CN105184386A - Method for establishing abnormal event early warning system based on expert experience and historical data - Google Patents
Method for establishing abnormal event early warning system based on expert experience and historical data Download PDFInfo
- Publication number
- CN105184386A CN105184386A CN201510435287.5A CN201510435287A CN105184386A CN 105184386 A CN105184386 A CN 105184386A CN 201510435287 A CN201510435287 A CN 201510435287A CN 105184386 A CN105184386 A CN 105184386A
- Authority
- CN
- China
- Prior art keywords
- variable
- early warning
- warning system
- anomalous event
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Alarm Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for establishing an abnormal event early warning system based on expert experience and historical data. The method includes three steps; a model is established offline in the first two steps; and the model is applied in real time and offline in the third step. According to the method, alarm data are continuously acquired, and the expert experience is used in combination, and therefore, an abnormal event early warning system is updated regularly; the system is implemented online, and the state change of variables are continuously monitored; the probability of abnormal events which may occur is predicted in real time, and root causes causing deviation are analyzed continuously; and an operator can be timely informed of the change of the system, and therefore, the operator can be assisted to take appropriate measures in time. With the Bayesian network-based early warning system management method adopted, the randomness and uncertainty of a real process can be embodied, and complexity of consideration on all variables in process knowledge modeling can be omitted, and correlativity between monitoring variables can be reflected, and discovery and judgment of fault sources can be benefitted for the operator.
Description
Technical field
The present invention relates to chemical field, in particular to a kind of method setting up anomalous event early warning system in conjunction with expertise and historical data.
Background technology
In industrial enterprise in early days, control system is comparatively simple, and each alerting signal is all be directly connected to Central Control Room by rigid line, but the method cost is higher, safeguards complicated, cannot reach good result of use.Widely use along with programmable logic controller (PLC) (PLC), field bus control system (FCS) and Distributed Control System (DCS) (DCS) etc. obtain, commercial production is achieved day by day complicated, maximization.Meanwhile, the loss that industrial accident causes also causes the attention of people further, because it not only can affect prestige and the benefit of enterprise, and greatly can affect the overall development of related industry.And countries in the world still cannot avoid the generation of anomalous event in commercial production so far.
In the process industrial in modern times, single control method such as closed-loop control, serials control is used by maturation, the fault diagnosis of single-point warning and local system is also very ripe, it is to obtaining alerting signal quickly and easily, improve security of system to play an important role, however the surge of warning quantity and unordered its effect in fault diagnosis that but makes unsatisfactory.
In industrial O&M process, for enhancing productivity, creating more high benefit, reducing industrial accident incidence, reduce the negative effect that security incident is brought, the staff of each specialty to instrument, equipment etc. from technique, material all constantly to improve and is optimizing.Anomalous event is carried out to the method for early warning, operating personnel are made before process units sends warning, generation loss and studies and judges and take measures.Maximum minimizing shut down time and loss of income, the personal safety of safeguard work personnel.
But the expansion of system scale and the simplification of signals collecting, make operating personnel need in the face of a large amount of system informations.How to utilize data generally collected in process of production to carry out early warning to anomalous event, become the important research direction in alarming and managing field.
Summary of the invention
The invention provides a kind of method setting up anomalous event early warning system in conjunction with expertise and historical data, in order to the anomalous event of Timeliness coverage system, and provide the warning message based on event and occurrence cause thereof, improve the performance of warning system with this.
