CN103023719A - Specified transformer acquisition terminal failure diagnosis method based on bayesian network - Google Patents
Specified transformer acquisition terminal failure diagnosis method based on bayesian network Download PDFInfo
- Publication number
- CN103023719A CN103023719A CN2012105109707A CN201210510970A CN103023719A CN 103023719 A CN103023719 A CN 103023719A CN 2012105109707 A CN2012105109707 A CN 2012105109707A CN 201210510970 A CN201210510970 A CN 201210510970A CN 103023719 A CN103023719 A CN 103023719A
- Authority
- CN
- China
- Prior art keywords
- probability
- failure
- acquisition terminal
- factor
- causes
- 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
Images
Abstract
The invention relates to a specified transformer acquisition terminal failure diagnosis method based on a bayesian network. The specified transformer acquisition terminal failure diagnosis method based on the bayesian network is characterized by including the following steps that when a specific failure occurs, all factor materials which can cause the failure are cleared up, then the probability of each factor which can cause the failure is analyzed, the probability of factors causing the failure is calculated according to a bayes formula, the probability of each factor which causes the failure is sequentially solved according to the current probability and the bayes formula, each probability directly or indirectly causing the failure is finally solved, and through comparison, the factor with larger probability is determined to be the reason of the failure. A trial proves that by means of the method, various failure reasons of a specified transformer acquisition terminal can be found out and correspondingly processed, the high accuracy is achieved, and the solving efficiency of the specified transformer acquisition terminal failure can be effectively improved.
Description
Technical field
The present invention relates to a kind of special change acquisition terminal method for diagnosing faults based on Bayesian network.
Background technology
China has begun to occur the development of Automatic meter reading system after the last century the nineties, domestic many research institutions and enterprise put into the research in Automatic meter reading system field one after another.At present, the appearance of our the existing multiple remote centralized meter-reading system of country.
Specially become acquisition terminal as the terminal of remote centralized meter-reading and automatic control, it had both played a kind of effect of data relay, the effect of data buffer storage in remote centralized meter-reading system, played again the effect of automatic control switch on off operating mode.Specially become acquisition terminal and generally be installed in outdoor platform and become near the district, its working condition is except with the hardware device of self and outside the Pass software has, and is also closely bound up with geographical position and the weather conditions of locality.When being in long-range special change acquisition terminal and breaking down, we should consider outside the environmental factor, also will consider the reason of self.Because it is too many specially to become the uncertain factor of acquisition terminal fault, so investigate particularly troublesome.In recent years, the brainstrust of domestic failure diagnosis is constantly gushed out for the diagnostic method of the fault of electric power system, such as expert system, artificial neural net and optimization method etc.In the electric network fault process, because protection or malfunction, tripping and the protection zone of switch such as arrange at the existence of factor, cause the appearance of information uncertainty, when multiple faults or expansion property fault occured, this uncertainty was especially obvious.Simultaneously, because factor affecting such as Automation of Electric Systems degree and communications, complete fault message also is difficult to obtain.
Bayesian network is that a kind of oriented diagram to probabilistic relation of structure Network Based is described, and is applicable to uncertain things and probability sexual behavior thing, is applied to rely on conditionally the decision-making of various control factor.The probability of use theory is processed by the condition between the different knowledge compositions and is correlated with and the uncertainty of generation, is applicable to uncertain and incompleteness object, calculates posterior probability by Bayes' theorem, is applied to rely on conditionally the decision-making of various control factor.The Bayesian network technology is applied to power system failure diagnostic, can remedies preferably the deficiency that above diagnostic techniques exists.
Summary of the invention
The purpose of this invention is to provide a kind of special change acquisition terminal method for diagnosing faults based on Bayesian network, can realize the automation of failure diagnosis and have higher accuracy rate of diagnosis.
A kind of special change acquisition terminal method for diagnosing faults based on Bayesian network, its special feature is, comprise the steps: after concrete fault occurs, put the factor material that all can cause that this fault occurs in order, then analyze the probability that each factor can cause that fault occurs, calculate the factor probability that causes that fault occurs according to Bayesian formula again, obtain successively the probability that causes that each factor occurs according to existing probability and according to Bayesian formula, obtain at last each probability that causes that directly or indirectly fault occurs, by relatively, probability is large namely regards as the reason that causes that this fault occurs.
Through probationary certificate, adopt method of the present invention after, corresponding processing can be investigated out and made to the various failure causes that specially become acquisition terminal, have higher accuracy rate, can Effective Raise specially become the solution efficient of acquisition terminal fault.
Description of drawings
All issuable reason structure charts when accompanying drawing 1 breaks down for specially becoming acquisition terminal;
Accompanying drawing 2 is the process chart of the inventive method.
Embodiment
As shown in Figure 2, the present invention is a kind of special change acquisition terminal method for diagnosing faults based on Bayesian network, comprise the steps: after concrete fault occurs, put the factor material that all can cause that this fault occurs in order, then analyze the probability that each factor can cause that fault occurs, calculate the factor probability that causes that fault occurs according to Bayesian formula again, obtain successively the probability that causes that each factor occurs according to existing probability and according to Bayesian formula, obtain at last each probability that causes that directly or indirectly fault occurs, by relatively, probability is large namely regards as the reason that causes that this fault occurs.
Bayesian network is different from general KBS Knowledge Based System, and it processes uncertain knowledge with strong mathematical tool, explains them in the mode of simple, intuitive.It also is different from general probability analysis instrument, and it combines diagrammatic representation and numeric representation.Based on the special change acquisition terminal method for diagnosing faults of Bayesian network, need us must understand first the possibility (probability of namely said generation) that all reasons that cause fault and each reason cause fault.
All issuable reason structure charts when breaking down for special change acquisition terminal as shown in Figure 1.We are expressed as decision problem under uncertain and the incomplete information to troubleshooting issue, set up the distributed treatment model, uncertainty to information quantizes, simultaneously the method is extended to and under incomplete information, carries out failure diagnosis, realized under uncertain and incomplete information, specially becoming the failure diagnosis of acquisition terminal system.
Bayes is as follows at the application principle that this specially becomes acquisition terminal:
1. the origin of Bayesian formula: we regard event B as the result of a certain process, A1, A2,, An regards several reasons of this process as, the probability that each reason occurs is known, be P (Ai) (i=1,2 ... n, ..) known, and each reason is known to result's influence degree, and namely P (B|Ai) is known, if this result of event B occurs, be which kind of reason when causing that this result occurs when we will investigate, then calculate with Bayesian formula, namely ask P (Ai|B).
Intuitively Ai is regarded as the various possible reason that causes chance event B to occur.If we know that this fresh information occurs chance event B, then it can be used for carrying out again estimation to the probability that event Ai occurs.Event P (Ai/B) has known rear the re-recognizing for probability of fresh information " A generation ".
Therefore, when special transformer terminals when breaking down, we just should associate which factor that has that causes fault, and will be appreciated that each probability that causes that failure factor occurs has much.This B just as top formula represents this result that breaks down, and the Ai representative is various to cause that the direct or indirect factor of fault is the same.P (B) is the various possible probability of list event B generation from generation to generation.P (Ai/B) causes the probability of Ai when B breaks down.
Cause that special change acquisition terminal failure cause is many, as shown in Figure 1, the below is the concrete analysis that causes the main cause of fault:
1. communication failure (generally being divided into uplink communication and downlink communication).Upper layer communication mainly refers to specially to become communicating by letter between acquisition terminal and the main website, mainly contains GPRS communication, cdma communication, 230M private network and infrared communication etc.Downlink communication mainly refers to specially to become communicating by letter of acquisition terminal and electric energy meter, mainly contains understanding RS-485 communication, RS-232 communication, ethernet communication etc.
2. the fault that causes of Rig up error.May cause for reasons such as misoperation or not prison weldings.
3. the fault of checking meter.It mainly contains, and on-the-spot specially change acquisition terminal is not copied in real time, the historical data problem; Main website is long-range not to be copied in real time, the historical data problem.
4. control fault.Specially becoming has four tunnel negative controlled relay outputs or alarm signal to break down on the acquisition terminal.
5. deadlock.May because the thread routine processes do not come, due to the process that perhaps downloads not.
6. shield in vain and the blank screen fault.Bai Ping is because driven by program is successful, but can not read the data that are stored in the flash memory, and menu manifests blank.Because can't detect voltage, liquid crystal display screen causes during blank screen
7. power failure.May be that the reason of Switching Power Supply or the reason of instrument transformer cause main board power supply undesired.
8. the outside environment impact causes fault.Outdoor thermal climate is changeable, under too high or too low temperature, specially becomes some components and parts cisco unity malfunction of acquisition terminal.
Claims (1)
1. special change acquisition terminal method for diagnosing faults based on Bayesian network, it is characterized in that, comprise the steps: after concrete fault occurs, put the factor material that all can cause that this fault occurs in order, then analyze the probability that each factor can cause that fault occurs, calculate the factor probability that causes that fault occurs according to Bayesian formula again, obtain successively the probability that causes that each factor occurs according to existing probability and according to Bayesian formula, obtain at last each probability that causes that directly or indirectly fault occurs, by relatively, probability is large namely regards as the reason that causes that this fault occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105109707A CN103023719A (en) | 2012-12-04 | 2012-12-04 | Specified transformer acquisition terminal failure diagnosis method based on bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105109707A CN103023719A (en) | 2012-12-04 | 2012-12-04 | Specified transformer acquisition terminal failure diagnosis method based on bayesian network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103023719A true CN103023719A (en) | 2013-04-03 |
Family
ID=47971871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105109707A Pending CN103023719A (en) | 2012-12-04 | 2012-12-04 | Specified transformer acquisition terminal failure diagnosis method based on bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103023719A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105607618A (en) * | 2015-12-23 | 2016-05-25 | 苏州汇莱斯信息科技有限公司 | Flight control computer system based on channel fault logical algorithm |
| CN111190072A (en) * | 2019-12-11 | 2020-05-22 | 贵州电网有限责任公司 | Centralized meter reading system diagnosis model establishing method, fault diagnosis method and fault diagnosis device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101507185A (en) * | 2006-06-30 | 2009-08-12 | 意大利电信股份公司 | Fault location in telecommunications networks using bayesian networks |
| CN102170648A (en) * | 2011-01-28 | 2011-08-31 | 北京浩阳华夏科技有限公司 | Passive diagnosis method of wireless sensor network |
| CN102411106A (en) * | 2011-11-18 | 2012-04-11 | 广东电网公司广州供电局 | Fault monitoring method and device for power transformer |
| CN102707708A (en) * | 2012-05-25 | 2012-10-03 | 清华大学 | Method and device for diagnosing faults of multi-mode flight control system |
-
2012
- 2012-12-04 CN CN2012105109707A patent/CN103023719A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101507185A (en) * | 2006-06-30 | 2009-08-12 | 意大利电信股份公司 | Fault location in telecommunications networks using bayesian networks |
| CN102170648A (en) * | 2011-01-28 | 2011-08-31 | 北京浩阳华夏科技有限公司 | Passive diagnosis method of wireless sensor network |
| CN102411106A (en) * | 2011-11-18 | 2012-04-11 | 广东电网公司广州供电局 | Fault monitoring method and device for power transformer |
| CN102707708A (en) * | 2012-05-25 | 2012-10-03 | 清华大学 | Method and device for diagnosing faults of multi-mode flight control system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105607618A (en) * | 2015-12-23 | 2016-05-25 | 苏州汇莱斯信息科技有限公司 | Flight control computer system based on channel fault logical algorithm |
| CN111190072A (en) * | 2019-12-11 | 2020-05-22 | 贵州电网有限责任公司 | Centralized meter reading system diagnosis model establishing method, fault diagnosis method and fault diagnosis device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Data-driven fault diagnosis and thermal runaway warning for battery packs using real-world vehicle data | |
| CN103806005B (en) | A kind of intelligent remote monitoring of underground utilities galvanic protection, monitoring method | |
| Miclea et al. | About dependability in cyber-physical systems | |
| KR101916926B1 (en) | Smart meter system and detection method applying abnormal information detection technology | |
| CN101719309B (en) | System and method for monitoring running state of intelligent LED display | |
| CN110212645B (en) | Power consumption information acquisition terminal power failure event reporting method and device | |
| US20080183406A1 (en) | Online IED Fault Diagnosis Device and Method for Substation Automation System Based on IEC61850 | |
| CN105894133A (en) | Wind turbine component maintenance and spare part demand forecasting method | |
| KR101582695B1 (en) | System for monitoring a communication failure of power device based on ethernet and method therefor | |
| JP6599428B2 (en) | System and method for classifying on-site sensor response data patterns representing grid anomaly severity | |
| CN105980946A (en) | System and method of fault detection | |
| CN105067956A (en) | Anti-colony-algorithm-based distribution network fault positioning method | |
| CN105974232B (en) | A kind of electric network failure diagnosis method suitable for grid | |
| CN104122508B (en) | Online monitoring method for backup power supply system of intelligent power distribution terminal | |
| CN104380554A (en) | Fault detection in energy supply networks | |
| CN103138400A (en) | Detecting and monitoring integrated device of touch type man-machine interaction switch cabinet | |
| WO2022057555A1 (en) | Fault detection method and apparatus, and photovoltaic power generation system | |
| KR20190069213A (en) | Apparatus and method for operation and management of distributed photovoltaic energy generator based on remote monitoring | |
| CN103424662A (en) | Smart power grid transmission line fault monitoring system and method | |
| JP2022115061A (en) | Weather-related overhead distribution line failures online prediction | |
| CN103208049A (en) | Quick accident analysis method and system for abnormal alarm | |
| CN103023719A (en) | Specified transformer acquisition terminal failure diagnosis method based on bayesian network | |
| CN106959414B (en) | The condition detection method and system of switchgear | |
| CN108204334B (en) | The repositioning method and device of wind power generating set | |
| CN107482783B (en) | Comprehensive intelligent system for monitoring and controlling service power |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130403 |