices;
(2) the temperature sensor self-checking device and the method described in the specific embodiment of the invention not only utilize the threshold index to carry out self-checking early warning, but also further detect and find abnormality from the angle of comparison distribution change, compared with the prior art which only uses one or two indication indexes to analyze sensor faults, the rules and results of self-checking and early warning are more accurate and effective;
(3) the temperature sensor self-checking device and the method described in the specific embodiment of the invention are based on a large amount of normal and abnormal data development analysis and application in the actual operation process, compared with the problems of less data amount and the like in the prior art, the model result is more reliable, the considered factors are more sufficient and reasonable, and the verifiability and the practicability are stronger;
(4) the temperature sensor self-checking device and the method described in the specific embodiment of the invention perform real-time self-checking and early warning based on a large amount of temperature data measured in the running process of a train, automatically adjust the threshold value and distribute the checking segmentation mode based on continuously updated data, and have remarkable high efficiency and intelligent level.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make many possible variations and modifications to the disclosed embodiments, or equivalent modifications, without departing from the spirit and scope of the invention, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent replacement, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the protection scope of the technical solution of the present invention.

Claims (6)

1. A temperature sensor self-test device, comprising:
the anomaly detection threshold calculation module (1) is used for carrying out differential processing on a temperature data sequence T measured by a sensor under the normal running condition of a train to obtain a segmentation standard deviation sequence theta of the temperature difference sequence T and carrying out statistical analysis on the standard deviation sequence theta to obtain an anomaly detection threshold K;
the key characteristic value extraction module (2) is used for carrying out differential processing on a temperature data sequence t measured by a sensor input in real time to obtain a segmented standard deviation sequence η of the temperature difference sequence t;
the first anomaly detection module (3) is used for judging whether the segmented temperature difference sequence t is abnormal or not according to the anomaly detection threshold K output by the anomaly detection threshold calculation module (1) and the standard deviation sequence η output by the key characteristic value extraction module (2), if the segmented standard deviation sequence η of a certain temperature difference sequence t is greater than or equal to the anomaly detection threshold K, judging that the temperature difference sequence t is abnormal and outputting the temperature difference sequence t with the abnormality, otherwise, judging that the sensor is normal;
the consistency checking module (4) is used for carrying out distribution consistency checking on the temperature difference sequence t with the abnormality output by the first abnormality detecting module (3), a normal reference sequence and a temperature difference sequence t in the previous adjacent time period;
the second anomaly detection module (5) is used for judging whether the distribution consistency detection occurrence probability P value output by the consistency detection module (4) is smaller than a set standard or not, if so, outputting a sensor anomaly early warning signal, otherwise, the sensor is normal;
the abnormal detection threshold value calculation module (1) acquires a temperature data sequence T measured by a sensor in the running process of a certain part of a train under normal conditions, and calculates a temperature difference value sequence T according to unit time delta T; for the same temperature difference value sequence T in unit timeThe length T1 is segmented, and the standard deviation theta of each segment of temperature difference value sequence T is calculatediAnd forming a standard deviation sequence theta; analyzing the distribution condition of the standard deviation sequence theta, calculating the mean value mu and the standard deviation sigma of the standard deviation sequence theta according to the occurrence probability
Figure FDA0002508719640000011
Constructing an abnormal detection threshold value K corresponding to the part of the train according to the principle of (1);
wherein, theta is the standard deviation of the temperature difference value sequence T;
Figure FDA0002508719640000012
Figure FDA0002508719640000013
wherein, ω isiAs weighting coefficients, here
Figure FDA0002508719640000014
xiIs a sample value, n is the number of samples;
the key characteristic value extraction module (2) acquires a temperature data sequence T measured by a real-time input sensor, calculates a temperature difference sequence T according to unit time delta T, segments the temperature difference sequence T in unit time according to the same length T2, calculates the standard deviation of each segment of the temperature difference sequence T, and forms a standard deviation sequence η.
2. The temperature sensor self-checking device according to claim 1, wherein the consistency check module (4) compares the anomaly detection threshold K with the standard deviation sequence η to find that the temperature difference sequence t in a certain section of the train running process has suspected abnormal data, and records the temperature difference sequence x in the certain section of the train running processtAnd obtaining the temperature difference value sequence x of the sectiontAnd the temperature difference sequence y of the previous adjacent time periodtAnd simultaneously acquiring a temperature difference sequence z1 measured by other similar position sensors of the train in the same time periodt，…，zntAnd for the sequence x of temperature differences suspected to be abnormaltSequence y of temperature differences respectively from a preceding adjacent time segmenttAnd temperature difference series measured by other similar position sensors { z1t，…，zntCarry out K-S distribution test one by one.
3. The temperature sensor self-testing device according to claim 1 or 2, characterized in that: the consistency checking module (4) judges the temperature difference value sequence x to be checkedtSequence y of temperature differences from a preceding adjacent time periodtAnd temperature difference series measured by other similar position sensors { z1t，…，zntWhen the distribution is consistent, the temperature difference value sequence x is determined by checking the maximum difference value D of the empirical distribution function among the sequencestThe significance of (a); when the maximum difference value D obtained by actual calculation is larger than a certain set standard value or the distribution probability P value corresponding to the maximum difference value D is smaller than a certain set standard value, the two temperature difference value sequences do not have consistency;
wherein, the temperature difference sequence xtIs n1, sequence of temperature differences yt，z1t，…，zntThe sample size of any difference sequence is n2, F1(x) And F2(x) Respectively representing accumulated empirical distribution functions of two samples, wherein j is a temperature difference sequence segmentation identifier, and x is a sample;