For achieving the above object, the invention provides a kind of method setting up anomalous event early warning system in conjunction with expertise and historical data, comprehensive expertise, excavate the information in alarm logging historical data simultaneously, set up the anomalous event early warning system based on Bayesian network, improve warning system based on this, the method comprises the following steps:
The first step, identifies anomalous event scene, is specially:
Step 1.1, accepts user according to expertise and identifies contingent anomalous event in chemical system by dangerous acupoint, and determines that the extent of injury is huge, affects serious hazard event;
Step 1.2, determines the monitored variable associated with these hazard events;
Step 1.3, identifies the scene of event correlation, the combination of state when namely event occurs residing for all associated variables;
Second step, set up the model of anomalous event early warning system, be specially:
Step 2.1, collects the historical data of alarm procedure;
Step 2.2, the bayesian network structure of Learning-memory behavior variable, sets up the directed acyclic graph comprising correlationship qualitatively between monitored variable;
Step 2.3, the Bayesian network parameters of Learning-memory behavior variable, obtains the conditional probability table between the distributions of variable and correlated variables, namely quantitative between different variable condition dependence;
Step 2.4, accept user and add main matter variable to the Bayesian network of monitored variable according to expertise, using the probability of happening of main matter as variable node, add Bayesian network to, afterwards, contacting between main matter and associated monitoring variable is set up;
Step 2.5, sets up the Bayesian network model comprising monitored variable and main matter, calculates the parameter of all variablees;
3rd step, implement anomalous event WARNING IN ADVANCE SYSTEM MODEL, comprising:
Step 3.1, whether the state of real-time judge monitored variable changes;
Step 3.2, when the state of monitored variable changes, as observation evidence, upgrades the probability of happening of main matter;
Step 3.3, judges the probability of happening of main matter, and after probability is greater than the setting value upper limit, diagnosis causes the basic reason of current scene;
Step 3.4, provides appropriate affair alarm and basic reason thereof, the change occurred in handled easily personnel understanding process, and takes necessary measure in time, avoids issuable anomalous event to occur.
Further, the first step in said method, second step are the processes of off-line Modling model, and the 3rd step is the process of online real-time application model; Continuous collection alert data, in conjunction with expertise, regular update anomalous event early warning system, this anomalous event early warning system of on-line implement afterwards, the state change of continuous surveillance variable, the probability of the contingent anomalous event of real-time estimate, constantly analyzes the basic reason causing deviation, notify the phylogenetic change of operating personnel in time, handled easily personnel adopt appropriate measures in time.
The present invention combines expertise, excavate the knowledge in alarm logging historical data simultaneously, and then the anomalous event early warning system set up based on Bayesian network, for the anomalous event of Timeliness coverage system, and the warning message provided based on event and occurrence cause thereof, improves the performance of warning system with this.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the method flow diagram setting up anomalous event early warning system in conjunction with expertise and historical data of one embodiment of the invention;
Fig. 2 is the water tank alarm system schematic diagram of one embodiment of the invention;
Fig. 3 is the directed acyclic graph of water tank alarm system the best of one embodiment of the invention;
Fig. 4 is correlationship and the parameter schematic diagram of the variable of water tank alarm system of the present invention;
Fig. 5 is the monitored variable of water tank alarm system of the present invention and the correlationship schematic diagram of main matter;
Fig. 6 a ~ Fig. 6 d is the change in process schematic diagram that water tank alarm system of the present invention occurs in the anomalous event early warning system set up.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not paying the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is the method flow diagram setting up anomalous event early warning system in conjunction with expertise and historical data of one embodiment of the invention; As shown in Figure 1, the method comprises the following steps:
The first step, identifies anomalous event scene, is specially:
Step 1.1, identifies contingent anomalous event in chemical system by dangerous acupoint, and determines that the extent of injury is huge, affects serious event;
Step 1.2, determines the monitored variable with these event correlations;
Step 1.3, identifies the scene of event correlation, the combination of state when namely event occurs residing for all associated variables.
Second step, set up the model of anomalous event early warning system, be specially:
Step 2.1, collects the historical data of alarm procedure;
Step 2.2, the bayesian network structure of Learning-memory behavior variable, sets up the directed acyclic graph comprising correlationship qualitatively between monitored variable;
Step 2.3, the Bayesian network parameters of Learning-memory behavior variable, obtains the conditional probability table between the distributions of variable and correlated variables, namely quantitative between different variable condition dependence;
Step 2.4, adds main matter variable to the Bayesian network of monitored variable according to expertise, using the probability of happening of main matter as variable node, adds Bayesian network to, afterwards, set up contacting between main matter and associated monitoring variable;
Step 2.5, sets up the Bayesian network model comprising monitored variable and main matter, calculates the parameter of all variablees.
