CN114936675A - Fault early warning method and device, storage medium and electronic equipment - Google Patents
Fault early warning method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114936675A CN114936675A CN202210451033.2A CN202210451033A CN114936675A CN 114936675 A CN114936675 A CN 114936675A CN 202210451033 A CN202210451033 A CN 202210451033A CN 114936675 A CN114936675 A CN 114936675A
- Authority
- CN
- China
- Prior art keywords
- early warning
- state data
- sensors
- fault
- difference
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000007619 statistical method Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000002955 isolation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The application relates to the technical field of rail transit fault early warning, and discloses a fault early warning method, which is characterized by comprising the following steps: acquiring running state data of all target sensors, wherein all the target sensors are similar sensors; monitoring and early warning all the target sensors according to the running state data through a fault early warning model; and generating the fault early warning model according to the operation state data of a plurality of similar sensors of the target sensor. The method is characterized in that the running state data of the similar sensors of the train is used as a basis, the state data difference between the similar sensors is subjected to statistical analysis, the change characteristics and the distribution rule of the difference are extracted, and then a set of sensor abnormity self-checking method is constructed, so that the intelligent early warning of sudden faults and gradual faults of the similar sensor system of the train is realized, the suggestions are provided for the maintenance work of the after-sales personnel in advance, and the safe and efficient running of the train is guaranteed.
Description
Technical Field
The present application relates to the field of rail transit fault early warning technologies, and in particular, to a fault early warning method, an apparatus, a storage medium, and an electronic device.
Background
Currently, research on the early warning of the failure of the sensor itself is mainly focused on the following four categories: the fault early warning system comprises an expert experience-based early warning model, an intelligent hardware analysis-based fault early warning model, an alarm trip limit-based fault early warning model and a data-driven fault early warning model.
The early warning model based on expert experience is mainly used for describing the fault phenomenon and the fault mode of each device in the fault process qualitatively or quantitatively on the basis of accumulated experience knowledge of relevant experts and operators. After the sensor has abnormal symptoms, the reasoning ability of the process expert on monitoring is simulated in a system reasoning mode, a deduction mode and the like, and therefore the sensor fault early warning is automatically completed. The method depends on experience knowledge and is subjective.
The early warning idea of the fault early warning model based on intelligent hardware analysis needs to install a high-performance sensor on a monitored sensor, and advance early warning is carried out through signal acquisition, demodulation and analysis. This early warning method requires additional equipment, is costly, and in some cases is not feasible due to installation constraints.
The main monitoring standard of the early warning mode of the fault early warning model based on the alarm trip limit value is a manufacturer threshold value or an industry threshold value, and timely alarming or tripping is carried out after the parameter of a sensor to be monitored exceeds the limit, so that the equipment and personal safety are protected. In the early warning mode, the fault early warning time is mostly in the late stage of the fault, and meanwhile, the fault hidden danger within the threshold value cannot be detected.
The idea of the data-driven fault early warning model is to utilize state data of a sensor during operation to transversely or longitudinally acquire the state data characteristics and the change rule of the sensor, and perform early warning analysis on sudden faults and trend abnormity according to the state data characteristics and the change rule. The method does not need to be additionally provided with additional equipment, only utilizes the self-state data of the sensor to carry out early warning, and has low input cost and strong applicability.
For the similar sensors of the train, due to the consistency of the measured objects, the situation of large measurement data difference is almost impossible to occur between the similar sensors which normally work.
Disclosure of Invention
In order to solve the problems, the application provides a fault early warning method, a fault early warning device, a storage medium and electronic equipment, on the basis of running state data of similar sensors of a train, the difference of the state data among the similar sensors is subjected to statistical analysis, then the change characteristics and the distribution rule of the difference are extracted, and a set of sensor abnormity self-checking method is further constructed, so that intelligent early warning of sudden faults and gradual faults of the similar sensor system of the train is realized, a suggestion is provided for maintenance work of after-sales personnel in advance, and the safe and efficient running of the train is guaranteed.
In a first aspect of the present application, a fault pre-warning method is provided, where the method includes:
acquiring running state data of all target sensors, wherein all the target sensors are similar sensors;
monitoring and early warning all the target sensors according to the running state data through a fault early warning model;
the fault early warning model is generated according to the operation state data of a plurality of similar sensors of the target sensor.
In some embodiments, the generating of the fault pre-warning model includes:
acquiring operation state data of the plurality of sensors of the same type;
acquiring an original state data difference sequence according to the running state data;
acquiring a window characteristic value difference sequence according to the running state data;
and generating the fault early warning model according to the original state data difference sequence and the window characteristic value difference sequence.
In some embodiments, the plurality of homogeneous sensors are all sensors that have not historically failed.