note Dj＝F1(xj)-F2(xj)，
Figure FDA0002508719640000021
Figure FDA0002508719640000022
Represents DjMaximum value of absolute distance; the test statistic Z is approximated to a normal distribution, expressed as:
Figure FDA0002508719640000023
when the null hypothesis is true, the Z-dependent density distribution d converges to the K-distribution, i.e. when the samples are taken from the one-dimensional continuous distribution F,
Figure FDA0002508719640000024
Figure FDA0002508719640000025
taking the maximum value of the absolute distance of B (F (x)), wherein x is a sample;
the empirical distribution function B (t) is:
Figure FDA0002508719640000026
wherein x is an independent variable, and i is a natural number.
4. A temperature sensor self-checking method is characterized by comprising the following steps:
s10) carrying out differential processing on a temperature data sequence T measured by a sensor under the normal running condition of the train to obtain a segmentation standard deviation sequence theta of the temperature difference sequence T, and carrying out statistical analysis on the standard deviation sequence theta to obtain an anomaly detection threshold value K;
s20) carrying out the same difference processing as the step S10) on the temperature data sequence t input in real time and measured by the sensor to obtain a segmented standard deviation sequence η of the temperature difference sequence t;
s30) judging whether the segmented temperature difference sequence t is abnormal or not based on the abnormal detection threshold K obtained in the step S10) and the standard deviation sequence η obtained in the step S20), if the segmented standard deviation sequence η of a certain temperature difference sequence t is more than or equal to the abnormal detection threshold K, judging that the temperature difference sequence t is abnormal, and entering the step S40), otherwise, judging that the sensor is normal;
s40) judging the distribution consistency of the temperature difference sequence t with the abnormality in the step S30) with the normal reference sequence and the temperature difference sequence t of the previous adjacent time period; if the consistency exists, the sensor is judged to be normal, and if the consistency does not exist, the sensor is judged to be abnormal;
the step S10) further includes:
s11) selecting a temperature data sequence T measured by a sensor in the running process of a certain part of the train under normal conditions, and calculating a temperature difference sequence T according to the delta T in unit time;
s12) segmenting the temperature difference sequence T in unit time according to the same length T1, and calculating the standard deviation theta of each temperature difference sequence TiAnd forming a standard deviation sequence theta;
s13), analyzing the distribution condition of the standard deviation sequence theta, and calculating the mean value mu and the standard deviation sigma of the standard deviation sequence theta according to the occurrence probability
Figure FDA0002508719640000031
Constructing an abnormal detection threshold value K corresponding to the part of the train according to the principle of (1);
wherein, theta is the standard deviation of the temperature difference value sequence T;
Figure FDA0002508719640000032
Figure FDA0002508719640000033
wherein, ω isiAs weighting coefficients, here
Figure FDA0002508719640000034
xiIs a sample value, n is the number of samples;
the step S20) further includes:
s21) inputting the temperature data sequence t measured by the sensor in real time;
s22) calculating a temperature difference sequence t according to the unit time delta t;
s23) segmenting the temperature difference value sequences T in unit time according to the same length T2, calculating the standard deviation of each temperature difference value sequence T, and forming standard deviation sequences η.
5. The self-test method of a temperature sensor according to claim 4,
the step S40) further includes:
s41) comparing the abnormal detection threshold K with the standard deviation sequence η to find the data of suspected abnormality of a temperature difference sequence t in a certain section in the running process of the train, and recording the temperature difference sequence x in the sectiontAnd obtaining the temperature difference value sequence x of the sectiontAnd the temperature difference sequence y of the previous adjacent time periodt；
S42) obtaining a temperature difference value sequence z1 measured by other similar position sensors of the train in the same time periodt，…，znt；
S43) the sequence of temperature differences x for suspected abnormalitytSequence y of temperature differences respectively from a preceding adjacent time segmenttAnd temperature difference series measured by other similar position sensors { z1t，…，zntPerforming K-S distribution test one by one;
s44), when the occurrence probability P values of all the tests are smaller than the set standard, outputting an abnormal early warning signal of the sensor, otherwise, the sensor is normal.
6. The temperature sensor self-testing method according to claim 4 or 5, wherein the step S43) further comprises:
setting a sequence x of temperature differencestIs n1, sequence of temperature differences yt，z1t，…，zntThe sample size of any difference sequence is n2, F1(x) And F2(x) Respectively representing accumulated empirical distribution functions of two samples, wherein j is a temperature difference sequence segmentation identifier, and x is a sample;
note Dj＝F1(xj)-F2(xj)，
Figure FDA0002508719640000041
Figure FDA0002508719640000042
Represents DjMaximum value of absolute distance; the test statistic Z is approximated to a normal distribution, expressed as:
Figure FDA0002508719640000043
when the null hypothesis is true, the Z-dependent density distribution d converges to the K-distribution, i.e. when the samples are taken from the one-dimensional continuous distribution F,
Figure FDA0002508719640000044
Figure FDA0002508719640000045
taking the maximum value of the absolute distance of B (F (x)), wherein x is a sample;
the empirical distribution function B (t) is:
Figure FDA0002508719640000046
wherein x is an independent variable, and i is a natural number;
in judging the temperature difference value sequence x to be detectedtSequence y of temperature differences from a preceding adjacent time periodtAnd temperature difference series measured by other similar position sensors { z1t，…，zntWhen the distribution is consistent, the temperature difference value sequence x is determined by checking the maximum difference value D of the empirical distribution function among the sequencestThe significance of (a); when the maximum difference value D obtained by actual calculation is greater than a certain set standard value, or the distribution probability P corresponding to the maximum difference value D is less than a certain set standard value, there is no consistency between the two temperature difference value sequences.
CN201811236829.6A 2018-10-23 2018-10-23 Temperature sensor self-checking device and method Active CN109186813B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811236829.6A CN109186813B (en) 2018-10-23 2018-10-23 Temperature sensor self-checking device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811236829.6A CN109186813B (en) 2018-10-23 2018-10-23 Temperature sensor self-checking device and method

Publications (2)

Publication Number Publication Date
CN109186813A CN109186813A (en) 2019-01-11
CN109186813B true CN109186813B (en) 2020-07-24

Family

ID=64942836

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811236829.6A Active CN109186813B (en) 2018-10-23 2018-10-23 Temperature sensor self-checking device and method

Country Status (1)

Country Link
CN (1) CN109186813B (en)

Families Citing this family (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110107389B (en) * 2019-07-08 2019-10-22 潍柴动力股份有限公司 A kind of creditability detection method and device of temperature sensor
CN110398375B (en) * 2019-07-16 2021-10-19 广州亚美信息科技有限公司 Method, device, equipment and medium for monitoring working state of vehicle cooling system
CN112241511B (en) * 2019-07-19 2024-05-14 上海杰之能软件科技有限公司 Performance detection method and device for auxiliary electrical system of vehicle and terminal
CN110751045B (en) * 2019-09-19 2023-12-08 厦门科华数能科技有限公司 Fault recording method, system and terminal equipment
CN110736894A (en) * 2019-09-19 2020-01-31 科华恒盛股份有限公司 Fault recording method, system and terminal equipment
CN110658765A (en) * 2019-10-14 2020-01-07 北京东方瑞威科技发展股份有限公司 Railway overload and unbalanced load rail weighbridge multi-path data acquisition system with diagnosis function
CN110715678B (en) * 2019-10-22 2021-12-03 东软睿驰汽车技术（沈阳）有限公司 Sensor abnormity detection method and device
CN113065219B (en) * 2020-01-02 2023-03-14 株洲中车时代电气股份有限公司 Method and device for detecting abnormality of train traction transformer cooling system
CN111371594B (en) * 2020-02-25 2023-05-02 成都西加云杉科技有限公司 Equipment abnormality alarm method and device and electronic equipment
CN111562123B (en) * 2020-05-07 2022-01-21 广东电网有限责任公司 Self-checking method for damp-proof device
CN111998972B (en) * 2020-09-17 2021-07-16 南方电网科学研究院有限责任公司 Terminal block temperature drastic change alarm function detection method, device, terminal and medium
CN112037489B (en) * 2020-09-17 2021-07-16 南方电网科学研究院有限责任公司 Method and device for detecting out-of-limit alarm function of terminal block temperature, terminal and medium
CN112802312A (en) * 2020-12-30 2021-05-14 江苏龙威中科技术有限公司 Loongson 1B CPU-based monitoring board and detection method
CN114688693A (en) * 2020-12-31 2022-07-01 佛山市顺德区美的电热电器制造有限公司 Method and device for detecting ambient temperature change, electronic device, and medium
CN113392874B (en) * 2021-05-13 2022-12-13 中车唐山机车车辆有限公司 Abnormal state diagnosis method and device for rail vehicle and terminal equipment
CN113606752B (en) * 2021-06-29 2023-03-03 宁波德业日用电器科技有限公司 Jump-prevention dehumidifier humidity display method
CN113687609A (en) * 2021-07-21 2021-11-23 浙江微科机电有限公司 Intelligent monitoring system and monitoring method for Internet of things applied to abnormal environment
CN114383646B (en) * 2021-10-29 2023-08-25 廊坊市大华夏神农信息技术有限公司 Method and equipment for detecting resolution of continuously-variable measured sensor
CN114444988A (en) * 2022-04-11 2022-05-06 交通运输部公路科学研究所 Service performance evaluation method and device for traffic infrastructure health monitoring system
CN114961952A (en) * 2022-05-20 2022-08-30 潍柴动力股份有限公司 Method, device and equipment for determining probe identification and storage medium
CN115840897B (en) * 2023-02-09 2023-04-18 广东吉器电子有限公司 Temperature sensor data exception handling method
CN116090939B (en) * 2023-04-12 2023-06-23 山东民生集团有限公司 Artificial intelligence-based method for identifying and tracking problem products in supply chain
CN116643951B (en) * 2023-07-24 2023-10-10 青岛冠成软件有限公司 Cold chain logistics transportation big data monitoring and collecting method
CN117648232B (en) * 2023-12-11 2024-05-24 武汉天宝莱信息技术有限公司 Application program data monitoring method, device and storage medium
CN118051744A (en) * 2024-04-16 2024-05-17 天津君磊科技有限公司 Waterproof signal connector fault diagnosis method based on machine learning algorithm

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6013533A (en) * 1997-09-05 2000-01-11 Lsi Logic Corporation Real time quiescent current test limit methodology
CN101581587B (en) * 2009-06-23 2011-12-07 北京航空航天大学 Method for automatically evaluating uncertainty of measurement of virtual instrument
CN104408907B (en) * 2014-10-31 2016-07-13 重庆大学 There is the freeway traffic event Duration Prediction method of on-line optimization ability
CN106112697B (en) * 2016-07-15 2018-07-17 西安交通大学 A kind of milling parameter automatic alarm threshold setting method based on 3 σ criterion
CN106570073B (en) * 2016-10-14 2019-11-15 北京建筑大学 Surface water quality data parasitic error screening method and device

Also Published As

Publication number Publication date
CN109186813A (en) 2019-01-11

Similar Documents

Publication Publication Date Title
CN109186813B (en) Temperature sensor self-checking device and method
CN109239265B (en) Fault detection method and device for monitoring equipment
CN116879662B (en) Transformer fault detection method based on data analysis
KR20190013017A (en) Method and device for equipment health monitoring based on sensor clustering
CN111964909A (en) Rolling bearing operation state detection method, fault diagnosis method and system
CN112734977B (en) Equipment risk early warning system and algorithm based on Internet of things
KR102417800B1 (en) Apparatus and method for determining power cable aging
KR20200103167A (en) Predictive diagnosis method and system of nuclear power plant equipment
KR20200010671A (en) System and method for fault diagnosis of equipment based on machine learning
CN114666117A (en) Network security situation measuring and predicting method for power internet
Ginart et al. Automated feature selection for embeddable prognostic and health monitoring (PHM) architectures
KR20230125116A (en) The method for fault detection without training data or diagnosis with prediction of remaining time until breakdown using clustering algorithm and statistical methods
CN117630797A (en) Ammeter health state detection method, system and storage medium based on working current
KR20220132824A (en) Distribution facility condition monitoring system and method
EP4273520A1 (en) Method and system for comprehensively diagnosing defect in rotating machine
CN114001887B (en) Bridge damage assessment method based on deflection monitoring
KR102649453B1 (en) Method and system for diagnosing defects in rotating machinery
CN112228042B (en) Method for judging working condition similarity of pumping well based on cloud edge cooperative computing
CN114492636A (en) Transformer winding state signal acquisition system
RU2648413C1 (en) Method of the modes control based on the neural network diagnostics of faults and technical condition of the electric-drive gas-compressor unit
CN115511237A (en) Device operation condition monitoring method and system
CN111986469A (en) Intelligent diagnosis method for field terminal fault
CN117783792B (en) Valve side sleeve insulation state detection method and system based on multiparameter real-time monitoring
CN116878728B (en) Pressure sensor fault detection analysis processing system
KR102303406B1 (en) Method for something wrong diagnosis of industrial equipment and the device

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