3rd step, implement anomalous event WARNING IN ADVANCE SYSTEM MODEL, mainly comprise:
Step 3.1, whether the state of real-time judge monitored variable changes;
Step 3.2, when the state of monitored variable changes, as observation evidence, upgrades the probability of happening of main matter;
Step 3.3, judges the probability of happening of main matter, and after probability is greater than the setting value upper limit, diagnosis causes the basic reason of current scene;
Step 3.4, provides appropriate affair alarm and basic reason thereof, the change occurred in handled easily personnel understanding process, and takes necessary measure in time, avoids issuable anomalous event to occur.
Wherein the first step, second step are the processes of off-line Modling model, and the 3rd step is the process of online real-time application model.Continuous collection alert data, in conjunction with expertise, regular update anomalous event early warning system, this system of on-line implement afterwards, the state change of continuous surveillance variable, the probability of the contingent anomalous event of real-time estimate, constantly analyzes the basic reason causing deviation, notify the phylogenetic change of operating personnel in time, handled easily personnel adopt appropriate measures in time.
Compared with prior art, the invention has the beneficial effects as follows:
By in conjunction with expertise and alarm logging historical data, set up anomalous event early warning system, use the form of network, describe correlationship complicated between monitored variable and the relation between monitored variable and event; Use Bayesian inference method to upgrade in time the contingent probability of event, use the diagnostic method of Bayesian network accurately to locate basic reason; The probability occur event and basic reason send to operating personnel as alarm content, and handled easily personnel understand the state of system in time, and then adopt appropriate measures.
Below in conjunction with water tank alarm system, set forth the step that the present invention's specific embodiment comprises.
Fig. 2 is the water tank alarm system schematic diagram of one embodiment of the invention, builds this water tank alarm system and comprises the following steps:
The first step, identifies anomalous event scene, is specially:
Step 1.1, accepts user according to expertise and identifies contingent anomalous event in chemical system by dangerous acupoint, and determines that the extent of injury is huge, affects serious hazard event;
Step 1.2, determines the monitored variable associated with these hazard events;
Step 1.3, identifies the scene of event correlation, the combination of state when namely event occurs residing for all associated variables.
Carry out dangerous acupoint to cistern system, find monitored variable and the state thereof of event and the association mainly paid close attention to, result is as shown in table 1, and in cistern system, main matter is that water tank overflows, and water tank dries up.
The dangerous acupoint of table 1. cistern system and the result of event variable scene analysis
Second step, set up the model of anomalous event early warning system, be specially:
Step 2.1, collects the historical data of alarm procedure;
The alert data of cistern system synthesis is as shown in table 2.
The water tank DCS system alert data that table 2. synthesizes
*NR:meansreturntonormalsituation.
Step 2.2, the bayesian network structure of Learning-memory behavior variable, sets up the directed acyclic graph comprising correlationship qualitatively between monitored variable;
By the historical data that analysis monitoring variable is reported to the police, find best directed acyclic graph as shown in Figure 3.In theory, the directed acyclic graph result of Fig. 3, has maximum probability and generates the alert data collection observed.Wherein, in Fig. 3-Fig. 6 d, L represents Level (liquid level), I represents Inlet (inlet flow rate), O represents Outlet (rate of discharge), and Of represents Overflow (spilling), and Rd represents Rundry (drying up), P represents Present (probability of happening), and A represents Absent (not probability of happening).
Step 2.3, the Bayesian network parameters of Learning-memory behavior variable, obtains the conditional probability table between the distributions of variable and correlated variables, namely quantitative between different variable condition dependence;
When given alert data collection, use the method for maximal possibility estimation, set up the optimization problem of the parameter estimating Bayesian network.By solving-optimizing problem, obtain best estimated parameter, in this problem, result of calculation is as shown in table 3 to table 6.As shown in Figure 4, Fig. 4 is correlationship and the parameter schematic diagram of the variable of water tank alarm system of the present invention to node diagram.
The parameter of table 3. inlet flow rate (Inlet)
The parameter of table 4. rate of discharge (Outlet)
The parameter of table 5. liquid level (Level)
The conditional probability table of table 6. liquid level (Level)
Step 2.4, adds main matter variable to the Bayesian network of monitored variable according to expertise, using the probability of happening of main matter as variable node, adds Bayesian network to, afterwards, set up contacting between main matter and associated monitoring variable; Fig. 5 is the monitored variable of water tank alarm system of the present invention and the correlationship of main matter;
Step 2.5, sets up the Bayesian network model comprising monitored variable and main matter, calculates the parameter of all variablees.
The probability (according to expertise) of main matter is there is under the different variable combination condition of table 7.
3rd step, implement anomalous event WARNING IN ADVANCE SYSTEM MODEL, mainly comprise:
Step 3.1, whether the state of real-time judge monitored variable changes;
Step 3.2, when the state of monitored variable changes, as observation evidence, upgrades the probability of happening of main matter;
Step 3.3, judges the probability of happening of main matter, and after probability is greater than the setting value upper limit, diagnosis causes the basic reason of current scene;
Step 3.4, provides appropriate affair alarm and basic reason thereof, the change occurred in handled easily personnel understanding process, and takes necessary measure in time, avoids issuable anomalous event to occur.
With the situation after the anomalous event early warning system on-line implement set up in Imitating second step, along with the continuous operation of system, the monitored variable in system constantly changes.Here suppose it is first that liquid level (Level) constantly reduces, lower than the lower limit of setting, send warning, the state of demonstrating is LO; Afterwards, inlet flow rate (Inlet) is lower than setting value, and state is LO; Finally, rate of discharge (Outlet) is higher than the upper limit, and state is HI.In traditional DCS system, this change procedure is by generation three alarm loggings, as shown in table 8.
The DCS alarm logging data that table 8. is traditional
Same change procedure, the process occurred in the anomalous event early warning system set up as shown in Figure 6.As shown in Figure 6 a, this is the early warning system set up based on historical data and expertise to original state.When the fluid level condition of water tank becomes LO, using this state change process as new evidence, the early warning system that input is set up, utilize the inference mechanism of Bayesian network, the probability of happening of all events upgrades accordingly, the probability that water tank overflows is reduced to 29% by 41%, and dry probability has 49% increase by 60%, as shown in Figure 6 b.The possible cause of this change is caused to be rate of discharge higher (possibility 51%), inlet flow rate normal (possibility is 72%), therefore, most possible basic reason is flow normal (now more wishing that the state of inlet flow rate is for high).Like this, in the early warning system of anomalous event, when the state of system changes, the probability of the contingent anomalous event of system can upgrade in time, and causes the most possible reason of this change also can be found by reasoning.
Same, when the state of inlet flow rate (Inlet) becomes low (LO), the probability of the main matter of corresponding renewal system, the probability that water tank dries up is increased to 83% by 60%, as fig. 6 c.Now, the probability of the event that water tank dries up is higher than acceptable setting value (being assumed to 70%), so early warning system sends the early warning information of water tank dry (possibility is 83%) to operator.
When system changes further, when the state of rate of discharge (Outlet) becomes height (HI), upgrade the probability of all events, the possibility that water tank dries up increases further, is increased to 90%, as shown in fig 6d by 83%.Now, early warning system can continue the early warning information sending water tank dry (possibility is 90%) to operator.Remind the state of operator's current system, handled easily person take appropriate measures.
Set up in the method for anomalous event early warning system in conjunction with expertise and historical data above-mentioned, the first step, second step are the processes of off-line Modling model, and the 3rd step is the process of online real-time application model.Continuous collection alert data, in conjunction with expertise, regular update anomalous event early warning system, this system of on-line implement afterwards, the state change of continuous surveillance variable, the probability of the contingent anomalous event of real-time estimate, constantly analyzes the basic reason causing deviation, notify the phylogenetic change of operating personnel in time, handled easily personnel adopt appropriate measures in time.
The outstanding advantages of the above-mentioned early warning system management method based on Bayesian network is, it embodies randomness and the uncertainty of real processes, eliminate procedural knowledge modeling and consider the loaded down with trivial details of all variablees, particularly reflect the correlationship between monitored variable, be conducive to operating personnel and find and failure judgement source.
One of ordinary skill in the art will appreciate that: accompanying drawing is the schematic diagram of an embodiment, the module in accompanying drawing or flow process might not be that enforcement the present invention is necessary.
