CN117935519B - Gas detection alarm system - Google Patents
Gas detection alarm system Download PDFInfo
- Publication number
- CN117935519B CN117935519B CN202410330936.4A CN202410330936A CN117935519B CN 117935519 B CN117935519 B CN 117935519B CN 202410330936 A CN202410330936 A CN 202410330936A CN 117935519 B CN117935519 B CN 117935519B
- Authority
- CN
- China
- Prior art keywords
- event
- abnormal
- gas system
- data
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000007789 gas Substances 0.000 claims 26
- 239000002737 fuel gas Substances 0.000 claims 1
- 230000007797 corrosion Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000010485 coping Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a gas detection alarm system, which relates to the technical field of gas early warning and comprises the following components: the event detection module is arranged on the gas system and used for carrying out event acquisition on the gas system to obtain event data of the gas system; the event identification module is used for identifying event keywords in the event data of the gas system; the event learning module is used for calculating abnormal relevance indexes of event keywords; the intelligent analysis module is used for determining the abnormal risk of the event of the gas system based on the event keywords in the event data of the gas system; and the protection early warning module is used for outputting protection early warning signals based on the abnormal event risk of the gas system. The invention has the advantages that: the method has the advantages that the repeated learning of historical operation data is effectively realized, intelligent learning updating can be effectively carried out by combining the operation data of the gas system, the fault event protection accuracy and timeliness of the alarm system are greatly improved, and intelligent protection of the alarm system is realized.
Description
Technical Field
The invention relates to the technical field of gas early warning, in particular to a gas detection alarm system.
Background
The safe operation of the gas pipe network relates to the safety of social production and people life and property, gas enterprises provide clean and efficient energy for thousands of households, manages crisscross underground gas pipe networks and mass production equipment in the range of an operation area, relates to a plurality of links of production, transmission, storage, metering, use, marketing and the like, monitors the gas pipelines, and is an important premise for guaranteeing the use safety of gas.
The existing gas detection alarm greatly depends on a preset safety fault judgment standard, and is difficult to comprehensively analyze according to real-time data in the operation process of a gas system and operation and maintenance big data of the gas system, so that the alarm system lacks intelligent learning updating capability, is difficult to deal with the protection and identification of complex fault events, and has poor coping capability of the alarm system to the fault events and security holes.
Disclosure of Invention
In order to solve the technical problems, the technical scheme provides a gas detection alarm system, which solves the problems that the alarm system in the prior art lacks intelligent learning updating capability, is difficult to deal with the protection and identification of complex fault events, causes poor coping capability of the alarm system to the fault events and has security holes.
In order to achieve the above purpose, the invention adopts the following technical scheme:
A gas detection alarm system comprising:
the event detection modules are arranged on the gas system and are used for carrying out event acquisition on the gas system to obtain gas system event data;
The event identification module is in communication connection with the event detection module by adopting a wire or a wireless mode, and is used for identifying event keywords in the event data of the gas system;
The event learning module is in communication connection with the large database by adopting a wire or wireless mode and is used for calculating abnormal relevance indexes of event keywords;
the intelligent analysis module is electrically connected with the event identification module and the event learning module and is used for determining the abnormal event risk of the gas system based on the abnormal relevance index of the event keywords in the event data of the gas system;
The protection early warning module is used for being electrically connected with the intelligent analysis module, and the protection early warning module is used for outputting protection early warning signals based on abnormal event risks of the gas system.
Preferably, the event recognition module specifically includes:
The standard event learning unit is used for determining standard parameter operation intervals of all events in the operation process of the gas system;
the event analysis unit is used for screening out a plurality of moments which do not accord with the standard parameter operation interval of the event in the event data of the gas system and recording the moments as abnormal moments;
The keyword extraction unit is used for extracting event abnormal values which are corresponding to abnormal moments and do not accord with the standard parameter operation interval of the event, and the event abnormal values are recorded as event keywords.
Preferably, the determining the standard parameter operation interval of each event in the operation process of the gas system specifically includes:
Acquiring a plurality of historical operation data corresponding to each event in the operation process of the gas system, and recording the historical operation data as sample data;
Based on the Grabbs criterion, eliminating abnormal data in the sample data to obtain a plurality of standard operation data corresponding to the event;
The average value and standard deviation of a plurality of standard operation data corresponding to the event are obtained, and the standard parameter operation interval of the event is that ,/>For the average value of a plurality of standard running data corresponding to the event,/>The standard deviation of a plurality of standard operation data corresponding to the event is obtained;
The expression of the glabros criterion is: ,
In the method, in the process of the invention, For/>Sample data,/>For the average value of the sample data,/>Is the standard deviation of the sample data, is the total number of the sample data,/>Is a significant level/>Lower/>Values of the distribution, if the expression of the glabros criterion is satisfied,/>Is abnormal data.
