CN105743595A - Fault early warning method and device for medium and short wave transmitter - Google Patents
Fault early warning method and device for medium and short wave transmitter Download PDFInfo
- Publication number
- CN105743595A CN105743595A CN201610214907.7A CN201610214907A CN105743595A CN 105743595 A CN105743595 A CN 105743595A CN 201610214907 A CN201610214907 A CN 201610214907A CN 105743595 A CN105743595 A CN 105743595A
- Authority
- CN
- China
- Prior art keywords
- data
- transmitter
- cycle
- fault
- probability
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H20/00—Arrangements for broadcast or for distribution combined with broadcast
- H04H20/12—Arrangements for observation, testing or troubleshooting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/10—Monitoring; Testing of transmitters
- H04B17/15—Performance testing
- H04B17/18—Monitoring during normal operation
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The invention provides a fault early warning method and device for a medium and short wave transmitter. The method comprises the following steps: obtaining historical operation data of the transmitter before the ith operation period and real-time operation data of the transmitter within the ith operation period, wherein the historical operation data comprises normal data and fault data, and i is an integer larger than or equal to 1; determining a fault judgment model of the transmitter within the ith operation period according to the normal data and the fault data; determining a fault probability of the transmitter within the ith operation period according to the fault judgment model of the transmitter within the ith operation period and the real-time operation data of the transmitter within the ith operation period; and carrying out fault early warning on the transmitter according to the fault probability. By adopting the fault early warning method and device for the medium and short wave transmitter provided by the invention, the fault of the transmitter can be monitored automatically, and the fault early warning is carried out in advance.
Description
Technical field
The present embodiments relate to field of broadcast televisions, particularly relate to a kind of intermediate waves transmitter failure method for early warning and device.
Background technology
The main flow equipment that the large-scale broadcast signal transmission station adopts at present is high-power intermediate waves transmitter.Along with transmitter runs the increase of time, under complicated inside and outside running environment impact, unavoidably there will be the situation that equipment performance declines, fault rate increases.And the broadcast transmission station requires extremely strict for the stable operation launching equipment, therefore, need transmitter running status is carried out Intelligent real-time monitoring, judge the running status of transmitter in advance, to realize intervening with artificial technology for broadcasting to switch rapidly before breaking down, it is ensured that normally complete broadcast task.
In prior art, generally adopt the index value in Automatic monitoring systems collection and record and transmitter real time execution process, and corresponding index value is sent to multiple dial plate shows.The running status of transmitter is judged by plant maintenance personnel according to the indices numerical value of display on dial plate.
But, owing to high-power intermediate waves broadcast transmitter Inner Constitution is extremely complex, the reason causing fault is also intricate, if plant maintenance personnel do not possess extremely strong professional skill and maintenance experience, it is difficult to according to the index value of display on single dial plate, the running status of transmitter apparatus is carried out accurate anticipation.
Summary of the invention
The embodiment of the present invention provides a kind of intermediate waves transmitter failure method for early warning and device, in order to solve the problem that broadcast transmitter fault pre-alarming mode of the prior art can not accurately judge broadcast transmitter fault.
The embodiment of the present invention provides a kind of intermediate waves transmitter failure method for early warning, including:
Obtaining transmitter history data before i-th cycle of operation and the real-time running data in described i-th cycle of operation, described history data includes normal data and fault data；I is the integer be more than or equal to 1；
The described transmitter breakdown judge model at i-th cycle of operation is determined according to described normal data and fault data；
Real-time running data according to the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation；
According to described probability of malfunction, described transmitter is carried out fault pre-alarming.
In another embodiment, described determine transmitter failure judgment models according to described normal data and fault data, including:
Described normal data and described fault data are normalized；
Described normal data after normalized and described fault data are ranked up, and described normal data and fault data after sequence are carried out equidistant sampling；
It is modeled by the sample of the logistic regression analysis described normal data to obtaining after equidistant sampling and described abnormal data, it is determined that described transmitter failure judgment models.
In another embodiment, the described real-time running data according to described transmitter failure judgment models and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation, including:
According to
Determining described transmitter probability of malfunction P (z) in described i-th cycle of operation, wherein, β represents the mapping relations of described normal data and described fault data, and z represents the real-time running data of described i-th cycle of operation.
In another embodiment, described method also includes:
Real time data according to the described i-th cycle of operation obtained updates the described transmitter breakdown judge model at i+1 cycle of operation.
In another embodiment, described according to described probability of malfunction, described transmitter is carried out fault pre-alarming, including:
When described probability of malfunction is higher than the first predetermined threshold value, described probability of malfunction is higher than the number of times of described first predetermined threshold value more than Second Threshold, and adjacent twice probability of malfunction higher than described first predetermined threshold value when there is the interval between the moment less than three threshold values, generate alarm logging.
The embodiment of the present invention also provides for a kind of intermediate waves transmitter failure prior-warning device, including:
Acquisition module, for obtaining the real-time running data in transmitter history data before i-th cycle of operation and described i-th cycle of operation；
Modeling analysis module, for determining the described transmitter breakdown judge model at i-th cycle of operation according to described normal data and fault data；I is the integer be more than or equal to 1；
Computing module, for determining described transmitter probability of malfunction in described i-th cycle of operation according to the real-time running data of the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation；
Warning module, for carrying out fault pre-alarming according to described probability of malfunction and default early warning rule to described transmitter.
In another embodiment, described modeling analysis module, specifically for:
Described normal data and described fault data are normalized；
Described normal data after normalized and described fault data are ranked up, and described normal data and fault data after sequence are carried out equidistant sampling；
It is modeled by the sample of the logistic regression analysis described normal data to obtaining after equidistant sampling and described abnormal data, it is determined that described transmitter failure judgment models.
In another embodiment, described computing module, specifically for:
According to
Determining described transmitter probability of malfunction in described i-th cycle of operation, wherein, β represents the mapping relations of described normal data and described fault data, and z represents the real-time running data of described i-th cycle of operation.
In another embodiment, described modeling analysis module, it is additionally operable to:
Real time data according to the described i-th cycle of operation obtained updates the described transmitter breakdown judge model at i+1 cycle of operation.
In another embodiment, described warning module, specifically for:
When described probability of malfunction is higher than the first predetermined threshold value, described probability of malfunction is higher than the number of times of described first predetermined threshold value more than Second Threshold, and adjacent twice probability of malfunction higher than described first predetermined threshold value when there is the interval between the moment less than three threshold values, generate alarm logging.
The intermediate waves transmitter failure method for early warning of embodiment of the present invention offer and device, by obtaining transmitter history data before i-th cycle of operation and the real-time running data in described i-th cycle of operation, determine the described transmitter breakdown judge model at i-th cycle of operation according to described historical data；And the real-time running data according to the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation；Finally according to described probability of malfunction, described transmitter is carried out fault pre-alarming.Adopt the intermediate waves transmitter failure method for early warning that the embodiment of the present invention provides, can determine, according to the real-time running data of transmitter and breakdown judge model, the probability that transmitter breaks down, in advance the failure condition of described transmitter be made early warning according to described probability of malfunction.Avoid prior art artificially judges, according to transmitter service data, the situation that transmitter running status causes forecasting inaccuracy true..
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, introduce the accompanying drawing used required in embodiment or description of the prior art is done one simply below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The overall framework figure of Fig. 1 embodiment of the present invention intermediate waves broadcast transmitter fault early warning system；
Fig. 2 is the schematic flow sheet of embodiment of the present invention intermediate waves broadcast transmitter fault pre-alarming；
Fig. 3 is the schematic flow sheet that embodiment of the present invention intermediate waves transmitter failure method for early warning determines transmitter failure judgment models；
Fig. 4 is the schematic diagram of the similarity curve that embodiment of the present invention intermediate waves transmitter failure method for early warning generates；
Fig. 5 is the fault pre-alarming accuracy statistical result schematic diagram of embodiment of the present invention intermediate waves transmitter failure method for early warning；
Fig. 6 is the structural representation of embodiment of the present invention intermediate waves transmitter failure prior-warning device.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
Fig. 1 is the overall framework figure of embodiment of the present invention intermediate waves broadcast transmitter fault early warning system.
Referring to Fig. 1, embodiment of the present invention intermediate waves broadcast transmitter fault early warning system includes: calculated off line platform 10, in real time calculate platform 20 and can interactive user interface 30.Described calculated off line platform includes data memory module (Hadoop) 11 and modeling analysis module 12.Described real-time calculating platform includes real-time computing module (storm) 21 and document database (Mongodb) 22.The external data source of native system comes from the transmitter business datum switching centre launching the station, wherein comprises transmitting equipment operating data.The Computational frame of system adopts Lambda framework, manages real-time Computational frame and calculated off line framework simultaneously.Basic data passes through HTML (Hypertext Markup Language) application programming interface (HyperTextTransferProtocolApplicationProgrammingInterface, it is called for short HTTPAPI) after 40 entrance systems, carry out preliminary identification filtration through data acquisition module 50, recorded in message queue (Kafka).After data enter Kafka, it is simultaneously in described data memory module 11 and described real-time computing module 21 is respectively used to calculated off line and calculates in real time.
Data are written to data memory module 11 described in described data memory module 11 via described data acquisition module 50 and store.Data at described data memory module 11, it is possible to inquire about framework etc. by programming model MapReduce Computational frame and Hive and complete the work such as data operation process.Described modeling analysis module 12 is entered through normalized data.Described modeling analysis module 12 adopts logistic regression modeling analysis algorithm that the transmitter service data of input is analyzed, it is determined that the breakdown judge model of transmitter exports model text.Text, after model transformer 60 is changed, is input in described real-time computing module 21.Along with the continuous accumulation of transmitter service data, model regular update modal analysis results.Regularly the result after renewal is input in described real-time computing module 21 by described model transformer 60, continues transmitter service data is calculated in real time according to the breakdown judge model after updating for described real-time computing module 21.Additionally, if the user while empirical rule setting can be have changed by interactive user interface 30 by described, a message informing can be produced in system, arrive described modeling analysis module 12 via described document database 22, according to new rule settings model algorithm, regenerate data results.It is then passed through described model transformer 60, in described real-time computing module, updates corresponding content.
After transmitting equipment operating data arrives described real-time computing module 21 via described data acquisition module 50, message can complete the process of streaming, completes response in real time and processes or calculate.Analysis, statistics task on described real-time computing module 21 carry out concrete computing according to the result of model analysis, and result of calculation exports in described document database 22.
Described document database 22 is a document object data base, different and traditional Relational DataBase, it is a kind of unstructured search language (NotOnlyStructuredQueryLanguage, it is called for short NoSQL) data base, it does not have the concept of " OK " of traditional database, each data is one " document ", and a document is the data of a json form.In systems, the output database that described document database 22 will calculate in real time as described real-time computing module 21, described real-time computing module 21 reads the data of Real-time Collection from described data acquisition module 50, after completing calculating, result of calculation exports described document database 22 and stores.User can obtain real-time accounting report by reading described document database 22 result.
Described real-time computing module 21 exports the real-time result of calculation in described document database 22, the real-time report page in Operation and Maintenance Center read, and be shown to described can on interactive user interface 30.Described can mainly provide three functions by interactive user interface 30: the setting of the visual presentation of equipment running status, empirical rule, history run status poll etc..Can the holistic health of Real Time Observation transmitter write music line in Web page, when there is unit exception, according to abnormal different brackets, produce Multi-stage alarming respectively, for instance: health degree moderate alarm (yellow), health degree severe alarm (orange), transmitter failure early warning (redness).
Fig. 2 is the schematic flow sheet of embodiment of the present invention intermediate waves broadcast transmitter fault pre-alarming.
Refer to Fig. 2, the intermediate waves transmitter failure method for early warning that the embodiment of the present invention provides, including:
S101: obtaining transmitter history data before i-th cycle of operation and the real-time running data in described i-th cycle of operation, described history data includes normal data and fault data；I is the integer be more than or equal to 1；
Specifically, described history data is came into the transmitter service data being stored in described data memory module 11 before described i-th cycle of operation.
Before the normal data in history data before the described i-th cycle of operation of described acquisition, it is necessary to the data entering described intermediate waves broadcast transmitter fault early warning system are carried out.Concrete data cleansing mode is as follows:
Read the data after cleaning filing in described data memory module 11, disturb data and fault data according to data cleansing redundant rule elimination, be all healthy service data with what ensure entrance model analysis.The rule settings of abnormal data is based on the service chart of Broadcast and TV system different transmitters, and broadcasting and TV rules and regulations (" before and after the transmitter pilot tone phase three minutes, warning of breaking down belongs to normal condition ").
Data cleansing rule settings is specific as follows:
1, broadcasting and TV return data is return with the second by regulation, but occasional exists data back less than, or blocking of causing of a variety of causes.If during data truncation, transmitter breaks down, data model distortion can be caused.So setting rule time to chopping more than 5 minutes namely 300 seconds within the properly functioning cycle in advance, by a period of state data deletion before point of cut-off.
2, only retaining state in broadcasting and TV return data is 11 (operations) or the data of 30 (faults).
3, for guaranteeing the reliability of service data, therefore state is run discontented 2 minute datas and also deletes.
4, for guaranteeing the speed of data platform computing, 60 day data nearest from the present are only retained.
5, for guaranteeing speed and the accuracy that model sets up, the record of identical running status is only retained one, all the other deletions.
If 6 break down, trouble point to this (my god) the earliest run duration data all delete, it is ensured that retain normal data as far as possible.
After data are carried out by above steps, described normal data can be obtained.The data that state is high frequency broadcast that fault occurs first 3 minutes are left fault data.Two sample sets obtained after cleaning are " normal data set " that include described normal data and include " the fault data collection " of described fault data.
S102: determine the described transmitter breakdown judge model at i-th cycle of operation according to described normal data and fault data；
Specifically, described determine transmitter failure judgment models according to described normal data and fault data, including:
Described normal data and described fault data are normalized；
Described normal data after normalized and described fault data are ranked up, and described normal data and fault data after sequence are carried out equidistant sampling；
It is modeled by the sample of the logistic regression analysis described normal data to obtaining after equidistant sampling and described abnormal data, it is determined that described transmitter failure judgment models.
Fig. 3 is the schematic flow sheet that embodiment of the present invention intermediate waves transmitter failure method for early warning determines transmitter failure judgment models.
Refer to Fig. 3, in implementing process, it is determined that transmitter failure judgment models comprises the following steps:
1, the equidistant sampling of data
First the normal data after screening and fault data are ranked up, the data after sequence are carried out equidistant sampling, with smallest sample collection 20% for extracting radix.The method using equidistant sampling guarantees that sample data is minimum spacing, so that it is guaranteed that sampling is uniform.
Sort algorithm is based on Euclid norm principle, is undertaken square by all fields, is added and then carries out evolution again.Equal in a disguised form multidimensional data being integrated into one-dimensional data, then it is ranked up.
Sort algorithm formula is:
Wherein, x represents a field in each row or every column data, and n represents the quantity of the field in each row or every column data.
Such as normal sample set sum 100, fault sample set sum 50, that unification is respectively extracted 20 in the way of equidistant sampling according to normal sample set and is modeled.
Sampling algorithm is by circulation operation, and setting one " initial point " is 1, and at " initial point+extraction interval " one point of random choose within the scope of this, then " initial point " is updated to " initial point+extraction interval ".Till being drawn into the extraction quantity of needs always.
2, the normalized of variable
All data are normalized, the dimension relation between uniform variable.Noticing that in data, Partial Variable value is likely to unchanged, such data normalization will be failed, so needing to delete these part data further.
Transmitter service data mostly is discrete type, therefore adopts zero-mean standardization.
Normalization formula is:
Wherein, z represents the normalization result of the service data of each cycle of operation, x represents each row or each column service data value after sort algorithm processes, μ represents the average of all service datas, and σ represents the variance between described each row or each column service data value and the average of described service data after sort algorithm processes.
3, logistic regression judges transmitter failure probability
Logistic regression is a kind of generalized linear regression, is the conventional mathematical modeies of a kind of two classification.Embodiment of the present invention intermediate waves transmitter failure method for early warning is basic to be predicted as, and purpose is that to judge that the probability that transmitter breaks down has much.
Logic-based returns principle, the set of data samples of two equivalent is modeled, and generates the fault pre-alarming model of transmitter, and the result of described fault pre-alarming model is every time using probability as output.
S103: determine described transmitter probability of malfunction in described i-th cycle of operation according to the real-time running data of the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation.
Specifically, the described real-time running data according to described transmitter failure judgment models and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation, including: according to
Determine described transmitter probability of malfunction P (z) in described i-th cycle of operation, wherein, z represents the real-time running data of described i-th cycle of operation, β represents the mapping relations of described normal data and described fault data, is obtain through training according to the normal data in a large amount of historical datas and fault data.
S104: described transmitter is carried out fault pre-alarming according to described probability of malfunction and default early warning rule.
Specifically, described default early warning rule can be: when described probability of malfunction is higher than the first predetermined threshold value, described probability of malfunction is higher than the number of times of described first predetermined threshold value more than Second Threshold, and adjacent twice probability of malfunction higher than described first predetermined threshold value when there is the interval between the moment less than three threshold values, generate alarm logging.
Concrete prealarming process is as follows:
1, similarity curve is generated
Fig. 4 is the schematic diagram of the similarity curve that embodiment of the present invention intermediate waves transmitter failure method for early warning generates.
Referring to Fig. 4, each real time data of transmitter apparatus calculates such as through logistic regression and obtains the possible probability that a fault occurs.Along with the operation of equipment, real-time running data continually enters in model, thus obtaining the similarity curve of transmitter apparatus running status.This similarity curve out, features the instant health status of transmitting equipment with visual mode real-time exhibition in Web page.
2, exceptionization normality filters
Often there is the situation of sporadic condition of instant error in transmitter, but just no longer occurs abnormal sign afterwards.This situation tends not to affect normal broadcast, and for a kind of normality of transmitter, this phenomenon is referred to as the exception normality in model.When monitoring transmitter health degree, it is necessary to this exceptionization normality is filtered, otherwise can be greatly increased the false alarm rate of system.
The filtering rule of exceptionization normality is: user can input the parameters such as " early warning line ", " warning cumulative frequency ", " alarm interval duration " in Web page according to plant maintenance experience.Only when health degree (similarity that model calculates) is lower than " early warning line ", " alarm interval duration " less than M moment and " warning cumulative frequency " more than n times time, system just can generate an alarm logging.Alarm logging comprises the variablees such as early warning time started, advanced warning grade, early warning persistent period.
Such as setting " warning cumulative frequency " is 10, and " alarm interval duration " was 60 (seconds), and " early warning line " is 0.1.So after health degree value is lower than 0.1, alarm times adds 1 and adds up to 1.Check and in this time abnormal latter 60 seconds, whether also have the situation lower than 0.1 to occur.Were it not for appearance, alarm times adds up to 1, then this time do not generate alarm logging.
If again occurring when the 59th second that the situation lower than 0.1 occurs, alarm times adds 1 and adds up to 2, continues to check in ensuing 60 seconds whether the situation lower than " early warning line " occurs again.If being accumulated to 10 times, then generate alarm logging.
3, classifying alarm
Transmitter holistic health degree can be carried out the warning of three ranks, respectively: health degree moderate alarm (yellow), health degree severe warning (orange), transmitter failure early warning (redness).The respectively corresponding different rule settings of reporting to the police of these three grade, i.e. different grades of " early warning line ", " warning cumulative frequency ", the parameter setting such as " alarm interval duration ".Adjustable classifying alarm, meets broadcasting and TV side's business demand to fault pre-alarming management work.
On the basis of above-described embodiment, further, in order to ensure in i+1 the cycle, the judgement of fault pre-alarming is more accurate, described method also includes:
Real time data according to the described i-th cycle of operation obtained updates the described transmitter breakdown judge model at i+1 cycle of operation.
Specifically, after described i-th cycle of operation terminates, namely the service data of described i-th cycle of operation becomes historical data, and storage is in described data memory module 11.Described fault pre-alarming model is updated by described modeling analysis module 12 according to the latest data after adding the service data of i-th cycle of operation, according to the fault pre-alarming model after updating, the data of i+1 cycle of operation are calculated in real time, it is determined that described transmitter is at the probability of malfunction of described i+1 cycle of operation.
Fig. 5 is the fault pre-alarming accuracy statistical result schematic diagram of embodiment of the present invention intermediate waves transmitter failure method for early warning.
Refer to Fig. 5, added up within one month, after system provides fault pre-alarming, the probability of equipment generation physical fault within 24 hours, 2 days, 3 days.When the alarm threshold value difference set, the sensitivity of system is different.Alarm threshold value is more low, and early warning number of times is more few, and early warning accuracy is more high, but false dismissed rate also can increase accordingly.Therefore, it is not that threshold value sets more low more good, it should consider the balance between accuracy and false dismissed rate, in accuracy tolerance interval, reduces false dismissed rate as far as possible.According to adopting embodiment of the present invention intermediate waves fault early warning method to carry out the statistics of the accuracy corresponding to early warning under various threshold conditions, when the threshold value of warning of health degree curve is set as 0.00008, if there are unusual fluctuations in transmitter, model provides fault pre-alarming, in 24 hours, the ratio of device fails is 58% subsequently, the ratio broken down in 2 days is 89%, and the ratio broken down in 3 days is 97%.This result can meet the business demand of the equipment control of Radio, Film and Television Administration preferably.
The intermediate waves transmitter failure method for early warning that the embodiment of the present invention provides, by obtaining transmitter history data before i-th cycle of operation and the real-time running data in described i-th cycle of operation, determine the described transmitter breakdown judge model at i-th cycle of operation according to described historical data；And the real-time running data according to the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation；Finally according to described probability of malfunction, described transmitter is carried out fault pre-alarming.Adopt the intermediate waves transmitter failure method for early warning that the embodiment of the present invention provides, can determine, according to the real-time running data of transmitter and breakdown judge model, the probability that transmitter breaks down, in advance the failure condition of described transmitter be made early warning according to described probability of malfunction.Avoid prior art artificially judges, according to transmitter service data, the situation that transmitter running status causes forecasting inaccuracy true.
Fig. 6 is the structural representation of embodiment of the present invention intermediate waves transmitter failure prior-warning device.Referring to Fig. 3, the intermediate waves transmitter failure prior-warning device device that the embodiment of the present invention provides at least includes:
Acquisition module 610, for obtaining the real-time running data in transmitter history data before i-th cycle of operation and described i-th cycle of operation；
Modeling analysis module 620, for determining the described transmitter breakdown judge model at i-th cycle of operation according to described normal data and fault data；I is the integer be more than or equal to 1；
Computing module 630, for determining described transmitter probability of malfunction in described i-th cycle of operation according to the real-time running data of the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation；
Warning module 640, for carrying out fault pre-alarming according to described probability of malfunction and default early warning rule to described transmitter.
Described modeling analysis module 620, specifically for:
Described normal data and described fault data are normalized；
Described normal data after normalized and described fault data are ranked up, and described normal data and fault data after sequence are carried out equidistant sampling；
It is modeled by the sample of the logistic regression analysis described normal data to obtaining after equidistant sampling and described abnormal data, it is determined that described transmitter failure judgment models.
Described computing module 630, specifically for:
According to
Determining described transmitter probability of malfunction in described i-th cycle of operation, wherein, β represents the mapping relations of described normal data and described fault data, and z represents the real-time running data of described i-th cycle of operation.
Described modeling analysis module 620, is additionally operable to:
Real time data according to the described i-th cycle of operation obtained updates the described transmitter breakdown judge model at i+1 cycle of operation.
Described warning module 640, specifically for:
When described probability of malfunction is higher than the first predetermined threshold value, described probability of malfunction is higher than the number of times of described first predetermined threshold value more than Second Threshold, and adjacent twice probability of malfunction higher than described first predetermined threshold value when there is the interval between the moment less than three threshold values, generate alarm logging.
The intermediate waves transmitter failure prior-warning device that the embodiment of the present invention provides, obtained transmitter history data before i-th cycle of operation and the real-time running data in described i-th cycle of operation by acquisition module, modeling analysis module determines the described transmitter breakdown judge model at i-th cycle of operation according to described historical data；Computing module determines described transmitter probability of malfunction in described i-th cycle of operation according to the real-time running data of the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation；Finally according to described probability of malfunction, described transmitter is carried out fault pre-alarming by warning module.Adopt the intermediate waves transmitter failure method for early warning that the embodiment of the present invention provides, can determine, according to the real-time running data of transmitter and breakdown judge model, the probability that transmitter breaks down, in advance the failure condition of described transmitter be made early warning according to described probability of malfunction.Avoid prior art artificially judges, according to transmitter service data, the situation that transmitter running status causes forecasting inaccuracy true.
Specifically, the shape library extraction element that the embodiment of the present invention provides is for performing the intermediate waves transmitter failure method for early warning that said method embodiment provides, and it realizes principle and technique effect is similar, does not repeat them here.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each embodiment of the method can be completed by the hardware that programmed instruction is relevant.Aforesaid program can be stored in the read/write memory medium of a computer, mobile phone or other portable units.This program upon execution, performs to include the step of above-mentioned each embodiment of the method；And aforesaid storage medium includes: the various media that can store program code such as ROM, RAM, magnetic disc or CDs.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit；Although the present invention being described in detail with reference to foregoing embodiments, it will be understood by those within the art that: the technical scheme described in foregoing embodiments still can be modified by it, or wherein some or all of technical characteristic is carried out equivalent replacement；And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (10)
1. an intermediate waves transmitter failure method for early warning, it is characterised in that including:
Obtaining transmitter history data before i-th cycle of operation and the real-time running data in described i-th cycle of operation, described history data includes normal data and fault data；I is the integer be more than or equal to 1；
The described transmitter breakdown judge model at i-th cycle of operation is determined according to described normal data and fault data；
Real-time running data according to the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation；
According to described probability of malfunction, described transmitter is carried out fault pre-alarming.
2. method according to claim 1, it is characterised in that described determine transmitter failure judgment models according to described normal data and fault data, including:
Described normal data and described fault data are normalized；
Described normal data after normalized and described fault data are ranked up, and described normal data and fault data after sequence are carried out equidistant sampling；
It is modeled by the sample of the logistic regression analysis described normal data to obtaining after equidistant sampling and described abnormal data, it is determined that described transmitter failure judgment models.
3. method according to claim 1, it is characterised in that the described real-time running data according to described transmitter failure judgment models and described i-th cycle of operation determines described transmitter probability of malfunction in described i-th cycle of operation, including:
According to
Determining described transmitter probability of malfunction P (z) in described i-th cycle of operation, wherein, β represents the mapping relations of described normal data and described fault data, and z represents the real-time running data of described i-th cycle of operation.
4. the method according to any one of claim 1-3, it is characterised in that also include:
Real time data according to the described i-th cycle of operation obtained updates the described transmitter breakdown judge model at i+1 cycle of operation.
5. the method according to any one of claim 1-3, it is characterised in that described according to described probability of malfunction, described transmitter is carried out fault pre-alarming, including:
When described probability of malfunction is higher than the first predetermined threshold value, described probability of malfunction is higher than the number of times of described first predetermined threshold value more than Second Threshold, and adjacent twice probability of malfunction higher than described first predetermined threshold value when there is the interval between the moment less than three threshold values, generate alarm logging.
6. an intermediate waves transmitter failure prior-warning device, it is characterised in that including:
Acquisition module, for obtaining the real-time running data in transmitter history data before i-th cycle of operation and described i-th cycle of operation；
Modeling analysis module, for determining the described transmitter breakdown judge model at i-th cycle of operation according to described normal data and fault data；I is the integer be more than or equal to 1；
Computing module, for determining described transmitter probability of malfunction in described i-th cycle of operation according to the real-time running data of the described transmitter breakdown judge model at i-th cycle of operation and described i-th cycle of operation；
Warning module, for carrying out fault pre-alarming according to described probability of malfunction and default early warning rule to described transmitter.
7. device according to claim 6, it is characterised in that described modeling analysis module, specifically for:
Described normal data and described fault data are normalized；
Described normal data after normalized and described fault data are ranked up, and described normal data and fault data after sequence are carried out equidistant sampling；
It is modeled by the sample of the logistic regression analysis described normal data to obtaining after equidistant sampling and described abnormal data, it is determined that described transmitter failure judgment models.
8. device according to claim 6, it is characterised in that described computing module, specifically for:
According to
Determining described transmitter probability of malfunction in described i-th cycle of operation, wherein, β represents the mapping relations of described normal data and described fault data, and z represents the real-time running data of described i-th cycle of operation.
9. the device according to any one of claim 6-8, it is characterised in that described modeling analysis module, is additionally operable to:
Real time data according to the described i-th cycle of operation obtained updates the described transmitter breakdown judge model at i+1 cycle of operation.
10. the device according to any one of claim 6-8, it is characterised in that described warning module, specifically for:
When described probability of malfunction is higher than the first predetermined threshold value, described probability of malfunction is higher than the number of times of described first predetermined threshold value more than Second Threshold, and adjacent twice probability of malfunction higher than described first predetermined threshold value when there is the interval between the moment less than three threshold values, generate alarm logging.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610214907.7A CN105743595A (en) | 2016-04-08 | 2016-04-08 | Fault early warning method and device for medium and short wave transmitter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610214907.7A CN105743595A (en) | 2016-04-08 | 2016-04-08 | Fault early warning method and device for medium and short wave transmitter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105743595A true CN105743595A (en) | 2016-07-06 |
Family
ID=56252972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610214907.7A Pending CN105743595A (en) | 2016-04-08 | 2016-04-08 | Fault early warning method and device for medium and short wave transmitter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105743595A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108199795A (en) * | 2017-12-29 | 2018-06-22 | 北京百分点信息科技有限公司 | The monitoring method and device of a kind of equipment state |
| CN108765017A (en) * | 2018-05-31 | 2018-11-06 | 浪潮软件股份有限公司 | A kind of processing method and processing device of warning data |
| CN110537347A (en) * | 2017-04-20 | 2019-12-03 | 奥迪股份公司 | For the method and central computer of the probability of malfunction of radio net to be detected and determined |
| CN110781220A (en) * | 2019-09-20 | 2020-02-11 | 江苏欣皓测试技术有限公司 | Fault early warning method and device, storage medium and electronic equipment |
| CN110908956A (en) * | 2019-11-19 | 2020-03-24 | 许继集团有限公司 | Information protection main station system and fault information filing method thereof |
| CN111899372A (en) * | 2020-07-06 | 2020-11-06 | 唐山昌宏科技有限公司 | Man-machine interactive management system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270271A (en) * | 2011-05-03 | 2011-12-07 | 北京中瑞泰科技有限公司 | Equipment failure early warning and optimizing method and system based on similarity curve |
| CN102809965A (en) * | 2012-07-30 | 2012-12-05 | 燕山大学 | Fault early warning method for hydraulic equipment based on fault frequent pattern |
| US20140333447A1 (en) * | 2013-05-10 | 2014-11-13 | Cheng Uei Precision Industry Co., Ltd. | Failure alarm system and method of failure alarming thereof |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
-
2016
- 2016-04-08 CN CN201610214907.7A patent/CN105743595A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270271A (en) * | 2011-05-03 | 2011-12-07 | 北京中瑞泰科技有限公司 | Equipment failure early warning and optimizing method and system based on similarity curve |
| CN102809965A (en) * | 2012-07-30 | 2012-12-05 | 燕山大学 | Fault early warning method for hydraulic equipment based on fault frequent pattern |
| US20140333447A1 (en) * | 2013-05-10 | 2014-11-13 | Cheng Uei Precision Industry Co., Ltd. | Failure alarm system and method of failure alarming thereof |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
Non-Patent Citations (3)
| Title |
|---|
| 潘峰: "发射机健康管理和预测性维护系统的设计与实现", 《广播电视信息》 * |
| 白国强: "《网络安全基础 应用与标准 第4版》", 31 January 2011 * |
| 陈昆亮: "汽轮发电机组状态监测与故障预警系统研究", 《CNKI博士学位论文全文库》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110537347A (en) * | 2017-04-20 | 2019-12-03 | 奥迪股份公司 | For the method and central computer of the probability of malfunction of radio net to be detected and determined |
| CN110537347B (en) * | 2017-04-20 | 2023-07-14 | 奥迪股份公司 | Method and central computer for detecting and determining the probability of failure of a radio network |
| CN108199795A (en) * | 2017-12-29 | 2018-06-22 | 北京百分点信息科技有限公司 | The monitoring method and device of a kind of equipment state |
| CN108199795B (en) * | 2017-12-29 | 2019-05-10 | 北京百分点信息科技有限公司 | A kind of monitoring method and device of equipment state |
| CN108765017A (en) * | 2018-05-31 | 2018-11-06 | 浪潮软件股份有限公司 | A kind of processing method and processing device of warning data |
| CN110781220A (en) * | 2019-09-20 | 2020-02-11 | 江苏欣皓测试技术有限公司 | Fault early warning method and device, storage medium and electronic equipment |
| CN110908956A (en) * | 2019-11-19 | 2020-03-24 | 许继集团有限公司 | Information protection main station system and fault information filing method thereof |
| CN111899372A (en) * | 2020-07-06 | 2020-11-06 | 唐山昌宏科技有限公司 | Man-machine interactive management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105743595A (en) | Fault early warning method and device for medium and short wave transmitter | |
| CN108199795B (en) | A kind of monitoring method and device of equipment state | |
| US11403164B2 (en) | Method and device for determining a performance indicator value for predicting anomalies in a computing infrastructure from values of performance indicators | |
| US20170371757A1 (en) | System monitoring method and apparatus | |
| KR20180108446A (en) | System and method for management of ict infra | |
| CN108388503A (en) | Data-base performance monitoring method, system, equipment and computer readable storage medium | |
| CN103761173A (en) | Log based computer system fault diagnosis method and device | |
| US11055717B2 (en) | Below-the-line thresholds tuning with machine learning | |
| CN106656590A (en) | Method and device for processing network equipment alarm message storm | |
| US11307916B2 (en) | Method and device for determining an estimated time before a technical incident in a computing infrastructure from values of performance indicators | |
| CN104158682B (en) | A kind of SDH SDH failure localization method based on contribution degree | |
| CN106708692B (en) | Method and device for establishing filtering alarm model, method and device for filtering alarm and electronic equipment | |
| CN107239388A (en) | A kind of monitoring alarm method and system | |
| CN103746831A (en) | Alarm analysis method, device and system | |
| US20220188280A1 (en) | Machine learning based process and quality monitoring system | |
| CN114267178B (en) | Intelligent operation maintenance method and device for station | |
| US11675643B2 (en) | Method and device for determining a technical incident risk value in a computing infrastructure from performance indicator values | |
| CN104777827A (en) | Method for diagnosing fault of high-speed railway signal system vehicle-mounted equipment | |
| DE112021000370T5 (en) | DATA MONITORING BASED ON MACHINE LEARNING | |
| CN116680113B (en) | Equipment detection implementation control system | |
| CN107332680A (en) | A kind of system monitoring method and device | |
| CN107104848A (en) | Information technology system monitoring method and device | |
| CN117194919A (en) | Production data analysis system | |
| CN205510066U (en) | Well short wave transmitting machine fault early -warning device | |
| CN112347163A (en) | High-dispersion SQL dynamic baseline warning method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160706 |