CN112820090A - Alarm system based on big data and implementation method thereof - Google Patents
Alarm system based on big data and implementation method thereof Download PDFInfo
- Publication number
- CN112820090A CN112820090A CN202011609580.6A CN202011609580A CN112820090A CN 112820090 A CN112820090 A CN 112820090A CN 202011609580 A CN202011609580 A CN 202011609580A CN 112820090 A CN112820090 A CN 112820090A
- Authority
- CN
- China
- Prior art keywords
- alarm
- measuring
- fault
- point
- measuring points
- 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 34
- 239000000284 extract Substances 0.000 claims abstract description 6
- 238000012163 sequencing technique Methods 0.000 claims abstract description 6
- 230000036541 health Effects 0.000 claims description 44
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000011157 data evaluation Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 6
- 238000012880 independent component analysis Methods 0.000 claims description 5
- 230000001960 triggered effect Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims 1
- 230000035945 sensitivity Effects 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 14
- 238000012423 maintenance Methods 0.000 description 11
- 230000002159 abnormal effect Effects 0.000 description 8
- 230000002596 correlated effect Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/188—Data fusion; cooperative systems, e.g. voting among different detectors
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses an alarm system based on big data and an implementation method thereof.A signal transmitting module transmits an alarm signal to an alarm signal receiving module, wherein the alarm signal consists of a plurality of single-point alarm signals and a plurality of associated-point alarm signals; the alarm signal receives the alarm signal, extracts fault measuring points in the alarm signal and counts the occurrence frequency of the fault measuring points; accessing the fault measuring points into a fault contribution degree model, calculating pre-alarm coefficients of the fault measuring points, and sequencing the fault measuring points according to each pre-alarm coefficient to obtain an alarm notification signal set; sequentially sending fault measuring points in the alarm notification signal set to a trigger module according to the sequence of the pre-alarm coefficients from large to small; the triggering module receives the fault measuring points and the corresponding pre-alarm coefficients in sequence, matches the fault measuring points with the alarm rules and the alarm threshold values, and triggers the alarm module to send out an alarm. The invention improves the sensitivity and the accuracy of the alarm system by combining the occurrence frequency of fault measuring points and the contribution degree of the fault measuring points.
Description
Technical Field
The invention relates to the field of big data application, in particular to an alarm system based on big data and an implementation method thereof.
Background
Since the industrial revolution, the monitoring and diagnosis of equipment faults have been in progress. Workers have long judged whether equipment has failed or not, mainly through long-term accumulated experience or observation of equipment appearance. Along with the development of the industry to the intelligent, large-scale, high-speed and distributed directions, the maintenance of equipment tends to be intelligent and precise, in order to meet the requirements of automatic intelligent alarm, a big data analysis method is generally used for modeling historical data, a health state monitoring model is established based on normal state historical data screened from the historical data, the health state monitoring model is optimized and verified, and then an alarm device can be combined to give an alarm.