Preferably, the calculating the abnormal relevance index of the event keyword specifically includes:
Acquiring all historical operation events in the operation process of the gas system;
Forming an event keyword library by all event keywords of all historical operation events in the operation process of the gas system;
classifying event keywords to obtain a plurality of event keyword classes;
acquiring event keywords corresponding to each event keyword class in the event keyword library, and combining the event keywords into an event keyword set Wherein/>For the event keyword set corresponding to the ith event keyword class,/>For the jth event keyword in the event keyword library corresponding to the ith event keyword class,The total number of the event keywords corresponding to the ith event keyword class in the event keyword library;
and calculating abnormal relevance indexes between elements of any two event keyword sets through a relevance calculation algorithm.
Preferably, the correlation calculation algorithm specifically includes:
two event keyword sets are arbitrarily acquired and respectively recorded as And/>;
Calling for occurrences in a large databaseElement/>Is marked as first abnormal data;
Calling for occurrences in a large database Element/>Is noted as second anomaly data,
Wherein,The method comprises the steps of setting an mth event keyword corresponding to an mth event keyword class in an event keyword library;
Calculation based on correlation calculation formula And/>Abnormal relatedness index between the two.
Preferably, the correlation calculation formula specifically includes:,
In the method, in the process of the invention, For/>And/>Abnormal relevance index between/(For the first abnormal data total number,/>For the second abnormal data total number,/>Is the total number of historical operating data of the gas system.
Preferably, the intelligent analysis module specifically includes:
the event keyword classification unit is used for performing traversal search on the event keywords in the event data of each gas system in the event keyword library to obtain matched event keywords corresponding to the event keywords in the event data of each gas system;
The abnormal risk calculation unit is used for calculating event abnormal risk values corresponding to the event data of the gas system based on the abnormal relevance indexes of all the matched event keywords.
Preferably, calculating the event abnormal risk value corresponding to the gas system event data based on the abnormal relevance indexes of all the matching event keywords specifically includes:
combining all the matching event keywords in any pair to obtain a plurality of matching event keyword groups;
Determining an abnormal relevance index between two matched event keywords of each matched event keyword group, and marking the abnormal relevance index as an abnormal index of the matched event keyword group;
And accumulating the abnormal indexes of all the matched event key groups to obtain event abnormal risk values corresponding to the event data of the gas system.
Preferably, the outputting the protection early warning signal specifically includes:
Judging whether an event abnormal risk value corresponding to the event data of the gas system is larger than a preset value, if so, judging that the gas system has a fault event, outputting a protection early warning signal, and if not, judging that the gas system has no fault event, and not outputting the protection early warning signal.
Compared with the prior art, the invention has the beneficial effects that:
The invention provides a gas detection alarm system, which is used for comprehensively analyzing historical operation data in the operation process of a gas system, constructing abnormal relevance indexes between every two event keywords existing in the operation process of the gas system, wherein the abnormal relevance indexes represent risks of faults of the gas system when the event keywords are simultaneously generated, identifying and extracting event keywords in the event data of the gas system for the monitored event data of the gas system, and calculating abnormal event risk values, so that the risks of faults of the gas system can be timely found.
Drawings
FIG. 1 is a block diagram of a gas detection alarm system according to the present invention;
FIG. 2 is a flow chart of a method for determining standard parameter operating intervals of each event in the operation process of the gas system in the invention;
FIG. 3 is a flowchart of a method for calculating an anomaly correlation indicator for an event keyword in the present invention;
FIG. 4 is a flow chart of a correlation calculation algorithm according to the present invention;
FIG. 5 is a flowchart of a method for calculating an event anomaly risk value corresponding to gas system event data according to the present invention;
fig. 6 is a flowchart of a method for outputting a protection early warning signal based on abnormal risk of an event in a gas system in the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, a gas detection alarm system includes:
The system comprises at least one event detection module, a plurality of event detection modules and a control module, wherein the event detection modules are arranged in a gas system and are used for carrying out event acquisition on the gas system to obtain gas system event data;
the event recognition module is in communication connection with the event detection module by adopting a wire or a wireless mode, and is used for recognizing event keywords in the event data of the gas system;
the event learning module is in communication connection with the large database by adopting a wire or wireless mode and is used for calculating abnormal relevance indexes of event keywords;
The intelligent analysis module is electrically connected with the event identification module and the event learning module and is used for determining the event abnormal risk of the gas system based on the abnormal relevance index of the event keywords in the event data of the gas system;
the protection early warning module is used for being electrically connected with the intelligent analysis module, and the protection early warning module is used for outputting protection early warning signals based on abnormal event risks of the gas system.