One of ordinary skill in the art will appreciate that: the module in the device in embodiment can describe according to embodiment and be distributed in the device of embodiment, also can carry out respective change and be arranged in the one or more devices being different from the present embodiment.The module of above-described embodiment can merge into a module, also can split into multiple submodule further.
Last it is noted that above embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in previous embodiment, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of embodiment of the present invention technical scheme.
Claims (2)
1. set up the method for anomalous event early warning system in conjunction with expertise and historical data for one kind, it is characterized in that, comprehensive expertise, excavate the information in alarm logging historical data simultaneously, set up the anomalous event early warning system based on Bayesian network, improve warning system based on this, the method comprises the following steps:
The first step, identifies anomalous event scene, is specially:
Step 1.1, accepts user according to expertise and identifies contingent anomalous event in chemical system by dangerous acupoint, and determines that the extent of injury is huge, affects serious hazard event;
Step 1.2, determines the monitored variable associated with these hazard events;
Step 1.3, identifies the scene of event correlation, the combination of state when namely event occurs residing for all associated variables;
Second step, set up the model of anomalous event early warning system, be specially:
Step 2.1, collects the historical data of alarm procedure;
Step 2.2, the bayesian network structure of Learning-memory behavior variable, sets up the directed acyclic graph comprising correlationship qualitatively between monitored variable;
Step 2.3, the Bayesian network parameters of Learning-memory behavior variable, obtains the conditional probability table between the distributions of variable and correlated variables, namely quantitative between different variable condition dependence;
Step 2.4, accept user and add main matter variable to the Bayesian network of monitored variable according to expertise, using the probability of happening of main matter as variable node, add Bayesian network to, afterwards, contacting between main matter and associated monitoring variable is set up;
Step 2.5, sets up the Bayesian network model comprising monitored variable and main matter, calculates the parameter of all variablees;
3rd step, implement anomalous event WARNING IN ADVANCE SYSTEM MODEL, comprising:
Step 3.1, whether the state of real-time judge monitored variable changes;
Step 3.2, when the state of monitored variable changes, as observation evidence, upgrades the probability of happening of main matter;
Step 3.3, judges the probability of happening of main matter, and after probability is greater than the setting value upper limit, diagnosis causes the basic reason of current scene;
Step 3.4, provides appropriate affair alarm and basic reason thereof, the change occurred in handled easily personnel understanding process, and takes necessary measure in time, avoids issuable anomalous event to occur.
2. the method setting up anomalous event early warning system in conjunction with expertise and historical data according to claim 1, is characterized in that, wherein the first step, second step are the processes of off-line Modling model, and the 3rd step is the process of online real-time application model; Continuous collection alert data, in conjunction with expertise, regular update anomalous event early warning system, this anomalous event early warning system of on-line implement afterwards, the state change of continuous surveillance variable, the probability of the contingent anomalous event of real-time estimate, constantly analyzes the basic reason causing deviation, notify the phylogenetic change of operating personnel in time, handled easily personnel adopt appropriate measures in time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510435287.5A CN105184386A (en) | 2015-07-22 | 2015-07-22 | Method for establishing abnormal event early warning system based on expert experience and historical data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510435287.5A CN105184386A (en) | 2015-07-22 | 2015-07-22 | Method for establishing abnormal event early warning system based on expert experience and historical data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105184386A true CN105184386A (en) | 2015-12-23 |
Family
ID=54906449
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510435287.5A Pending CN105184386A (en) | 2015-07-22 | 2015-07-22 | Method for establishing abnormal event early warning system based on expert experience and historical data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105184386A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740989A (en) * | 2016-02-03 | 2016-07-06 | 杭州电子科技大学 | Water supply pipe network abnormal event detection method based on VARX (a Vector Auto-Regressive with eXogenous variables) models |
CN106384154A (en) * | 2016-08-18 | 2017-02-08 | 广州市迪士普音响科技有限公司 | Self-checking and fault self-processing method and system of intelligent platform |
CN107689956A (en) * | 2017-08-31 | 2018-02-13 | 北京奇安信科技有限公司 | The intimidation estimating method and device of a kind of anomalous event |
CN107958289A (en) * | 2016-10-18 | 2018-04-24 | 深圳光启合众科技有限公司 | Data processing method and device, robot for robot |
CN108241295A (en) * | 2016-12-23 | 2018-07-03 | Abb股份公司 | For the adaptive modeling method and system of the building energy control based on MPC |
CN109660419A (en) * | 2018-10-08 | 2019-04-19 | 平安科技(深圳)有限公司 | Predict method, apparatus, equipment and the storage medium of network equipment exception |
CN110222936A (en) * | 2019-05-09 | 2019-09-10 | 阿里巴巴集团控股有限公司 | A kind of root of business scenario is because of localization method, system and electronic equipment |
WO2020172913A1 (en) * | 2019-02-28 | 2020-09-03 | 东北大学 | Production index visual monitoring system and method based on configuration |
CN112072642A (en) * | 2020-08-19 | 2020-12-11 | 厦门盈盛捷电力科技有限公司 | Method for estimating abnormal operation state of power system |
CN112085200A (en) * | 2016-08-29 | 2020-12-15 | 韩国水力原子力株式会社 | Method and system for pre-detecting signs of abnormality in nuclear power plant equipment including process for determining equipment importance and alarm validity |
CN112415894A (en) * | 2020-11-20 | 2021-02-26 | 中国矿业大学 | Active learning and BN (boron nitride) -based heavy medium coal preparation process safe operation control method |
CN113554224A (en) * | 2021-07-20 | 2021-10-26 | 上海航天测控通信研究所 | Fault diagnosis method and system combining multipoint statistics with health trend prediction |
CN113642986A (en) * | 2021-08-02 | 2021-11-12 | 上海示右智能科技有限公司 | Method for constructing digital notarization |
CN114295936A (en) * | 2021-12-31 | 2022-04-08 | 合肥联信电源有限公司 | Power grid voltage detection system and method applied to static switch |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07234861A (en) * | 1994-02-24 | 1995-09-05 | Toshiba Corp | Data monitoring system |
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 |
CN104238545A (en) * | 2014-07-10 | 2014-12-24 | 中国石油大学(北京) | Fault diagnosis and pre-warning system in oil refining production process and establishment method thereof |
-
2015
- 2015-07-22 CN CN201510435287.5A patent/CN105184386A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07234861A (en) * | 1994-02-24 | 1995-09-05 | Toshiba Corp | Data monitoring system |
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 |
CN104238545A (en) * | 2014-07-10 | 2014-12-24 | 中国石油大学(北京) | Fault diagnosis and pre-warning system in oil refining production process and establishment method thereof |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740989A (en) * | 2016-02-03 | 2016-07-06 | 杭州电子科技大学 | Water supply pipe network abnormal event detection method based on VARX (a Vector Auto-Regressive with eXogenous variables) models |
CN105740989B (en) * | 2016-02-03 | 2019-09-27 | 杭州电子科技大学 | A kind of water supply network anomalous event method for detecting based on VARX model |
CN106384154A (en) * | 2016-08-18 | 2017-02-08 | 广州市迪士普音响科技有限公司 | Self-checking and fault self-processing method and system of intelligent platform |
CN112085200A (en) * | 2016-08-29 | 2020-12-15 | 韩国水力原子力株式会社 | Method and system for pre-detecting signs of abnormality in nuclear power plant equipment including process for determining equipment importance and alarm validity |
CN107958289A (en) * | 2016-10-18 | 2018-04-24 | 深圳光启合众科技有限公司 | Data processing method and device, robot for robot |
CN107958289B (en) * | 2016-10-18 | 2022-02-01 | 深圳市中吉电气科技有限公司 | Data processing method and device for robot and robot |
CN108241295A (en) * | 2016-12-23 | 2018-07-03 | Abb股份公司 | For the adaptive modeling method and system of the building energy control based on MPC |
CN107689956B (en) * | 2017-08-31 | 2020-12-01 | 奇安信科技集团股份有限公司 | Threat assessment method and device for abnormal event |
CN107689956A (en) * | 2017-08-31 | 2018-02-13 | 北京奇安信科技有限公司 | The intimidation estimating method and device of a kind of anomalous event |
CN109660419A (en) * | 2018-10-08 | 2019-04-19 | 平安科技(深圳)有限公司 | Predict method, apparatus, equipment and the storage medium of network equipment exception |
WO2020172913A1 (en) * | 2019-02-28 | 2020-09-03 | 东北大学 | Production index visual monitoring system and method based on configuration |
CN110222936A (en) * | 2019-05-09 | 2019-09-10 | 阿里巴巴集团控股有限公司 | A kind of root of business scenario is because of localization method, system and electronic equipment |
CN110222936B (en) * | 2019-05-09 | 2023-08-29 | 创新先进技术有限公司 | Root cause positioning method and system of business scene and electronic equipment |
CN112072642A (en) * | 2020-08-19 | 2020-12-11 | 厦门盈盛捷电力科技有限公司 | Method for estimating abnormal operation state of power system |
CN112415894A (en) * | 2020-11-20 | 2021-02-26 | 中国矿业大学 | Active learning and BN (boron nitride) -based heavy medium coal preparation process safe operation control method |
CN113554224A (en) * | 2021-07-20 | 2021-10-26 | 上海航天测控通信研究所 | Fault diagnosis method and system combining multipoint statistics with health trend prediction |
CN113554224B (en) * | 2021-07-20 | 2022-11-25 | 上海航天测控通信研究所 | Fault diagnosis method and system combining multipoint statistics with health trend prediction |
CN113642986A (en) * | 2021-08-02 | 2021-11-12 | 上海示右智能科技有限公司 | Method for constructing digital notarization |
CN113642986B (en) * | 2021-08-02 | 2024-04-16 | 上海示右智能科技有限公司 | Method for constructing digital notarization |
CN114295936A (en) * | 2021-12-31 | 2022-04-08 | 合肥联信电源有限公司 | Power grid voltage detection system and method applied to static switch |
CN114295936B (en) * | 2021-12-31 | 2023-08-22 | 合肥联信电源有限公司 | Power grid voltage detection system and method applied to static switch |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105184386A (en) | Method for establishing abnormal event early warning system based on expert experience and historical data | |
US10013866B2 (en) | Production equipment monitoring method and system | |
CN106655522B (en) | A kind of main station system suitable for electric grid secondary equipment operation management | |
CN108873842B (en) | One-stop unattended pump station automatic control system | |
CN105163091B (en) | Pump station engineering management integrated linkage system | |
CN103744389A (en) | Operating state early-warning method of oil and gas production equipment | |
CN106655158A (en) | Smart grid based distribution network self-healing control system and method | |
CN106774187B (en) | The system and method for automatic monitoring production line beat | |
CN111401582A (en) | Abnormity identification method and monitoring platform for domestic sewage treatment facility | |
CN106779595A (en) | A kind of electric company early can system figure display platform | |
CN112394682A (en) | Thermal cracking steam boiler linkage control system | |
CN113340344A (en) | Hydraulic climbing mould intelligent monitoring control early warning system based on digital twin technology | |
CN113506010A (en) | Large-scale watershed hydropower station flood discharge gate digital centralized regulation and control method | |
CN108981785A (en) | A kind of intelligent Detection of coal breaker equipment safety | |
CN204485168U (en) | A kind of fire-fighting automatic inspection device | |
CN115220403A (en) | Configurable intelligent monitoring early warning and fault diagnosis system for thermal power plant | |
CN106444685A (en) | Distributed control system and method of distributed control system for dynamic scheduling resources | |
KR101627206B1 (en) | System and method for providing smart water grid service | |
CN117423201A (en) | Intelligent fire-fighting state monitoring method and system for restaurant | |
CN112291303A (en) | Multidirectional distance dynamic monitoring and early warning method based on edge calculation | |
CN202798762U (en) | Alarm device for power communication failure information analysis | |
CN207676153U (en) | Sewage disposal process supervisory systems | |
CN113684868B (en) | City utility tunnel early warning system | |
CN105809257B (en) | Trigger type state maintenance method based on power communication network | |
CN114623281A (en) | Pipeline prediction analysis alarm system and use method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151223 |
|
RJ01 | Rejection of invention patent application after publication |