In some embodiments, after the obtaining the operation state data of the plurality of homogeneous sensors, the method further includes:
and filtering the operation state data of the plurality of sensors of the same type.
In some embodiments, the generating the fault pre-warning model according to the raw state data difference sequence and the window feature value difference sequence includes:
acquiring an early warning threshold interval and a difference value time sequence according to the original state data difference sequence and the window characteristic value difference sequence;
performing stationarity analysis on the difference value time sequence to obtain an analysis result;
acquiring historical fault data of the same type of sensors which have faults;
and generating a burst fault early warning model according to the original state data difference sequence, the window characteristic value difference sequence and the early warning threshold interval, or generating a gradual change fault early warning model according to the analysis result and the historical fault data.
In some embodiments, if the fault early warning model is an emergency fault early warning model, the monitoring and early warning of all the target sensors according to the operating state data by the fault early warning model includes:
acquiring an original state data difference value and a window characteristic value difference value under a current time window from the running state data of all the target sensors;
carrying out abnormity judgment on the original state data difference value under the current time window and the window characteristic value difference values of a plurality of continuous time windows;
and when judging that the current time window has abnormal state difference data or the continuous time windows have abnormal window characteristic values, early warning is carried out.
In some embodiments, the performing an anomaly determination on the raw state data difference value in the current time window includes:
acquiring the number of early warning pieces with the original state data difference value not within the early warning threshold interval under the current time window;
and if the number of the early warning pieces is not less than the preset number of the early warning pieces, determining that abnormal state difference data exists in the current time window.
In some embodiments, the performing an anomaly determination on the window feature value difference values of the consecutive time windows includes:
if the window characteristic value difference value under the current time window is not within the early warning threshold interval, the characteristic value of the current time window is abnormal;
and if the number of the windows with the abnormal characteristic values is not less than the preset number of the abnormal windows, determining that the abnormal window characteristic values exist in the subsequent continuous multiple time windows.
In some embodiments, if the fault early warning model is a gradual change fault early warning model, the monitoring and early warning of all the target sensors by the fault early warning model according to the operating state data includes:
acquiring the fault probability of the sensors of the same type according to the running state data of all the target sensors;
and when the fault probability is not less than a preset early warning probability threshold value, early warning is carried out.
In a second aspect of the present application, there is provided a fault warning apparatus, the apparatus including:
the acquisition module is used for acquiring the running state data of all target sensors, wherein all the target sensors are the same type of sensors;
the early warning module is used for monitoring and early warning all the target sensors according to the running state data through a fault early warning model;
and the generating module is used for generating the fault early warning model according to the running state data of a plurality of similar sensors of the target sensor.
In a third aspect of the present application, a storage medium storing a computer program executable by one or more processors for implementing the fault pre-warning method as described above is provided.
In a fourth aspect of the present application, an electronic device is provided, which includes a memory and a processor, where the memory stores a computer program, and the memory and the processor are communicatively connected to each other, and when the computer program is executed by the processor, the fault pre-warning method as described above is implemented.
Compared with the prior art, the technical scheme of the application has the following advantages or beneficial effects:
1. the fault early warning is carried out by utilizing the self running state data of the similar sensors, so that the potential fault can be found more effectively and more directly; meanwhile, model construction and verification are carried out through a large amount of historical normal data and fault data, and the reliability of monitoring and early warning results is higher;
2. a sliding window mode is introduced to calculate difference characteristics, so that data information loss in a time dimension is avoided, and the integrity of the information is guaranteed;
3. stability analysis is introduced to judge whether trend change exists in the difference between the sensors of the same type, and the trend fault is simply and objectively determined;
4. a trend fault probability prediction model is constructed according to the fitting difference value data, so that faults can be predicted timely and accurately, maintenance efficiency is improved, and fault cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a fault early warning method according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a method for early warning of a sudden failure according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a gradual failure warning method according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an apparatus according to an embodiment of the present disclosure;
fig. 5 is a connection block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following detailed description will be provided with reference to the accompanying drawings and embodiments, so that how to apply the technical means to solve the technical problems and achieve the corresponding technical effects can be fully understood and implemented. The embodiments and various features in the embodiments of the present application can be combined with each other without conflict, and the formed technical solutions are all within the scope of protection of the present application.
Example one
The present embodiment provides a fault early warning method, and fig. 1 is a flowchart of the fault early warning method provided in the embodiment of the present application, and as shown in fig. 1, the method of the present embodiment includes:
and S110, acquiring running state data of all target sensors, wherein all the target sensors are the same type of sensors.
Optionally, the target sensor includes a plurality of sensors, and all of the sensors are the same type.