According to the scheme, based on historical operation data in the operation process of the gas system, abnormal relevance indexes between every two event keywords existing in the operation process of the gas system are constructed, the abnormal relevance indexes represent risks that the gas system is in fault when the event keywords are simultaneously generated, the monitored event data of the gas system are identified and extracted, abnormal event risk values are calculated, and then risks that the gas system is in fault can be timely found;
For example, for the gas system protection fault event of throwing an article into the dangerous area, before the system is used for optimization, early warning can only occur when the corrosion leakage of a gas pipeline occurs, after the system is used for optimization, intelligent learning is performed based on all abnormal events related to the corrosion of the gas system fault in the historical operation event in the operation process of the gas system, when the gas system is not corroded and leaked, only the initial event of corrosion occurs, and the abnormal events are learned and identified by the protection system, so that protection early warning can be performed at the initial stage of the fault event, and the longer the operation time of the alarm system is, the deeper the learning degree of the fault event of the gas system is, and the higher the alarm accuracy of the gas system is.
Referring to fig. 1, the event recognition module specifically includes:
the standard event learning unit is used for determining standard parameter operation intervals of all events in the operation process of the gas system;
the event analysis unit is used for screening out a plurality of moments which do not accord with the standard parameter operation interval of the event in the event data of the gas system and recording the moments as abnormal moments;
The keyword extraction unit is used for extracting event abnormal values which correspond to abnormal moments and do not accord with the standard parameter operation interval of the event, and the event abnormal values are recorded as event keywords.
Referring to fig. 2, determining standard parameter operation intervals of each event in the operation process of the gas system specifically includes:
Acquiring a plurality of historical operation data corresponding to each event in the operation process of the gas system, and recording the historical operation data as sample data;
Based on the Grabbs criterion, eliminating abnormal data in the sample data to obtain a plurality of standard operation data corresponding to the event;
The average value and standard deviation of a plurality of standard operation data corresponding to the event are obtained, and the standard parameter operation interval of the event is that ,/>For the average value of a plurality of standard running data corresponding to the event,/>The standard deviation of a plurality of standard operation data corresponding to the event is obtained;
The expression of the glabros criterion is: ,
In the method, in the process of the invention, For/>Sample data,/>For the average value of the sample data,/>Is the standard deviation of the sample data, is the total number of the sample data,/>Is a significant level/>Lower/>Values of the distribution, if the expression of the glabros criterion is satisfied,/>Is abnormal data.
It can be understood that in the gas system process, due to the influence of the gas system operation environment, the operation parameters often cause deviation points, and the deviation points generate larger error influence when the parameter standard interval is calculated, and in order to eliminate the deviation points, the method is based on the Grabbs test algorithm, the density degree and the outlier of the sample data are identified and calculated, and the outlier in the sample data is eliminated, so that the influence of the deviation points on the parameter standard interval calculation is reduced, the accuracy of the parameter standard interval is further effectively improved, and the identification accuracy of abnormal operation events of the gas system is improved.
Referring to fig. 3, calculating an abnormality association index of an event keyword specifically includes:
Acquiring all historical operation events in the operation process of the gas system;
Forming an event keyword library by all event keywords of all historical operation events in the operation process of the gas system;
classifying event keywords to obtain a plurality of event keyword classes;
acquiring event keywords corresponding to each event keyword class in the event keyword library, and combining the event keywords into an event keyword set Wherein/>For the event keyword set corresponding to the ith event keyword class,/>For the jth event keyword in the event keyword library corresponding to the ith event keyword class,The total number of the event keywords corresponding to the ith event keyword class in the event keyword library;
and calculating abnormal relevance indexes between elements of any two event keyword sets through a relevance calculation algorithm.