Disclosure of Invention
The invention mainly aims to solve the problem that the early warning of equipment faults is not facilitated in time by a mode of realizing early warning based on fault signals of single measuring points due to complex equipment fault mechanisms, and provides an alarm system based on big data and an implementation method thereof.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a big data based alarm implementing method, including:
firstly, a signal transmitting module transmits an alarm signal to an alarm signal receiving module, wherein the alarm signal consists of a plurality of single-measuring-point alarm signals and a plurality of associated measuring-point alarm signals, the single-measuring-point alarm signal comprises pre-alarm information of one measuring point, and the associated measuring-point alarm signals comprise pre-alarm information of a plurality of measuring points;
step two, the alarm signal receiving module receives the alarm signal in the step one, extracts fault measuring points in the alarm signal and counts the occurrence frequency of the fault measuring points;
thirdly, the fault measuring points are accessed into a fault contribution degree model, signals of the fault measuring points are reduced or amplified, measuring point fault contribution degrees corresponding to the measuring points one by one are arranged in the fault contribution degree model, and the product of the occurrence frequency of the fault measuring points and the measuring point fault contribution degrees is calculated to obtain a pre-alarm coefficient;
step four, sequencing the fault measuring points according to each pre-alarm coefficient to obtain an alarm notification signal set, and sequentially sending the fault measuring points in the alarm notification signal set to the trigger module according to the sequence of the pre-alarm coefficients from large to small;
step five, the triggering module receives each fault measuring point in step three in sequence, the fault measuring point in step three carries a pre-alarm coefficient corresponding to the fault measuring point, an alarm rule and an alarm threshold value are arranged on the triggering module, the fault measuring point is matched with the alarm rule, and the alarm module is triggered to send out an alarm;
the method for counting the occurrence frequency of the fault measuring points comprises the following steps: and one fault measuring point can be extracted from each single measuring point alarm signal, two fault measuring points can be extracted from the related measuring point alarm signals, and the occurrence frequency of the fault measuring points is increased once every time the fault measuring points are extracted until all the alarm signals are extracted.
Preferably, the method for acquiring the alarm signal comprises:
the method comprises the steps that single-measuring-point real-time data and associated real-time data are accessed into a health monitoring data evaluation model, and a single-measuring-point health threshold value and an associated measuring-point health threshold value are set in the health monitoring data evaluation model;
if the single-measuring-point real-time data are located within the single-measuring-point health threshold range, judging that the single-measuring-point real-time data are not sent;
if the single-measuring-point real-time data is located outside the single-measuring-point health threshold range, judging that the single-measuring-point real-time data located outside the single-measuring-point health threshold range is a single-measuring-point alarm signal and sending the single-measuring-point alarm signal to the signal transmitting module;
if the associated real-time data is located within the health threshold range of the associated measuring point, judging not to send the associated real-time data;
and if the associated real-time data is located outside the associated measuring point health threshold range, judging that the associated real-time data located outside the associated measuring point health threshold range is an associated measuring point alarm signal and sending the associated real-time data to the signal transmitting module.
Preferably, the health monitoring data evaluation model is established based on historical data, the health threshold of the single measuring point is determined by noise reduction and trend analysis based on the historical data of each measuring point, and the health threshold of the associated measuring point is determined by association degree analysis after noise reduction based on the historical data of each measuring point.
Preferably, the method for establishing the fault contribution model comprises the following steps: and carrying out independent component analysis on the fault measuring points, extracting original independent signals of the fault measuring points, defining independent element contribution degrees and a contribution degree matrix based on the original independent signals, and calculating to obtain the fault contribution degrees of the measuring points corresponding to the measuring points by adopting a fixed point algorithm.
Preferably, the method for sorting the fault measuring points in the alarm notification signal set comprises: and arranging the pre-alarm coefficients of the fault measuring points in a descending order to obtain the alarm notification signal set formed by combining a plurality of fault measuring points.
Preferably, the alarm rule is:
if the pre-alarm coefficient is larger than the alarm threshold value, an alarm is given out;
and if the pre-alarm coefficient is smaller than the alarm threshold value, no alarm is given.
Preferably, the method comprises the following steps:
the signal transmitting module is used for transmitting an alarm signal;
a plurality of alarm modules for issuing an alarm when triggered;
the triggering module is used for triggering the alarm module when receiving the alarm signal, and comprises an alarm signal receiving module, an alarm signal processing module and a line switch control module;
the alarm signal processing module is used for extracting the fault measuring points in the alarm signal and analyzing to obtain the alarm notification signal sets which are ordered according to the pre-alarm coefficients from large to small;
the line switch control module is used for sequentially receiving the alarm notification signal sets, alarm rules are arranged on the line switch control module, and the line switch control module is connected with the alarm module.
Preferably, the monitoring device further comprises a display module, the display module is in communication connection with the triggering module, and the display module can display the fault measuring point and the pre-alarm coefficient.
The invention at least comprises the following beneficial effects:
1. the alarm system comprises a signal transmitting module, an alarm signal receiving module, a fault detection point calculation module, a fault contribution degree model and a pre-alarm coefficient, wherein the signal transmitting module transmits an alarm signal to the alarm signal receiving module, the alarm signal consists of a plurality of single-point alarm signals and a plurality of related point alarm signals, the alarm signal receiving module can extract fault detection points in the alarm signal after receiving the alarm signal, counts the occurrence frequency of the fault detection points, accesses the fault detection points into the fault contribution degree model, the fault contribution degree model is provided with point fault contribution degrees corresponding to the detection points one by one, calculates the product of the occurrence frequency of the fault detection points and the point fault contribution degrees of the detection points to obtain the pre-alarm coefficient, and sorts; and sequentially sending the fault measuring points in the alarm notification signal set to the trigger module according to the sequence of the pre-alarm coefficients from large to small, and finally giving an alarm by the alarm module according to the alarm rule. The alarm signal of the invention comprises a plurality of single-measuring-point alarm signals and a plurality of associated measuring-point alarm signals, so that the trigger module is combined with the alarm signals of the single-measuring-point and the associated measuring-point to carry out synchronous analysis, and the key point is to analyze the influence of the associated measuring-point on the fault, thereby improving the accuracy of early warning.
2. The alarm system also comprises a display module, wherein the display module is in communication connection with the trigger module, and can display the fault measuring point and the pre-alarm coefficient. Maintenance personnel can lead to alarm information on the display module to reasonably arrange a troubleshooting plan, and the display module has the advantage of being convenient for maintenance personnel to overhaul. At a certain time when the equipment operates, the abnormal single-point signal can be judged as a single-point abnormal signal. If the influence of the measuring point on the running state of the equipment is large, namely the value of the fault contribution degree of the measuring point is large, and the value of the fault contribution degree of another measuring point in the associated real-time signal associated with the measuring point is also large, the associated real-time signal can be judged as an abnormal signal, so that the single-measuring-point signal and the associated signal can be detected as alarm signals, the single-measuring-point alarm signal and the associated measuring-point alarm signal can obtain a pre-alarm coefficient corresponding to the fault measuring point after passing through the signal transmitting module, the alarm signal receiving module and the fault contribution degree model, namely, the measuring point with the large value of the fault contribution degree is secondarily amplified, and therefore, the sensitivity and the accuracy of an alarm system are improved for some measuring points with large fault contribution degrees; if the influence of the measuring point on the running state of the equipment is small, namely the measuring point fault contribution degree value is small, and the fault contribution degree value of another measuring point in the correlated real-time signal associated with the measuring point is also small, the correlated real-time signal can be judged as a normal signal, so that only the single-measuring-point signal is detected as an alarm signal, the single-measuring-point alarm signal can obtain a pre-alarm coefficient corresponding to the fault measuring point after passing through the signal transmitting module, the alarm signal receiving module and the fault contribution degree model, namely, the measuring point with the small fault contribution degree value is secondarily reduced, and the situations of false alarm, multiple alarm and unnecessary alarm of an alarm system are avoided for some measuring points with small fault contribution degree; if the fault contribution degree value of one measuring point in the correlated measuring points is small, and the fault contribution degree value of the other measuring point is large, the system can judge and analyze more accurately according to whether the single measuring point or other correlated measuring points corresponding to the single measuring point are diagnosed as alarm signals, and the sensitivity and the accuracy of the alarm system are improved.
3. The influence of each measuring point on the normal operation of the equipment under the abnormal condition of the equipment is integrated, the single measuring point alarm signal comprises fault information of a certain measuring point by extracting fault measuring points from the single measuring point alarm signal and the related measuring point alarm signal, the related measuring point alarm signal comprises the fault information of a plurality of measuring points, the influence degree of the fault measuring points on the normal operation of the equipment in the time period can be intuitively known by counting the occurrence frequency of the fault measuring points, and the measuring point fault contribution degree of the fault measuring points is obtained according to a big data technology.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
FIG. 1 is a flow chart of an alarm system;
FIG. 2 is a block diagram of an alarm system;
FIG. 3 is a block diagram of a big data-based alarm implementation method.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
The invention provides an alarm system based on big data and an implementation method thereof, and figures 1-3 show an implementation form according to the invention, and the implementation method of the alarm system comprises the following steps:
firstly, a signal transmitting module transmits an alarm signal to an alarm signal receiving module, wherein the alarm signal consists of a plurality of single-measuring-point alarm signals and a plurality of associated measuring-point alarm signals, the single-measuring-point alarm signals comprise pre-alarm information of one measuring point, and the associated measuring-point alarm signals comprise pre-alarm information of a plurality of measuring points;
the method for acquiring the alarm signal comprises the following steps:
the method comprises the following steps that single-measuring-point real-time data and associated real-time data are accessed into a health monitoring data evaluation model, and a single-measuring-point health threshold value and an associated measuring-point health threshold value are arranged in the health monitoring data evaluation model;
if the single-measuring-point real-time data are located within the single-measuring-point health threshold range, judging that the single-measuring-point real-time data are not sent;
if the single-measuring-point real-time data are located outside the single-measuring-point health threshold range, the single-measuring-point real-time data located outside the single-measuring-point health threshold range are judged to be single-measuring-point alarm signals and are sent to a signal transmitting module;
if the associated real-time data is located within the health threshold range of the associated measuring point, judging not to send the associated real-time data;
and if the associated real-time data is located outside the health threshold range of the associated measuring point, judging that the associated real-time data located outside the health threshold range of the associated measuring point is an associated measuring point alarm signal and sending the associated real-time data to the signal transmitting module.
The health monitoring data evaluation model is established based on historical data, the health threshold values of the single measuring points are determined by noise reduction and trend analysis based on the historical data of the measuring points, and the health threshold values of the associated measuring points are determined by performing correlation degree analysis after noise reduction based on the historical data of the measuring points.
The real-time data comprises single-point real-time data and associated real-time data, the health monitoring data evaluation model is used for screening abnormal data in the real-time data, real-time data located in a single-point health threshold range or outside the associated point health threshold range can be separated through data processing to obtain a single-point alarm signal and an associated point alarm signal, and the single-point alarm signal and the associated point alarm signal are transmitted to the signal transmitting module.
The alarm signal of the invention comprises a plurality of single-measuring-point alarm signals and a plurality of associated measuring-point alarm signals, so that the trigger module can synchronously analyze the alarm signals of the single-measuring-point and the associated measuring-point, and the key point is to analyze the influence of the associated measuring-point on the fault, thereby improving the accuracy of early warning.
Step two, an alarm signal receiving module receives the alarm signal in the step one, extracts fault measuring points in the alarm signal and counts the occurrence frequency of the fault measuring points;
the method for counting the occurrence frequency of the fault measuring points comprises the following steps: and one fault measuring point can be extracted from each single measuring point alarm signal, two fault measuring points can be extracted from the related measuring point alarm signal, and the occurrence frequency of one fault measuring point is increased once each fault measuring point is extracted until all the alarm signals are extracted. The method for establishing the fault contribution degree model comprises the following steps: and (3) carrying out independent component analysis on the fault measuring points, extracting original independent signals of each fault measuring point, defining an independent element contribution degree and a contribution degree matrix based on the original independent signals, and calculating to obtain the measuring point fault contribution degree corresponding to each measuring point by adopting a fixed point algorithm.
Thirdly, accessing the fault measuring points into a fault contribution degree model, reducing or amplifying signals of the fault measuring points, setting measuring point fault contribution degrees corresponding to the measuring points one by one in the fault contribution degree model, and calculating the product of the occurrence frequency of the fault measuring points and the measuring point fault contribution degrees to obtain a pre-alarm coefficient;
specifically, the method for establishing the fault contribution degree model comprises the following steps: and (3) carrying out independent component analysis on the fault measuring points, extracting original independent signals of each fault measuring point, defining an independent element contribution degree and a contribution degree matrix based on the original independent signals, and calculating to obtain the measuring point fault contribution degree corresponding to each measuring point by adopting a fixed point algorithm.
The triggering module extracts fault measuring points through the received alarm signals, counts the occurrence frequency of the fault measuring points, obtains the fault contribution degree of each fault measuring point through independent component analysis and calculation, and calculates the product of the occurrence frequency of the fault measuring points and the fault contribution degree of the measuring points to obtain the pre-alarm coefficient.
And fourthly, sequencing the fault measuring points according to each pre-alarm coefficient to obtain an alarm notification signal set, and sequentially sending the fault measuring points in the alarm notification signal set to the trigger module according to the sequence of the pre-alarm coefficients from large to small.
Specifically, the method for sequencing the fault measuring points in the alarm notification signal set comprises the following steps: and arranging according to the sequence of the pre-alarm coefficients of the fault measuring points from large to small to obtain an alarm notification signal set formed by combining a plurality of fault measuring points.
According to the invention, the fault measuring points in the alarm notification signal set are sequentially sent to the trigger module according to the sequence of the pre-alarm coefficients from large to small, and finally the alarm module gives an alarm according to the alarm rule, so that the alarm module can preferentially receive the measuring points with large fault contribution degree and preferentially alarm, so that maintenance personnel can process the main measuring points causing the fault occurrence in the first time, and the early warning efficiency and the maintenance efficiency of the maintenance personnel are improved.
And step five, the triggering module receives each fault measuring point in the step three in sequence, the fault measuring points in the step three carry corresponding pre-alarm coefficients, the triggering module is provided with alarm rules and alarm thresholds, the fault measuring points are matched with the alarm rules, and the triggering alarm module sends out an alarm. Wherein the alarm rule is as follows: if the pre-alarm coefficient is larger than the alarm threshold value, an alarm is given out; and if the pre-alarm coefficient is smaller than the alarm threshold value, no alarm is given.
The alarm system based on the alarm method comprises the following steps: the signal transmitting module is used for transmitting an alarm signal;
a plurality of alarm modules for issuing an alarm when triggered;
the trigger module is used for triggering the alarm module when receiving the alarm signal, and comprises an alarm signal receiving module, an alarm signal processing module and a line switch control module;
the alarm signal processing module is used for extracting fault measuring points in the alarm signal and analyzing to obtain an alarm notification signal set which is sorted from large to small according to a pre-alarm coefficient;
the line switch control module is used for sequentially receiving all the alarm notification signal sets, alarm rules are arranged on the line switch control module, and the line switch control module is connected with the alarm module.
The alarm system also comprises a display module, wherein the display module is in communication connection with the trigger module, and can display the fault measuring point and the pre-alarm coefficient. Maintenance personnel can lead to alarm information on the display module to reasonably arrange a troubleshooting plan, and the display module has the advantage of being convenient for maintenance personnel to overhaul.
At a certain time when the equipment operates, the abnormal single-point signal can be judged as a single-point abnormal signal. If the influence of the measuring point on the running state of the equipment is large, namely the value of the fault contribution degree of the measuring point is large, and the value of the fault contribution degree of another measuring point in the associated real-time signal associated with the measuring point is also large, the associated real-time signal can be judged as an abnormal signal, so that the single-measuring-point signal and the associated signal can be detected as alarm signals, the single-measuring-point alarm signal and the associated measuring-point alarm signal can obtain a pre-alarm coefficient corresponding to the fault measuring point after passing through the signal transmitting module, the alarm signal receiving module and the fault contribution degree model, namely, the measuring point with the large value of the fault contribution degree is secondarily amplified, and therefore, the sensitivity and the accuracy of an alarm system are improved for some measuring points with large fault contribution degrees; if the influence of the measuring point on the running state of the equipment is small, namely the measuring point fault contribution degree value is small, and the fault contribution degree value of another measuring point in the correlated real-time signal associated with the measuring point is also small, the correlated real-time signal can be judged as a normal signal, so that only the single-measuring-point signal is detected as an alarm signal, the single-measuring-point alarm signal can obtain a pre-alarm coefficient corresponding to the fault measuring point after passing through the signal transmitting module, the alarm signal receiving module and the fault contribution degree model, namely, the measuring point with the small fault contribution degree value is secondarily reduced, and the situations of false alarm, multiple alarm and unnecessary alarm of an alarm system are avoided for some measuring points with small fault contribution degree; if the fault contribution degree value of one measuring point in the correlated measuring points is small, and the fault contribution degree value of the other measuring point is large, the system can judge and analyze more accurately according to whether the single measuring point or other correlated measuring points corresponding to the single measuring point are diagnosed as alarm signals, and the sensitivity and the accuracy of the alarm system are improved.
In addition, the fault measuring points in the alarm notification signal set are sequentially sent to the trigger module according to the sequence of the pre-alarm coefficients from large to small, and finally the alarm module gives an alarm according to the alarm rule, so that the alarm module can preferentially receive the measuring points with large fault contribution degree and preferentially alarm, so that maintenance personnel can process the main measuring points which cause the fault occurrence in the first time, and the early-warning efficiency and the maintenance efficiency of the maintenance personnel are improved.
While embodiments of the invention have been disclosed above, it is not intended to be limited to the uses set forth in the specification and examples. It can be applied to all kinds of fields suitable for the present invention. Additional modifications will readily occur to those skilled in the art. It is therefore intended that the invention not be limited to the exact details and illustrations described and illustrated herein, but fall within the scope of the appended claims and equivalents thereof.
Claims (8)
1. An alarm implementation method based on big data is characterized by comprising the following steps:
firstly, a signal transmitting module transmits an alarm signal to an alarm signal receiving module, wherein the alarm signal consists of a plurality of single-measuring-point alarm signals and a plurality of associated measuring-point alarm signals, the single-measuring-point alarm signal comprises pre-alarm information of one measuring point, and the associated measuring-point alarm signals comprise pre-alarm information of a plurality of measuring points;
step two, the alarm signal receiving module receives the alarm signal in the step one, extracts fault measuring points in the alarm signal and counts the occurrence frequency of the fault measuring points;
thirdly, the fault measuring points are accessed into a fault contribution degree model, signals of the fault measuring points are reduced or amplified, measuring point fault contribution degrees corresponding to the measuring points one by one are arranged in the fault contribution degree model, and the product of the occurrence frequency of the fault measuring points and the measuring point fault contribution degrees is calculated to obtain a pre-alarm coefficient;
step four, sequencing the fault measuring points according to each pre-alarm coefficient to obtain an alarm notification signal set, and sequentially sending the fault measuring points in the alarm notification signal set to the trigger module according to the sequence of the pre-alarm coefficients from large to small;
step five, the triggering module receives each fault measuring point in step three in sequence, the fault measuring point in step three carries a pre-alarm coefficient corresponding to the fault measuring point, an alarm rule and an alarm threshold value are arranged on the triggering module, the fault measuring point is matched with the alarm rule, and the alarm module is triggered to send out an alarm;
the method for counting the occurrence frequency of the fault measuring points comprises the following steps: and extracting one fault measuring point from each single measuring point alarm signal, and extracting two fault measuring points from the related measuring point alarm signals, wherein the occurrence frequency of the fault measuring points is increased once every time the fault measuring points are extracted, until all the alarm signals are extracted.
2. The big data based alarm realization method of claim 1, wherein the method of obtaining the alarm signal is:
the method comprises the steps that single-measuring-point real-time data and associated real-time data are accessed into a health monitoring data evaluation model, and a single-measuring-point health threshold value and an associated measuring-point health threshold value are set in the health monitoring data evaluation model;
if the single-measuring-point real-time data are located within the single-measuring-point health threshold range, judging that the single-measuring-point real-time data are not sent;
if the single-measuring-point real-time data is located outside the single-measuring-point health threshold range, judging that the single-measuring-point real-time data located outside the single-measuring-point health threshold range is a single-measuring-point alarm signal and sending the single-measuring-point alarm signal to the signal transmitting module;
if the associated real-time data is located within the health threshold range of the associated measuring point, judging not to send the associated real-time data;
and if the associated real-time data is located outside the associated measuring point health threshold range, judging that the associated real-time data located outside the associated measuring point health threshold range is an associated measuring point alarm signal and sending the associated real-time data to the signal transmitting module.
3. The big data-based alarm realization method of claim 2, wherein the health monitoring data evaluation model is established based on historical data, the health threshold values of the single measuring points are determined by noise reduction and trend analysis based on the historical data of the measuring points, and the health threshold values of the associated measuring points are determined by association degree analysis after noise reduction based on the historical data of the measuring points.
4. The big data-based alarm implementation method of claim 1, wherein the fault contribution model is established by: and carrying out independent component analysis on the fault measuring points, extracting original independent signals of the fault measuring points, defining independent element contribution degrees and a contribution degree matrix based on the original independent signals, and calculating to obtain the fault contribution degrees of the measuring points corresponding to the measuring points by adopting a fixed point algorithm.
5. The big data-based alarm realization method of claim 1, wherein the sequencing method of the fault measurement points in the alarm notification signal set is as follows: and arranging the pre-alarm coefficients of the fault measuring points in a descending order to obtain the alarm notification signal set formed by combining a plurality of fault measuring points.
6. The big-data-based alarm implementation method according to claim 1, wherein the alarm rules are:
if the pre-alarm coefficient is larger than the alarm threshold value, an alarm is given out;
and if the pre-alarm coefficient is smaller than the alarm threshold value, no alarm is given.
7. An alarm system based on big data, comprising:
the signal transmitting module is used for transmitting an alarm signal;
a plurality of alarm modules for issuing an alarm when triggered;
the triggering module is used for triggering the alarm module when receiving the alarm signal, and comprises an alarm signal receiving module, an alarm signal processing module and a line switch control module;
the alarm signal processing module is used for extracting the fault measuring points in the alarm signal and analyzing to obtain the alarm notification signal sets which are ordered according to the pre-alarm coefficients from large to small;
the line switch control module is used for sequentially receiving the alarm notification signal sets, alarm rules are arranged on the line switch control module, and the line switch control module is connected with the alarm module.
8. The big data based alarm system of claim 7, further comprising a display module, wherein the display module is communicatively connected to the trigger module, and the display module can display the fault detection point and the pre-alarm coefficient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011609580.6A CN112820090A (en) | 2020-12-30 | 2020-12-30 | Alarm system based on big data and implementation method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011609580.6A CN112820090A (en) | 2020-12-30 | 2020-12-30 | Alarm system based on big data and implementation method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112820090A true CN112820090A (en) | 2021-05-18 |
Family
ID=75856167
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011609580.6A Pending CN112820090A (en) | 2020-12-30 | 2020-12-30 | Alarm system based on big data and implementation method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112820090A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114298437A (en) * | 2022-01-04 | 2022-04-08 | 国家能源集团国源电力有限公司 | Equipment early warning method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040002792A1 (en) * | 2002-06-28 | 2004-01-01 | Encelium Technologies Inc. | Lighting energy management system and method |
CN102844721A (en) * | 2010-02-26 | 2012-12-26 | 株式会社日立制作所 | Failure source diagnosis system and method |
CN104158682A (en) * | 2014-08-08 | 2014-11-19 | 深圳供电局有限公司 | Synchronous Digital Hierarchy (SDH) fault positioning method based on contribution degree |
CN110501169A (en) * | 2019-08-27 | 2019-11-26 | 北理慧动(常熟)车辆科技有限公司 | Diagnostic method, device and the electronic equipment of vehicle trouble |
CN111306051A (en) * | 2020-01-16 | 2020-06-19 | 中国石油大学(北京) | Probe type state monitoring and early warning method, device and system for oil transfer pump unit |
-
2020
- 2020-12-30 CN CN202011609580.6A patent/CN112820090A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040002792A1 (en) * | 2002-06-28 | 2004-01-01 | Encelium Technologies Inc. | Lighting energy management system and method |
CN102844721A (en) * | 2010-02-26 | 2012-12-26 | 株式会社日立制作所 | Failure source diagnosis system and method |
CN104158682A (en) * | 2014-08-08 | 2014-11-19 | 深圳供电局有限公司 | Synchronous Digital Hierarchy (SDH) fault positioning method based on contribution degree |
CN110501169A (en) * | 2019-08-27 | 2019-11-26 | 北理慧动(常熟)车辆科技有限公司 | Diagnostic method, device and the electronic equipment of vehicle trouble |
CN111306051A (en) * | 2020-01-16 | 2020-06-19 | 中国石油大学(北京) | Probe type state monitoring and early warning method, device and system for oil transfer pump unit |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114298437A (en) * | 2022-01-04 | 2022-04-08 | 国家能源集团国源电力有限公司 | Equipment early warning method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106655522A (en) | Master station system suitable for operation and maintenance management of secondary equipment of power grid | |
CN110703214B (en) | Weather radar state evaluation and fault monitoring method | |
CN103983881B (en) | The method for diagnosing faults of nuclear detector and device | |
CN111143438A (en) | Workshop field data real-time monitoring and anomaly detection method based on stream processing | |
CN116204842B (en) | Abnormality monitoring method and system for electrical equipment | |
CN107844067B (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
CN101718634A (en) | Equipment state comprehensive dynamic alarming method based on multivariate probability model | |
CN110231529A (en) | A kind of control cabinet intelligent Fault Diagnose Systems and method for diagnosing faults | |
CN110375983A (en) | Failsafe valve real-time diagnosis system and diagnostic method based on time series analysis | |
CN113657221A (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
CN111717753A (en) | Self-adaptive elevator fault early warning system and method based on multi-dimensional fault characteristics | |
CN115576738A (en) | Method and system for realizing equipment fault determination based on chip analysis | |
CN112820090A (en) | Alarm system based on big data and implementation method thereof | |
CN117289778B (en) | Real-time monitoring method for health state of industrial control host power supply | |
CN207992717U (en) | A kind of gate of hydropower station on-line condition monitoring system | |
CN109388512A (en) | For the assessment and analysis system of large-scale computer cluster intensity of anomaly | |
CN104007757B (en) | Self-diagnosis method and system for gateway communication abnormity in distributed control system of nuclear power plant | |
CN106019089A (en) | Method for carrying out partial discharging determination based on related relationship feature of alternate signals | |
CN115034094B (en) | Prediction method and system for operation state of metal processing machine tool | |
CN106444578A (en) | Method for detecting faults based on heterogeneous geodesic distance SVDD (support vector domain description) | |
CN115902476A (en) | Multi-dimensional transformer fault diagnosis and state evaluation system and method | |
CN110307899A (en) | Sound anomaly detection system based on deep learning | |
CN114689321A (en) | Bearing fault diagnosis method and device for wind generating set and electronic equipment | |
KR20210059267A (en) | A system and method for data collection | |
CN111980900B (en) | Water pump fault diagnosis method based on multi-source data fusion analysis |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |
|
RJ01 | Rejection of invention patent application after publication |