In some embodiments, after the acquiring the operation state data of all target sensors, all target sensors being the same type of sensor, the method further includes:
and filtering the running state data.
Optionally, the filtering process includes removing garbage data in the running state data, and the garbage data may include: null, error, etc. The garbage data may also include data under abnormal operating conditions, such as data immediately after power up, component isolation or over-equalization data.
It should be noted that, when the operating state data of the target sensor is optimized, data considered as junk data by other users can be removed, and specific junk data can be set according to actual needs of the users, which is not particularly limited herein.
And S120, monitoring and early warning are carried out on all the target sensors according to the running state data through a fault early warning model.
It should be noted that the fault early warning model is generated according to the operation state data of a plurality of similar sensors of the target sensor.
In some embodiments, the generating of the fault pre-warning model includes:
acquiring operation state data of the plurality of sensors of the same type;
acquiring an original state data difference sequence according to the running state data;
acquiring a window characteristic value difference sequence according to the running state data;
and generating the fault early warning model according to the original state data difference sequence and the window characteristic value difference sequence.
In some embodiments, the plurality of homogeneous sensors are sensors that have not historically failed.
Optionally, the acquiring the operation state data of a plurality of similar sensors includes: and acquiring the operation state data of a plurality of similar sensors which have not failed historically.
It should be noted that the sensors of the same type, which have not failed historically, do not include any target sensor.
Optionally, the sequences each include an array.
It should be noted that the same type of sensor includes a plurality of sensors capable of detecting the same type of data, and to the extent that two sensors have the same function and can detect the same type of data, the two sensors may be referred to as the same type of sensor.
In some embodiments, after the obtaining the operation state data of the plurality of homogeneous sensors, the method further comprises:
and filtering the operation state data of the plurality of sensors of the same type.
Optionally, after obtaining the operation state data of the sensors of the same type that have not failed in history, null values or error values in the operation state data are removed, and then the data are filtered to remove the sensor data under the abnormal working conditions (for example, when the system is just powered on, and components are isolated or excessively equal).
Optionally, the garbage data may include: null, error, etc. The garbage data may also include data under abnormal operating conditions, such as data immediately after power up, component isolation or over-equalization data.
It should be noted that, when the operating state data of the target sensor is optimized, data considered as junk data by other users can be removed, and specific junk data can be set according to actual needs of the users, which is not particularly limited herein.
Alternatively, the raw state difference may be represented as X _ diff ═ X _ a-X _ b, where a and b represent two sensors of the same type, and X _ a and X _ b represent the sequence of states of the respective sensors. The same type of sensor may also include more sensors, for example, X _ diff — X _ a-X _ b-X _ c- … X _ n, where X _ n is represented as a sequence of states for the nth sensor.
In some embodiments, the sequence of window feature value differences comprises:
mean, rate of change.
Optionally, determining a time window length T, and performing sliding window in a manner that an overlap ratio is P; for a state sequence of a single window, characteristic values such as a mean value and a change rate of data in the window are calculated, for example, a sequence { Xa _ t0, Xa _ t1, Xa _ t2,...... times.xa _ tn } of the sensor a in a time window length of t0 to tn is calculated, a mean value of the sequence is calculated (time sequence averaging), and a change rate det is (Xa _ t1-Xa _ t0)/(t1-t 0). A series of window characteristic difference values for sensors a and b may be obtained, and a series of window characteristic difference values for the same type of sensor may be calculated, for example, Y _ diff is Y _ a-Y _ b, where a and b represent 2 sensors of the same type, and Y _ a and Y _ b are series of window characteristic values (mean, rate of change, etc.) for sensors a and b, respectively.
In the present embodiment, the window feature information is reflected by the mean value and the change rate, and features such as variance and median may be used instead.
In some embodiments, the generating the fault pre-warning model according to the raw state data difference sequence and the window feature value difference sequence includes:
acquiring an early warning threshold interval and a difference value time sequence according to the original state data difference sequence and the window characteristic value difference sequence;
performing stationarity analysis on the difference value time sequence to obtain an analysis result;
acquiring historical fault data of the same type of sensors which have faults;
and generating a burst fault early warning model according to the original state data difference sequence, the window characteristic value difference sequence and the early warning threshold interval, or generating a gradual change fault early warning model according to the analysis result and the historical fault data.
Optionally, the other sensors of the same type include sensors of the same type that have failed.
In some embodiments, the obtaining an early warning threshold interval according to the original state data difference sequence and the window characteristic value difference sequence includes:
acquiring a mean value mean and a standard deviation std according to the original state data difference sequence and the window characteristic value difference sequence;
and respectively taking mean-3 std and mean +3 std as the upper limit and the lower limit of the early warning threshold interval.
Optionally, for the difference sequence (original state data difference sequence, window feature value difference sequence), a mean value mean and a standard deviation std are respectively calculated, and [ mean-3 × std, mean +3 × std ] is taken as an upper limit threshold and a lower limit threshold. The upper and lower threshold values may be expressed in other forms such as [ 0.01%, 99.99% ] quantile.
It should be noted that the upper and lower threshold values may be set according to the actual requirements of the user, and are not particularly limited herein.
Optionally, a mean and a standard deviation std are obtained according to the original state data difference sequence and the window characteristic value difference sequence, where the mean may be obtained by the following formula:
the standard deviation std can be obtained by the following formula:
optionally, after obtaining the difference sequence (the original state data difference sequence, the window characteristic value difference sequence), a difference value time sequence is obtained.
Optionally, the difference value time sequence is obtained according to the obtained original state data difference value sequence and the obtained window characteristic value difference value sequence, for example, if the difference value in the original state data difference value sequence does not meet a preset difference value requirement, the time window is stored in the difference value time sequence, wherein the specific preset difference value requirement may be set according to expert experience or actual requirements.
Optionally, performing stationarity analysis on the obtained difference value time sequence by an ADF unit root inspection method, and if the difference sequence has no unit root, the sequence is stable, that is, the difference value has no gradual change trend; and otherwise, the sequence is considered to be unstable, the difference value time sequence is fitted, and a gradual change fault early warning model is constructed by combining historical fault data.
It should be noted that although the ADF unit root inspection method is selected for the difference value stationarity inspection in the present embodiment, methods such as PP inspection, KPSS inspection, and LMC inspection may also be selected for the difference value stationarity inspection.
In some embodiments, if the fault early warning model is an emergency fault early warning model, the monitoring and early warning of all the target sensors according to the operating state data by the fault early warning model includes:
acquiring an original state data difference value and a window characteristic value difference value under a current time window from the running state data of all the target sensors;
carrying out abnormity judgment on the difference value of the original state data in the current time window and the difference values of the window characteristic values of a plurality of continuous time windows;
and when judging that the current time window has abnormal state difference data or the continuous time windows have abnormal window characteristic values, early warning is carried out.
Optionally, the current window includes a time sequence tracing back the window length from the current time.
In some embodiments, the performing an anomaly determination on the raw state data difference value in the current time window includes:
acquiring the number of early warning pieces with the original state data difference value not within the early warning threshold interval under the current time window;
and if the number of the early warning pieces is not less than the preset number of the early warning pieces, determining that abnormal state difference data exists in the current time window.
In some embodiments, the performing an anomaly determination on the window feature value difference values of the consecutive time windows includes:
if the window characteristic value difference value under the current time window is not within the early warning threshold interval, the characteristic value of the current time window is abnormal;
and if the number of the windows with the abnormal characteristic values is not less than the preset number of the abnormal windows, determining that the abnormal window characteristic values exist in the subsequent continuous multiple time windows.
Optionally, for the original value difference sequence, if the number of state data differences in the current window that do not satisfy the early warning threshold interval exceeds p × T, an alarm is given, where p is a value between (0 and 1); and for the window characteristic value difference value sequence, if the characteristic value difference values of t continuous windows do not meet the early warning threshold value interval, alarming, wherein t is an integer greater than or equal to 1.
It should be noted that the parameter time window length T, the overlap ratio P, the proportion P, and the window number T may be determined according to the specific representation of the historical data and/or the expert experience, or may be adjusted according to the actual requirements of the user, and the specific details are not particularly limited herein.
Optionally, fig. 2 may be referred to for the early warning of a sudden fault, and fig. 2 is a schematic diagram of an early warning method of a sudden fault according to an embodiment of the present disclosure.
Optionally, after the target sensor is early warned, the original state data and the window characteristic values of the multiple sensors in all the target sensors are respectively acquired, and then the sensor with the fault is located according to the change trends of the original state data and the original state data of the sensors, or according to the change trends of the window characteristic values and the window characteristic values of the sensors.
In some embodiments, if the fault early warning model is a gradual change fault early warning model, the monitoring and early warning of all the target sensors by the fault early warning model according to the operating state data includes:
acquiring the fault probability of the similar sensors according to the running state data of all the target sensors;
and when the fault probability is not less than a preset early warning probability threshold value, early warning is carried out.
Optionally, fitting the time series of the difference values by using an Auto-Regressive model (Auto-Regressive and Moving Average, referred to as ARMA model for short), and establishing a function d of the difference values and the sequence t ＝fun(x t ) Wherein x is t Is a sequence of time windows traced back from time t onwards. For a gradual fault, when the difference value is 0, the fault probability is defined to be 0, the fault occurrence time is defined to be 1, the difference value d at the time is, and for the time t, the fault probability at the time t can be expressed as Pt ═ d t /d。
Optionally, the preset early warning probability threshold may be set according to expert experience, for example, the preset early warning probability threshold is set to k, and when the current similar sensor fault probability is greater than the set threshold, a trending fault early warning result is output; otherwise, the sensor is normal, and monitoring is continued; where k is a value between (0, 1).
Optionally, referring to fig. 3, fig. 3 is a schematic diagram of a gradual failure warning method provided in an embodiment of the present application.
It should be noted that, for the real-time operation state data of the sensor, the data with the accumulated time length of T is input as a window, the difference sequence (the original state data difference sequence and the window characteristic value difference sequence) is calculated according to the above steps, and then the early warning judgment is performed according to the above early warning strategy; if the fault is judged, outputting an early warning result; otherwise, the state data of the sensor is continuously monitored.
The fault early warning method provided by the embodiment comprises the following steps: acquiring running state data of all target sensors, wherein all the target sensors are similar sensors; monitoring and early warning all the target sensors according to the running state data through a fault early warning model; and generating the fault early warning model according to the operation state data of a plurality of similar sensors of the target sensor. The method is characterized in that the running state data of the similar sensors of the train is used as a basis, the state data difference between the similar sensors is subjected to statistical analysis, the change characteristics and the distribution rule of the difference are extracted, and then a set of sensor abnormity self-checking method is constructed, so that the intelligent early warning of sudden faults and gradual faults of the similar sensor system of the train is realized, the suggestions are provided for the maintenance work of the after-sales personnel in advance, and the safe and efficient running of the train is guaranteed.
Example two
The embodiment of the present invention provides a fault warning device, which can be used to execute the embodiment of the method of the present application. Fig. 4 is a schematic structural diagram of an apparatus according to an embodiment of the present disclosure, and as shown in fig. 4, an apparatus 400 according to the embodiment includes:
an obtaining module 401, configured to obtain operating state data of all target sensors, where all target sensors are similar sensors;
the early warning module 402 is configured to monitor and early warn all the target sensors according to the operating state data through a fault early warning model;
a generating module 403, configured to generate the fault early warning model according to the operation state data of multiple similar sensors of the target sensor.
In some embodiments, the generation module 403 comprises: the device comprises a first acquisition unit, a second acquisition unit, a third acquisition unit and a generation unit; wherein the content of the first and second substances,
the first acquisition unit is used for acquiring the operation state data of the plurality of similar sensors;
the second acquisition unit is used for acquiring an original state data difference value sequence according to the running state data;
a third obtaining unit, configured to obtain a window feature value difference sequence according to the operating state data;
and the generating unit is used for generating the fault early warning model according to the original state data difference sequence and the window characteristic value difference sequence.
In some embodiments, the plurality of homogeneous sensors are sensors that have not historically failed.
In some embodiments, the obtaining module 401 includes a filtering unit, configured to filter the operation status data of the plurality of sensors of the same type after obtaining the operation status data of the plurality of sensors of the same type.
In some embodiments, the generating unit includes: the system comprises a first acquisition subunit, an analysis subunit, a second acquisition subunit and a generation subunit; wherein the content of the first and second substances,
the first acquisition subunit is used for acquiring an early warning threshold interval and a difference value time sequence according to the original state data difference value sequence and the window characteristic value difference value sequence;
the analysis subunit is used for performing stationarity analysis on the difference value time sequence to obtain an analysis result;
the second acquisition subunit is used for acquiring historical fault data of the same type of sensors which have failed;
and the generating subunit is used for generating a burst fault early warning model according to the original state data difference sequence, the window characteristic value difference sequence and the early warning threshold interval, or generating a gradual change fault early warning model according to the analysis result and the historical fault data.
In some embodiments, the early warning module 402 includes: the system comprises a first acquisition unit, a first judgment unit and an early warning unit; the first obtaining unit is used for obtaining an original state data difference value and a window characteristic value difference value under a current time window from the running state data of all the target sensors if the fault early warning model is a sudden fault early warning model;
the first judgment unit is used for judging the abnormality of the original state data difference value under the current time window and the window characteristic value difference values of a plurality of continuous time windows if the fault early warning model is a sudden fault early warning model;
and the early warning unit is used for carrying out early warning when judging that the current time window has abnormal state difference data or the continuous time windows have abnormal window characteristic values if the fault early warning model is a sudden fault early warning model.
In some embodiments, the determination unit comprises: acquiring a subunit and determining the subunit; wherein the content of the first and second substances,
the acquisition subunit is configured to acquire the number of early warning pieces with the original state data difference value not within the early warning threshold interval in the current time window;
and the determining subunit is configured to determine that abnormal state difference data exists in the current time window if the number of the early warning pieces is not less than a preset number of the early warning pieces.
In some embodiments, the performing an anomaly determination on the window feature value difference values of the consecutive time windows includes:
if the window characteristic value difference value under the current time window is not within the early warning threshold interval, the characteristic value of the current time window is abnormal;
and if the number of the windows with the abnormal characteristic values is not less than the preset number of the abnormal windows, determining that the abnormal window characteristic values exist in the subsequent continuous multiple time windows.
In some embodiments, the early warning module 402 further comprises: a second acquiring unit, a second judging unit; if the fault early warning model is a gradual change fault early warning model, the second obtaining unit is used for obtaining the fault probability of the similar sensors according to the running state data of all the target sensors; and the second judging unit is used for carrying out early warning through the early warning unit when the fault probability is not less than a preset early warning probability threshold value.
It should be noted that each of the modules/units may be a functional module or a program module, and may be implemented by software or hardware. For the modules/units implemented by hardware, the above modules/units may be located in the same processor; or the modules/units can be respectively positioned in different processors in any combination.
The device of the embodiment comprises: an obtaining module 401, configured to obtain operating state data of all target sensors, where all target sensors are similar sensors; the early warning module 402 is configured to monitor and early warn all the target sensors according to the operating state data through a fault early warning model; a generating module 403, configured to generate the fault early warning model according to the operation state data of multiple similar sensors of the target sensor. The method is characterized in that the running state data of the similar sensors of the train is used as a basis, the state data difference between the similar sensors is subjected to statistical analysis, the change characteristics and the distribution rule of the difference are extracted, and then a set of sensor abnormity self-checking method is constructed, so that the intelligent early warning of sudden faults and gradual faults of the similar sensor system of the train is realized, the suggestions are provided for the maintenance work of the after-sales personnel in advance, and the safe and efficient running of the train is guaranteed.
EXAMPLE III
The present embodiment further provides a storage medium, where a computer program is stored in the storage medium, and when the computer program is executed by a processor, the method steps in the first embodiment may be implemented, and details of the method are not repeated herein.
The storage medium may also include, among other things, a computer program, a data file, a data structure, etc., alone or in combination. The storage medium or computer program may be specially designed and understood by those skilled in the computer software arts, or the storage medium may be known and available to those skilled in the computer software arts. Examples of the storage medium include: magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CDROM disks and DVDs; magneto-optical media, e.g., optical disks; and hardware devices, particularly configured to store and execute computer programs, such as Read Only Memory (ROM), Random Access Memory (RAM), flash memory; or a server, app application mall, etc. Examples of computer programs include both machine code, such as produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter. The described hardware devices may be configured to act as one or more software modules to perform the operations and methods described above, and vice versa. In addition, the storage medium can be distributed over network coupled computer systems and can store and execute program code or computer programs in a distributed fashion.
Example four
Fig. 5 is a connection block diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 5, the electronic device 500 may include: a processor 501, a memory 502, a multimedia component 503, an input/output (I/O) interface 504, and a communication component 505.
The processor 501 is configured to perform all or part of the steps of the method according to the embodiment. The memory 502 is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.
The Processor 501 may be implemented by an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is configured to perform the method of the first embodiment.
The Memory 502 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk.
The multimedia component 503 may include a screen, which may be a touch screen, and an audio component for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in a memory or transmitted through a communication component. The audio assembly further comprises at least one speaker for outputting audio signals.
The I/O interface 504 provides an interface between the processor 501 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons.
The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. The wired communication includes communication through a network port, a serial port and the like; the wireless communication includes: Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, 5G, or a combination of one or more of them. The corresponding communication component 505 may thus comprise: Wi-Fi module, bluetooth module, NFC module.
In summary, the present application provides a fault early warning method, an apparatus, a storage medium, and an electronic device, where the method includes: acquiring running state data of all target sensors, wherein all the target sensors are similar sensors; monitoring and early warning all the target sensors according to the running state data through a fault early warning model; and generating the fault early warning model according to the operation state data of a plurality of similar sensors of the target sensor. The method is characterized in that the running state data of the similar sensors of the train is used as a basis, the state data difference between the similar sensors is subjected to statistical analysis, the change characteristics and the distribution rule of the difference are extracted, and then a set of sensor abnormity self-checking method is constructed, so that the intelligent early warning of sudden faults and gradual faults of the similar sensor system of the train is realized, the suggestions are provided for the maintenance work of the after-sales personnel in advance, and the safe and efficient running of the train is guaranteed.
It should be further understood that the method or system disclosed in the embodiments provided in the present application may be implemented in other ways. The method or system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and apparatus according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, a segment, or a portion of a computer program, which comprises one or more computer programs for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures, and in fact may be executed substantially concurrently, or in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer programs.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, apparatus or device comprising the element; if the description to "first", "second", etc. is used for descriptive purposes only, it is not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated; in the description of the present application, the terms "plurality" and "plurality" mean at least two unless otherwise indicated; if the server is described, it should be noted that the server may be an independent physical server or terminal, or a server cluster formed by a plurality of physical servers, or a cloud server capable of providing basic cloud computing services such as a cloud server, a cloud database, a cloud storage, a CDN, and the like; if an intelligent terminal or a mobile device is described in the present application, it should be noted that the intelligent terminal or the mobile device may be a mobile phone, a tablet Computer, an intelligent watch, a netbook, a wearable electronic device, a Personal Digital Assistant (PDA), an Augmented Reality device (AR), a Virtual Reality device (VR), a smart television, a smart audio, a Personal Computer (PC), and the like, but is not limited thereto, and the specific form of the intelligent terminal or the mobile device is not particularly limited in the present application.
Finally, it should be noted that in the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "one example" or "some examples" or the like is intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been illustrated and described above, it is to be understood that the above embodiments are exemplary, and the description is only for the purpose of facilitating understanding of the present application and is not intended to limit the present application. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims.
Claims (12)
1. A fault early warning method, characterized in that the method comprises:
acquiring running state data of all target sensors, wherein all the target sensors are similar sensors;
monitoring and early warning all the target sensors according to the running state data through a fault early warning model;
the fault early warning model is generated according to the operation state data of a plurality of similar sensors of the target sensor.
2. The method of claim 1, wherein the step of generating the fault warning model comprises:
acquiring operation state data of the plurality of sensors of the same type;
acquiring an original state data difference sequence according to the running state data;
acquiring a window characteristic value difference sequence according to the running state data;
and generating the fault early warning model according to the original state data difference sequence and the window characteristic value difference sequence.
3. The method of claim 1, wherein the plurality of homogeneous sensors are all sensors that have not historically failed.
4. The method of claim 2, further comprising, after said obtaining operational status data for a plurality of homogeneous sensors:
and filtering the operation state data of the plurality of sensors of the same type.
5. The method of claim 2, wherein generating the fault pre-warning model from the raw state data difference sequence and the window feature value difference sequence comprises:
acquiring an early warning threshold interval and a difference value time sequence according to the original state data difference sequence and the window characteristic value difference sequence;
performing stationarity analysis on the difference value time sequence to obtain an analysis result;
acquiring historical fault data of the same type of sensors which have faults;
and generating a burst fault early warning model according to the original state data difference sequence, the window characteristic value difference sequence and the early warning threshold interval, or generating a gradual fault early warning model according to the analysis result and the historical fault data.
6. The method of claim 1, wherein if the fault early warning model is an emergency fault early warning model, the monitoring and early warning of all the target sensors according to the operating state data by the fault early warning model comprises:
acquiring an original state data difference value and a window characteristic value difference value under a current time window from the running state data of all the target sensors;
carrying out abnormity judgment on the difference value of the original state data in the current time window and the difference values of the window characteristic values of a plurality of continuous time windows;
and when judging that the current time window has abnormal state difference data or the continuous time windows have abnormal window characteristic values, early warning is carried out.
7. The method of claim 6, wherein the determining the anomaly of the raw state data difference value in the current time window comprises:
acquiring the number of early warning pieces with the original state data difference value not within the early warning threshold interval under the current time window;
and if the number of the early warning pieces is not less than the preset number of the early warning pieces, determining that abnormal state difference data exists in the current time window.
8. The method according to claim 6, wherein the performing an anomaly determination on the window eigenvalue difference values of the consecutive time windows comprises:
if the window characteristic value difference value under the current time window is not within the early warning threshold interval, the characteristic value of the current time window is abnormal;
and if the number of the windows with the abnormal characteristic values continuously appears is not less than the preset number of the abnormal windows, determining that the abnormal window characteristic values exist in the subsequent continuous time windows.
9. The method according to claim 1, wherein if the fault early warning model is a gradual-change fault early warning model, the monitoring and early warning of all the target sensors according to the operating state data by the fault early warning model comprises:
acquiring the fault probability of the sensors of the same type according to the running state data of all the target sensors;
and when the fault probability is not less than a preset early warning probability threshold value, early warning is carried out.
10. A fault warning device, comprising:
the acquisition module is used for acquiring the running state data of all target sensors, wherein all the target sensors are similar sensors;
the early warning module is used for monitoring and early warning all the target sensors according to the running state data through a fault early warning model;
and the generating module is used for generating the fault early warning model according to the running state data of a plurality of similar sensors of the target sensor.
11. A storage medium storing a computer program which, when executed by one or more processors, implements a fault pre-warning method as claimed in any one of claims 1 to 9.
12. An electronic device comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the memory and the processor are communicatively connected to each other, and when the computer program is executed by the processor, the fault pre-warning method according to any one of claims 1 to 9 is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210451033.2A CN114936675A (en) | 2022-04-26 | 2022-04-26 | Fault early warning method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210451033.2A CN114936675A (en) | 2022-04-26 | 2022-04-26 | Fault early warning method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114936675A true CN114936675A (en) | 2022-08-23 |
Family
ID=82862694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210451033.2A Pending CN114936675A (en) | 2022-04-26 | 2022-04-26 | Fault early warning method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114936675A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115817178A (en) * | 2022-11-14 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Fault early warning method and device, battery, vehicle and storage medium |
| CN116399402A (en) * | 2023-04-18 | 2023-07-07 | 南京晓庄学院 | Fault early warning system of wireless sensor for ecological environment monitoring |
| CN116520755A (en) * | 2023-06-29 | 2023-08-01 | 深圳东原电子有限公司 | Automatic production line monitoring and early warning method and system for sound equipment |
| CN117132266A (en) * | 2023-10-25 | 2023-11-28 | 山东四季汽车服务有限公司 | Block chain-based automobile service security guarantee method and system |
-
2022
- 2022-04-26 CN CN202210451033.2A patent/CN114936675A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115817178A (en) * | 2022-11-14 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Fault early warning method and device, battery, vehicle and storage medium |
| CN116399402A (en) * | 2023-04-18 | 2023-07-07 | 南京晓庄学院 | Fault early warning system of wireless sensor for ecological environment monitoring |
| CN116399402B (en) * | 2023-04-18 | 2024-01-23 | 南京晓庄学院 | Fault early warning system of wireless sensor for ecological environment monitoring |
| CN116520755A (en) * | 2023-06-29 | 2023-08-01 | 深圳东原电子有限公司 | Automatic production line monitoring and early warning method and system for sound equipment |
| CN116520755B (en) * | 2023-06-29 | 2023-09-26 | 深圳东原电子有限公司 | Automatic production line monitoring and early warning method and system for sound equipment |
| CN117132266A (en) * | 2023-10-25 | 2023-11-28 | 山东四季汽车服务有限公司 | Block chain-based automobile service security guarantee method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114936675A (en) | Fault early warning method and device, storage medium and electronic equipment | |
| CN107426013B (en) | Equipment information monitoring method, device and system | |
| JP2003526859A5 (en) | ||
| CN111460392B (en) | Magnetic suspension train and suspension system fault detection method and system thereof | |
| CN109088775B (en) | Abnormity monitoring method and device and server | |
| US9524223B2 (en) | Performance metrics of a computer system | |
| CN111353911A (en) | Power equipment operation and maintenance method, system, equipment and storage medium | |
| CN105450454A (en) | Service monitoring and warning method and device | |
| CN110808864A (en) | Communication early warning method, device and system | |
| CN112285478A (en) | Method and device for detecting vehicle quiescent current, medium, equipment and vehicle | |
| CN113723338A (en) | Sensor abnormality detection method, sensor abnormality detection device, and computer-readable storage medium | |
| CN112532435A (en) | Operation and maintenance method, operation and maintenance management platform, equipment and medium | |
| JP6718367B2 (en) | Judgment system, judgment method, and program | |
| CN111400114A (en) | Deep recursion network-based big data computer system fault detection method and system | |
| CN115878598A (en) | Monitoring data processing method, electronic device and storage medium | |
| KR101960755B1 (en) | Method and apparatus of generating unacquired power data | |
| KR20160062259A (en) | Method, system and computer readable medium for managing abnormal state of vehicle | |
| CN112905463B (en) | Software test monitoring method and device, electronic equipment and readable storage medium | |
| CN116448219A (en) | Oil level abnormality detection method, apparatus, device, and computer-readable storage medium | |
| CN116108394A (en) | Industrial control system flow abnormality detection method, device and medium | |
| JPS61228501A (en) | Method for deciding treatment of plant abnormality | |
| CN115471968A (en) | Cable burglar alarm | |
| KR101462229B1 (en) | Integrated data merging unit | |
| KR101971553B1 (en) | Device management system and method based on Internet Of Things | |
| CN112579665A (en) | Energy equipment control method and device and energy equipment |
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 |