Referring to fig. 4, the correlation calculation algorithm specifically includes:
two event keyword sets are arbitrarily acquired and respectively recorded as And/>;
Calling for occurrences in a large databaseElement/>Is marked as first abnormal data;
Calling for occurrences in a large database Element/>Is noted as second anomaly data, wherein,The method comprises the steps of setting an mth event keyword corresponding to an mth event keyword class in an event keyword library;
Calculation based on correlation calculation formula And/>Abnormal relatedness index between the two.
The correlation calculation formula is specifically as follows:,
In the method, in the process of the invention, For/>And/>Abnormal relevance index between/(For the first abnormal data total number,/>For the second abnormal data total number,/>Is the total number of historical operating data of the gas system.
Based on the fact that the possible event abnormality risks caused by different event keyword combinations are different, comprehensive analysis and calculation are performed by combining event keywords appearing in fault events in historical operation events of the gas system, and abnormal relevance indexes between event keywords under each two different event keyword classes represent risk indexes of the fault event when two event keywords appear in the same event at the same time, and the larger the value is, the larger the risk indexes of the fault event are indicated when the two event keywords appear simultaneously at the same time.
Referring to fig. 1, the intelligent analysis module specifically includes:
The event keyword classification unit is used for performing traversal search on the event keywords in the event data of each gas system in the event keyword library to obtain matched event keywords corresponding to the event keywords in the event data of each gas system;
The abnormal risk calculation unit is used for calculating event abnormal risk values corresponding to the event data of the gas system based on the abnormal relevance indexes of all the matched event keywords.
Referring to fig. 5, calculating an event abnormality risk value corresponding to the gas system event data based on abnormality association indexes of all the matching event keywords specifically includes:
combining all the matching event keywords in any pair to obtain a plurality of matching event keyword groups;
determining an abnormal relevance index between two matching event keywords of each matching event keyword group, and marking the abnormal relevance index as an abnormal index of the matching event keyword group;
And accumulating the abnormal indexes of all the matched event key groups to obtain event abnormal risk values corresponding to the event data of the gas system.
Referring to fig. 6, based on the abnormal risk of the event of the gas system, outputting the protection pre-warning signal specifically includes:
Judging whether an event abnormal risk value corresponding to the event data of the gas system is larger than a preset value, if so, judging that the gas system has a fault event, outputting a protection early warning signal, and if not, judging that the gas system has no fault event, and not outputting the protection early warning signal.
It can be understood that there may be many event keywords at the same time, and the abnormal relevance indexes between the event keywords are integrated and accumulated, so as to obtain the risk of occurrence of the fault event requiring vigilance at the current detected time, and the higher the abnormal event risk value, the higher the probability of occurrence of the fault event.
In summary, the invention has the advantages that: the method has the advantages that the repeated learning of historical operation data is effectively realized, intelligent learning updating can be effectively carried out by combining the operation data of the gas system, the fault event protection accuracy and timeliness of the alarm system are greatly improved, and intelligent protection of the alarm system is realized.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. A gas detection alarm system, comprising:
the event detection modules are arranged on the gas system and are used for carrying out event acquisition on the gas system to obtain gas system event data;
The event identification module is in communication connection with the event detection module by adopting a wire or a wireless mode, and is used for identifying event keywords in the event data of the gas system;
The event learning module is in communication connection with the large database by adopting a wire or wireless mode and is used for calculating abnormal relevance indexes of event keywords;
the intelligent analysis module is electrically connected with the event identification module and the event learning module and is used for determining the abnormal event risk of the gas system based on the abnormal relevance index of the event keywords in the event data of the gas system;
The protection early-warning module is used for being electrically connected with the intelligent analysis module, and outputting a protection early-warning signal based on the abnormal event risk of the gas system;
the calculating the abnormal relevance index of the event keyword specifically comprises the following steps:
Acquiring all historical operation events in the operation process of the gas system;
Forming an event keyword library by all event keywords of all historical operation events in the operation process of the gas system;
classifying event keywords to obtain a plurality of event keyword classes;
acquiring event keywords corresponding to each event keyword class in the event keyword library, and combining the event keywords into an event keyword set ,/>Wherein/>For the event keyword set corresponding to the ith event keyword class,/>For the j-th event keyword in the event keyword library corresponding to the i-th event keyword class,/>The total number of the event keywords corresponding to the ith event keyword class in the event keyword library;
calculating abnormal relevance indexes between elements of any two event keyword sets through a relevance calculation algorithm;
the correlation calculation algorithm specifically comprises:
two event keyword sets are arbitrarily acquired and respectively recorded as the total number of event keywords corresponding to the ith event keyword class in the event keyword library;
calculating abnormal relevance indexes between elements of any two event keyword sets through a relevance calculation algorithm;
the correlation calculation algorithm specifically comprises:
two event keyword sets are arbitrarily acquired and respectively recorded as And/>;
Calling for occurrences in a large databaseElement/>Is marked as first abnormal data;
Calling for occurrences in a large database Element/>Is noted as second exception data, wherein/>The method comprises the steps of setting an mth event keyword corresponding to an mth event keyword class in an event keyword library;
Calculation based on correlation calculation formula And/>Abnormal association indexes between the two;
The correlation calculation formula specifically comprises: ,
In the method, in the process of the invention, For/>And/>Abnormal relevance index between/(For the first abnormal data total number,/>Second abnormal data total,/>The total number of historical operation data of the gas system;
the event recognition module specifically comprises:
The standard event learning unit is used for determining standard parameter operation intervals of all events in the operation process of the gas system;
the event analysis unit is used for screening out a plurality of moments which do not accord with the standard parameter operation interval of the event in the event data of the gas system and recording the moments as abnormal moments;
the keyword extraction unit is used for extracting event abnormal values which correspond to abnormal moments and do not accord with the standard parameter operation interval of the event, and recording the event abnormal values as event keywords;
The determining the standard parameter operation interval of each event in the operation process of the gas system specifically comprises the following steps:
Acquiring a plurality of historical operation data corresponding to each event in the operation process of the gas system, and recording the historical operation data as sample data;
Based on the Grabbs criterion, eliminating abnormal data in the sample data to obtain a plurality of standard operation data corresponding to the event;
The average value and standard deviation of a plurality of standard operation data corresponding to the event are obtained, and the standard parameter operation interval of the event is that ,/>For the average value of a plurality of standard running data corresponding to the event,/>The standard deviation of a plurality of standard operation data corresponding to the event is obtained;
The expression of the glabros criterion is: ,
In the method, in the process of the invention, For the g-th sample data,/>For the average value of the sample data,/>Standard deviation of the sample data, total number of sample data,Is a significant level/>The value of the t-distribution below, if the expression of the glabros criterion is satisfied,/>Is abnormal data.
2. The fuel gas detection alarm system of claim 1, wherein the intelligent analysis module specifically comprises:
the event keyword classification unit is used for performing traversal search on the event keywords in the event data of each gas system in the event keyword library to obtain matched event keywords corresponding to the event keywords in the event data of each gas system;
The abnormal risk calculation unit is used for calculating event abnormal risk values corresponding to the event data of the gas system based on the abnormal relevance indexes of all the matched event keywords.
3. The gas detection alarm system according to claim 2, wherein the calculating the event abnormality risk value corresponding to the gas system event data based on the abnormality association indexes of all the matching event keywords specifically comprises:
combining all the matching event keywords in any pair to obtain a plurality of matching event keyword groups;
Determining an abnormal relevance index between two matched event keywords of each matched event keyword group, and marking the abnormal relevance index as an abnormal index of the matched event keyword group;
And accumulating the abnormal indexes of all the matched event key groups to obtain event abnormal risk values corresponding to the event data of the gas system.
4. The gas detection alarm system according to claim 3, wherein the outputting the protection pre-warning signal based on the abnormal risk of the event of the gas system specifically comprises:
Judging whether an event abnormal risk value corresponding to the event data of the gas system is larger than a preset value, if so, judging that the gas system has a fault event, outputting a protection early warning signal, and if not, judging that the gas system has no fault event, and not outputting the protection early warning signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410330936.4A CN117935519B (en) | 2024-03-22 | 2024-03-22 | Gas detection alarm system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410330936.4A CN117935519B (en) | 2024-03-22 | 2024-03-22 | Gas detection alarm system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117935519A CN117935519A (en) | 2024-04-26 |
CN117935519B true CN117935519B (en) | 2024-06-11 |
Family
ID=90766784
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410330936.4A Active CN117935519B (en) | 2024-03-22 | 2024-03-22 | Gas detection alarm system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117935519B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
GB201423300D0 (en) * | 2014-12-29 | 2015-02-11 | Sprue Safety Products Ltd | Multi alarm remote monitoring system |
EP3660611A1 (en) * | 2018-11-29 | 2020-06-03 | Siemens Aktiengesellschaft | Method, apparatus and system for managing alarms |
CN111859779A (en) * | 2020-06-05 | 2020-10-30 | 北京市燃气集团有限责任公司 | Early warning method and device for preventing third-party construction damage risk of gas pipe network |
CN114721336A (en) * | 2022-03-03 | 2022-07-08 | 上海核工程研究设计院有限公司 | Information security event early warning method for technological parameters of instrument control system |
CN116486585A (en) * | 2023-06-19 | 2023-07-25 | 合肥米视科技有限公司 | Production safety management system based on AI machine vision analysis early warning |
CN117235649A (en) * | 2023-11-09 | 2023-12-15 | 广东正德工业科技股份有限公司 | Industrial equipment state intelligent monitoring system and method based on big data |
CN117609762A (en) * | 2023-11-22 | 2024-02-27 | 重庆杰友电气材料有限公司 | Well lid early warning and monitoring method and system based on intelligent gas well |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11106789B2 (en) * | 2019-03-05 | 2021-08-31 | Microsoft Technology Licensing, Llc | Dynamic cybersecurity detection of sequence anomalies |
US11671435B2 (en) * | 2020-01-02 | 2023-06-06 | Code42 Software, Inc. | Process for automated investigation of flagged users based upon previously collected data and automated observation on a go-forward basis |
-
2024
- 2024-03-22 CN CN202410330936.4A patent/CN117935519B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
GB201423300D0 (en) * | 2014-12-29 | 2015-02-11 | Sprue Safety Products Ltd | Multi alarm remote monitoring system |
EP3660611A1 (en) * | 2018-11-29 | 2020-06-03 | Siemens Aktiengesellschaft | Method, apparatus and system for managing alarms |
CN111859779A (en) * | 2020-06-05 | 2020-10-30 | 北京市燃气集团有限责任公司 | Early warning method and device for preventing third-party construction damage risk of gas pipe network |
CN114721336A (en) * | 2022-03-03 | 2022-07-08 | 上海核工程研究设计院有限公司 | Information security event early warning method for technological parameters of instrument control system |
CN116486585A (en) * | 2023-06-19 | 2023-07-25 | 合肥米视科技有限公司 | Production safety management system based on AI machine vision analysis early warning |
CN117235649A (en) * | 2023-11-09 | 2023-12-15 | 广东正德工业科技股份有限公司 | Industrial equipment state intelligent monitoring system and method based on big data |
CN117609762A (en) * | 2023-11-22 | 2024-02-27 | 重庆杰友电气材料有限公司 | Well lid early warning and monitoring method and system based on intelligent gas well |
Also Published As
Publication number | Publication date |
---|---|
CN117935519A (en) | 2024-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106888205B (en) | Non-invasive PLC anomaly detection method based on power consumption analysis | |
CN111507376B (en) | Single-index anomaly detection method based on fusion of multiple non-supervision methods | |
CN109800127A (en) | A kind of system fault diagnosis intelligence O&M method and system based on machine learning | |
CN112863134B (en) | Intelligent diagnosis system and method for rural sewage treatment facility abnormal operation | |
CN110837866A (en) | XGboost-based electric power secondary equipment defect degree evaluation method | |
CN117235649B (en) | Industrial equipment state intelligent monitoring system and method based on big data | |
CN107436277A (en) | The single index data quality control method differentiated based on similarity distance | |
CN112990656B (en) | Health evaluation system and health evaluation method for IT equipment monitoring data | |
CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
CN112287988A (en) | Method for identifying water pollution source online monitoring data abnormity | |
CN113435759B (en) | Primary equipment risk intelligent assessment method based on deep learning | |
CN115296933B (en) | Industrial production data risk level assessment method and system | |
CN115883163A (en) | Network safety alarm monitoring method | |
CN111931849A (en) | Hydroelectric generating set operation data trend early warning method | |
CN113987908A (en) | Natural gas pipe network leakage early warning method based on machine learning method | |
CN112462734A (en) | Industrial production equipment fault prediction analysis method and model | |
CN112036087A (en) | Multi-strategy fused nuclear power key equipment fault diagnosis method and system | |
CN113128707A (en) | Situation risk assessment method for distribution automation terminal | |
CN112365186A (en) | Health degree evaluation method and system for electric power information system | |
CN115358647A (en) | Hydrogen energy industry chain risk monitoring system and monitoring method based on big data | |
CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
CN113065580B (en) | Power plant equipment management method and system based on multi-information fusion | |
CN114519382A (en) | Nuclear power plant key operation parameter extraction and abnormity monitoring method | |
CN117935519B (en) | Gas detection alarm system | |
CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |