CN109327330A - Chemical Manufacture Exceptional Slices management method based on data-driven - Google Patents
Chemical Manufacture Exceptional Slices management method based on data-driven Download PDFInfo
- Publication number
- CN109327330A CN109327330A CN201811058446.4A CN201811058446A CN109327330A CN 109327330 A CN109327330 A CN 109327330A CN 201811058446 A CN201811058446 A CN 201811058446A CN 109327330 A CN109327330 A CN 109327330A
- Authority
- CN
- China
- Prior art keywords
- matrix
- position number
- data
- exceptional
- incidence matrix
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The Chemical Manufacture Exceptional Slices management method based on data-driven that the present invention relates to a kind of, the described method comprises the following steps: step 1 realizes the acquisition to each position number using sensor；Step 2 contraposition number carries out periodical association analysis, obtains the incidence matrix of different moments；Step 3 a certain moment, target position number are alarmed, are made the difference by the time, find out and alarm moment immediate incidence matrix；Step 4 calculates the similarity of incidence matrix and historical context matrix, obtains the highest one group of historical context matrix of similarity；Step 5 recalls the most like corresponding historical operation of historical context matrix, is sent to operator；After this alarm of step 6 solves, get off to be formed knowledge slice for the operation note of incidence matrix and operator to be put into historical data base, this method gets rid of the defect of the single warning message of tradition, the relevant parameter for finding out alarm parameters is calculated by incidence matrix, operator can obtain more failure decision-making foundations and operation foundation according to relevant parameter.
Description
Technical field
The present invention relates to a kind of slice management methods, and in particular to a kind of Chemical Manufacture Exceptional Slices based on data-driven
Management method belongs to Chemical Manufacture control technology field.
Background technique
Chemical production process is high-risk process, and parameter is numerous, and operator needs resident control room foundation DCS system interface,
By observing parameter in real time to understand production status variation in time, this traditional management mode of operation is limited by time, place,
Passivity is stronger.For the process of Chemical Manufacture because parameter is more, process diversity, process is complicated, needs to provide to operator flexible
Technical operation scheme, to cope with chemical production process complicated and changeable.
Currently, the main method of management position number is operator by the observation interface DCS and receives corresponding one-parameter alarm
Information.The warning message that this chemical process accident prevention management method is obviously lagged and provided is single, the process of Chemical Manufacture
Because parameter is more, process diversity, process is complicated, is difficult to establish accurately priori knowledge library.And more phases are provided to operator
Parameter information and relevant operation foundation are closed, then the decision process for judging for shortening accident and accelerating processing provides possibility, therefore, compels
That cuts needs a kind of new scheme to solve the technical problem.
Summary of the invention
The present invention exactly for the technical problems in the prior art, provides a kind of Chemical Manufacture based on data-driven
Exceptional Slices management method, the technical solution periodically calculate the incidence matrix of target position number, determine one group of parameter, usually
2-3.When a certain moment target position number is alarmed, by the incidence matrix at moment of alarming and historical context matrix progress similitude
Calculate, find with the most similar historical context matrix of current incidence matrix, then by this corresponding alarm detail of history matrix and
Correlation experience is pushed to operator by mobile terminal.After trouble shooting, accident details and experience are recorded, and are this time closed
Join in matrix deposit database and is used as historical context matrix, the judgment basis as next similar fault.
To achieve the goals above, technical scheme is as follows: a kind of Chemical Manufacture based on data-driven is abnormal
It is sliced management method, the described method comprises the following steps:
Step 1 realizes the acquisition to each position number using sensor；
Step 2 contraposition number carries out periodical association analysis, obtains the incidence matrix of different moments；
Step 3 a certain moment, target position number are alarmed, are made the difference by the time, find out and alarm moment immediate pass
Join matrix；
Step 4 calculates the similarity of incidence matrix and historical context matrix, obtains the highest one group of historical context of similarity
Matrix；
Step 5 recalls the most like corresponding historical operation of historical context matrix, is sent to operator；
After this alarm of step 6 solves, the operation note of incidence matrix and operator are got off to be formed knowledge slice and is put into and goes through
Control information in history database, as the following parameter alarm.
As an improvement of the present invention, detailed process is as follows for the step 2: calculating alarm using correlation calculations method
Position number has relevance with which position number；Specific calculation method:
In normal productive process, every 12 hours (or other times period) calculate once occurs strong close with target position number
The position number of connection simultaneously forms incidence matrix,
As an improvement of the present invention, the step 3 is specific as follows, when target position number is alarmed, by warning message
It is sent to operator, and is recalled and alarm moment immediate incidence matrix from database.
As an improvement of the present invention, the incidence matrix of mahalanobis distance calculating target position number and which step 4 utilize
A historical context matrix is most close.
As an improvement of the present invention, the step 5 remembers the corresponding accident description of this historical context matrix and experience
Record is presented to operator, and the operation as operator is referring to information.
As an improvement of the present invention, the step 6: after trouble shooting, by alarm parameters incidence matrix with it is corresponding
Accident description and experience record are put into historical data base, the comparison letter of incidence matrix when alarming as next target position number
Breath and corresponding operation guidance.
As an improvement of the present invention, the message of the step 3 and step 5 push is all that behaviour is shown to by mobile terminal
Work person, and have individual operation function i.e. in mobile terminal: whether open the switch for receiving alarm pushed information.
As an improvement of the present invention, calculating in the step 2) has strongly connected position matrix with target position number, then
It is calculated by related coefficient algorithm and changes the biggish other parameters of correlation with target position number, target position number indicated with x, y generation
Refer to that other participate in k position number of correlation calculations, calculating the related coefficient x=[x1, x2, x3 ... xn], y of x and y firstk=
[yk1,yk2,yk3,…ykn] (k=1 ... h), by x, yknBand formula 1, calculates the related coefficient of the two,
In statistics, the degree of correlation between two variables is described in quantity with " related coefficient ", with symbol " r " come
It indicates.Related coefficient value range is limited to: -1≤r≤1；
The meaning that related coefficient indicates；
| Related coefficient | 0.00 | 0.00…±0.3 | ±0.30…±0.50 | ±0.50…±0.80 | ±0.80…±1.00 |
| Degree of correlation | Without correlation | Micro- positive negative correlation | It is real positive negatively correlated | It is significant positive negatively correlated | Height is positive negatively correlated |
Take the absolute value of r to be greater than 0.8 coefficient as strong incidence coefficient here.
As an improvement of the present invention, a certain moment calculates this when target position number is alarmed in the step 4
Then the incidence matrix of moment this number carries out similarity calculation with the historical context matrix of this number, find out similarity maximum
One group of historical context matrix, incidence matrix at this time and historical context matrix similarity calculate and use mahalanobis distance algorithm: this
In with x for feeling the pulse with the finger-tip mark number, strong incidence matrix when alarming is A=[x, a1,a2…am]T, some historical context matrix
P=[x, p1,p2…pm], E is the covariance matrix of A, P matrix, then A is at a distance from P are as follows:
Then D value hour corresponding historical context matrix and incidence matrix A are most like, by this corresponding thing of historical context matrix
Therefore description and experience record are presented to operator.And preserved this incidence matrix as slice, become historical context matrix,
Foundation is operated for similar failed operation next time.
Compared with the existing technology, the invention has the advantages that, 1) technical scheme steps 2 close the parameter of acquisition
The analysis of connection property, then calculates relevant parameter matrix, and this method gets rid of the defect of the single warning message of tradition, passes through incidence matrix
Calculate and find out the relevant parameters of alarm parameters, operator according to relevant parameter can obtain more failure decision-making foundations and operation according to
According to；2) step 3 of the program periodically calculates the incidence matrix of target position number, records the correspondence time of incidence matrix generation.
Chemical process parameter is numerous and process has diversity, periodically calculates the incidence matrix of target position number, guarantees incidence matrix
Timeliness meets chemical process production actual conditions, and facilitates step 4 to rapidly find out and most connect with target position number generation time of fire alarming
Close incidence matrix；3) step 4 of the program finds out incidence matrix and which historical context matrix is most like, because of chemical process
Middle liquid, enterprise, solid, pressure and other parameters dimension are numerous, and mahalanobis distance is not influenced by dimension, the geneva between two o'clock away from
It is unrelated from the measurement unit of initial data.It is calculated and the most like historical context square of incidence matrix using mahalanobis distance algorithm
Battle array, the technical program uses big data method and the mode of thinking abundant digging utilization historical data value, from numerous history squares
Found out in battle array with incidence matrix historical context matrix the most similar, its corresponding operation and suggestion are applied in present production pipe
In control；4) step 5 of the program recalls the operation of most like historical context matrix, occurs to administrator, according to alarm parameters
Information, administrator itself has a set of operation rules and regulations according to itself professional standing and experience, and is recalled according to historical context matrix
Corresponding historical operation detailed rules and regulations, provide enough information to alarm failure processing, administrator has richer reliable
Operate foundation.The experiential operating of warning message and history similar fault record is sent to administrator, establishing by mobile terminal
The connection of work process and people is able to achieve the fast and effective publication of abnormal conditions by mobile interchange, and help promotes chemical process pipe
Control efficiency；5) after the final operator of the step 6 of the program, administrator solve this failure, the operation note of administrator is got off
And be put into historical data base with alert correlation matrix, a knowledge slice is formed, is judged by the similitude of Exceptional Slices, is filled
Divide digging utilization historical data value, provides more operation foundations for following certain position number alarm；6) technical solution retains
Incidence matrix and the storage of corresponding operation rules and regulations in the database, enrich historical data amount, increase next matrix similarity and calculate
Accuracy, that is, enhance this technology operating effect.
Traditional DCS system is merely given as the warning message of single parameter, and warning message is single, and administrator will often pass through
Sturdy professional knowledge and experience accumulation abundant, and the acquisition of warning message is entangled in control room.The report of this technical solution
The operation for the similar alarm of associated bit information, history that alert pushed information can obtain in mobile terminal and give alarm bit number is built
View, enriches the judgment basis of accident pattern.The meaning of this scheme is to record historical operation information by mobile interchange
Come, form knowledge slice, suggestion for operation is provided to the following the same or similar alarm failure, to improve the mesh of the efficiency of decision-making
Mark, and then accident judgement and treatment effeciency in Chemical Manufacture are reduced, the negative effect degree of accident is reduced to the maximum extent, is kept away
Exempt from the generation of secondary disaster.
Detailed description of the invention
Fig. 1 is workflow schematic diagram of the present invention.
Specific embodiment:
In order to deepen the understanding of the present invention, the present embodiment is described in detail with reference to the accompanying drawing.
Embodiment 1: referring to Fig. 1, a kind of Chemical Manufacture Exceptional Slices management method based on data-driven, the method packet
Include following steps:
Step 1: realizing the acquisition to parameters using sensor；
Step 2: correlation calculations, contraposition number carry out periodical association analysis, obtain the incidence matrix of different moments；Tool
The calculation method of body is as follows,
In normal productive process, periodically calculates and strongly connected position number occurs with target position number and forms associated bit number
Group, for example, calculate with A.WL.MT.LT901A numbers have strongly connected position number, then by related coefficient algorithm calculate and
A.WL.MT.LT901A changes other biggish positions number of correlation, and A.WL.MT.LT901A is indicated with x, and y generation refers to other participations
K position number of correlation calculations.The related coefficient x=of calculating x and y first [x1, x2, x3 ... xn], yk=[yk1,yk2,
yk3,…ykn] (k=1 ... h), by x, yknBring the related coefficient that formula calculates the two into,
In statistics, the degree of correlation between two variables is described in quantity with " related coefficient ", with symbol " r " come
It indicates；Related coefficient value range is limited to: -1≤r≤1；
The meaning that related coefficient indicates
| Related coefficient | 0.00 | 0.00…±0.3 | ±0.30…±0.50 | ±0.50…±0.80 | ±0.80…±1.00 |
| Degree of correlation | Without correlation | Micro- positive negative correlation | It is real positive negatively correlated | It is significant positive negatively correlated | Height is positive negatively correlated |
Take the absolute value of r to be greater than 0.8 coefficient as strong incidence coefficient here；
Such as target position number incidence matrix [A.WL.MT.LT901D, A.WL.MT.LT-1110A,
A.LY.YP.FI1501.PV ... ..], then it represents that these positions number and A.WL.MT.LT901A relevance are stronger, are
Facilitate statement hereafter with A=[x, a1,a2…am]TIndicate incidence matrix.
Step 3: a certain moment, target position number are alarmed, are made the difference by the time, find out and alarm moment immediate pass
Join matrix；Such as 12 hours, two days or one week at regular intervals, determine according to operating condition, repeat step 1, step 2, count again
Calculating has High relevancy position number with target position number, brings data at that time into, forms incidence matrix, i.e.,
A=[x, a1,a2…am]TWherein T is the time that the incidence matrix generates；
Step 4: calculating the similarity of incidence matrix and historical context matrix, obtain the highest one group of historical context of similarity
Matrix；A certain moment T1, will be with T when target position A.WL.MT.LT901A alarms1Corresponding pass at the time of difference minimum
Connection property matrix and historical context matrix carry out similarity calculation, find out one group of closest historical context matrix of similarity, will
The corresponding accident description of this historical context matrix and experience record are presented to operator, and incidence matrix is similar to historical context matrix
Property calculate use mahalanobis distance algorithm:
Incidence matrix when alarming is [x, a1,a2…am]T, some historical context matrix P=[x, p1,p2…
pm], E is the covariance matrix of A, P matrix, then A is at a distance from P are as follows:
Then corresponding historical context matrix and incidence matrix A are most like when D value minimum,
Step 5, the corresponding accident description of this historical context matrix and experiential operating record are sent to operator；
Step 6, after this alarm solves, the operation note of incidence matrix and operator is got off to be formed knowledge slice and is put into and goes through
Control information in history database, as the following parameter alarm.
Application example:
2018, certain chemical plant one was catalyzed for running gear parameter: the period of correlation matrix calculation is two days, sensing
The data of 2018.5.25 00:00 to the 11:50 of device acquisition, as shown in the table:
Using the related coefficient algorithm of step 2, the A.WL.MT.LT901A numbers correlations with other number are calculated.
Wherein h=35, n=72,The correlation coefficient r of A.WL.MT.LT901A parameter and other number is such as
Under:
Table 2
Relative coefficient absolute value, which is greater than, 0.9 takes strong correlation, 0.9 here be summed up according to operating condition practical experience come
, then there is the parameter such as following table of strong correlation with A.WL.MT.LT901A parameter.
| Parameter name | y | x |
| Outer pressure power | A.LY.YP.LI08.PV | A.WL.MT.LT901A |
| Outside heat removing material position | A.LY.YP.LI8410.PV | A.WL.MT.LT901A |
| Regeneration temperature | A.LY.YP.LXH12408S.U | A.WL.MT.LT901A |
Known by upper table, three outer pressure power, outside heat removing material position, regeneration temperature parameters have strong phase with A.WL.MT.LT901A
It closes, brings the data of 2018.5.25 00:00 to 11:50 into, form incidence matrix A, it may be assumed that A=
|A.WL.MT.LT901A,A.LY.YP.LI08.PV,A.LY.YP.LI8410.PV,A.LY.YP.LXH12408S.U
|2018.5.25.00.00.002018.5.25 a number 16:40A.WL.MT.LT901A alarms, then is made the difference and compared by the time, above-mentioned pass
Calculating time and the alarm time of origin for joining matrix are closest, then recall the incidence matrix, and bring current alerts data into
According to the calculated historical context matrix of above-mentioned incidence coefficient algorithm when P1, P2 ... .Pn are history alarms,
Which historical context matrix in A and database calculated using mahalanobis distance algorithm
It is closest, it is existing to administrator to recall the corresponding experience recording layer of historical context matrix, wherein
Last traversal history incidence matrix is calculated, A between P4 at a distance from it is minimum, 8.3298.So from historical data
The corresponding historical experience record of P4 is recalled in library, it may be assumed that outside heat removing booster carries out reporting by telephone, class to workshop leader and production department
The outer behaviour of group rushes towards outside heat removing air inlet-outlet-housing immediately and prepares to search leakage tube bank, when tissue administrative staff the first on duty are led in workshop
Between reach operating room and command accident treatment, reaction member technician leads outer rashly except producing after the 1# tube bank of external warmer leakage
Restore steady, each Parameter reconstruction is normal.
The above operation note is that suggestion for operation is provided to operator, and administrator is according to the professional standing and experience of oneself product
Tired, this suggestion is adopted in decision, and final each Parameter reconstruction is steady.
Since when tube bank cuts out judgement by root, a few root canal beam pressure changes are slow, the judgement of leakage point is caused centainly
It influences.This tube bank beginning leakage rate is smaller, and teams and groups are leakage accident is found, judgement is with treatment process, and discovery is timely, judgement
Accurately, processing is proper, avoids the expansion of the state of affairs, it is ensured that normal production.If accident finds not in time, to judge inaccuracy,
The pressure of the safety and steady operation and full factory 3.5MPa steam pipe network of the present apparatus will directly be jeopardized, and then influence other devices
Steadily.
It should be noted that above-described embodiment, is not intended to limit the scope of protection of the present invention, in above-mentioned technical proposal
On the basis of made equivalents or substitution each fall within the range that the claims in the present invention are protected.
Claims (9)
1. a kind of Chemical Manufacture Exceptional Slices management method based on data-driven, which is characterized in that the method includes following
Step:
Step 1 realizes the acquisition to each position number using sensor；
Step 2 contraposition number carries out periodical association analysis, obtains the incidence matrix of different moments；
Step 3 a certain moment, target position number are alarmed, are made the difference by the time, find out and alarm moment immediate association square
Battle array；Step 4 calculates the similarity of incidence matrix and historical context matrix, obtains the highest one group of historical context matrix of similarity；
Step 5 recalls the most like corresponding historical operation of historical context matrix, is sent to operator；
After this alarm of step 6 solves, the operation note of incidence matrix and operator are got off to be formed knowledge slice and are put into history number
According to the control information in library, as the following parameter alarm.
2. the Chemical Manufacture Exceptional Slices management method according to claim 1 based on data-driven, which is characterized in that institute
Stating step 2, detailed process is as follows: calculating alarm bit number using correlation calculations method and which position number has relevance；Specifically
Calculation method:
In normal productive process, every 12 hours, which calculate, once to be occurred strongly connected position number and is formed to be associated with square with target position number
Battle array.
3. the Chemical Manufacture Exceptional Slices management method according to claim 2 based on data-driven, which is characterized in that institute
It is specific as follows to state step 3, when target position number is alarmed, warning message is sent to operator, and recall from database with
Alarm moment immediate incidence matrix.
4. the Chemical Manufacture Exceptional Slices management method according to claim 3 based on data-driven, which is characterized in that institute
Step 4 is stated, it is most close using the incidence matrix and which historical context matrix of mahalanobis distance calculating target position number.
5. the Chemical Manufacture Exceptional Slices management method according to claim 4 based on data-driven, which is characterized in that institute
Step 5 is stated, the corresponding accident description of this historical context matrix and experience record are presented to operator, the operation as operator
Referring to information.
6. the Chemical Manufacture Exceptional Slices management method according to claim 5 based on data-driven, which is characterized in that institute
It states step 6: after trouble shooting, alarm parameters incidence matrix being described with corresponding accident and experience record puts historical data base into
In, comparison information and the corresponding operation guidance of incidence matrix when alarming as next target position number.
7. the Chemical Manufacture Exceptional Slices management method according to claim 6 based on data-driven, which is characterized in that institute
The message push for stating step 3 and step 5 is all operator to be shown to by mobile terminal, and have individual operation function in mobile terminal
It can be i.e.: whether opening the switch for receiving alarm pushed information.
8. the Chemical Manufacture Exceptional Slices management method according to claim 7 based on data-driven, which is characterized in that institute
It states to calculate in step 2) and has strongly connected position matrix with target position number, then calculated by related coefficient algorithm and become with target position number
Change the biggish other parameters of correlation, target position number is indicated with x, y generation refers to that other participate in k position number of correlation calculations, first
First calculate the related coefficient x=[x1, x2, x3 ... xn] of x and y, yk=[yk1, yk2, yk3... ykn] (k=1 ... h), by x, ykn
Band formula 1, calculates the related coefficient of the two,
In statistics, the degree of correlation between two variables is described in quantity with " related coefficient ", with symbol " r " come table
Show.Related coefficient value range is limited to: -1≤r≤1
The meaning that related coefficient indicates
Take the absolute value of r to be greater than 0.8 coefficient as strong incidence coefficient here.
9. the Chemical Manufacture Exceptional Slices management method according to claim 7 based on data-driven, which is characterized in that institute
State a certain moment in step 4, when target position number is alarmed, calculate the incidence matrix of the moment this number, then with the position
Number historical context matrix carry out similarity calculation, find out the maximum one group of historical context matrix of similarity, association square at this time
Battle array calculates with historical context matrix similarity and uses mahalanobis distance algorithm:
Here with x for feeling the pulse with the finger-tip mark number, strong incidence matrix when alarming is A=[x, a1, a2...am]T, some history pass
Join matrix P=[x, p1, p2...pm], E is the covariance matrix of A, P matrix, then A is at a distance from P are as follows:
Then D value hour corresponding historical context matrix and incidence matrix A are most like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811058446.4A CN109327330B (en) | 2018-09-11 | 2018-09-11 | Chemical production abnormal slice management method based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811058446.4A CN109327330B (en) | 2018-09-11 | 2018-09-11 | Chemical production abnormal slice management method based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109327330A true CN109327330A (en) | 2019-02-12 |
| CN109327330B CN109327330B (en) | 2022-02-22 |
Family
ID=65265033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811058446.4A Active CN109327330B (en) | 2018-09-11 | 2018-09-11 | Chemical production abnormal slice management method based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109327330B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899119A (en) * | 2020-06-16 | 2020-11-06 | 西安交通大学 | Intelligent alarm suppression method and system for coal-fired power plant |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201222183Y (en) * | 2008-07-02 | 2009-04-15 | 南京金炼科技有限公司 | Optimized control system for heating stove |
| CN102053613A (en) * | 2010-12-31 | 2011-05-11 | 北京三博中自科技有限公司 | Energy real-time monitoring system of industrial process equipment and monitoring method thereof |
| CN102176221A (en) * | 2011-03-16 | 2011-09-07 | 中南大学 | Coke furnace temperature predicting method based on dynamic working conditions in coke furnace heating and burning process |
| WO2013116993A1 (en) * | 2012-02-08 | 2013-08-15 | Telefonaktiebolaget L M Ericsson | Method, computer program, computer program product and system for handling sensor data |
| CN103699118A (en) * | 2013-12-18 | 2014-04-02 | 北京航天测控技术有限公司 | Method and device for analyzing abnormal state of spacecraft in operating process |
| CN104750072A (en) * | 2015-03-12 | 2015-07-01 | 用友网络科技股份有限公司 | Production process monitoring method and system, monitoring device and monitoring system |
| EP2919124A1 (en) * | 2014-03-12 | 2015-09-16 | Haltian Oy | Relevance determination of sensor event |
| CN105893700A (en) * | 2016-04-26 | 2016-08-24 | 陆新建 | Chemical production on-line fault detection and diagnosis technique based on physical-large data hybrid model |
| CN106020154A (en) * | 2016-07-12 | 2016-10-12 | 中国石油化工股份有限公司 | Safe dynamic health assessment method and assessment system for ethylene production |
| US20160327417A1 (en) * | 2013-09-06 | 2016-11-10 | International Business Machines Corporation | Detecting Device, Detecting Method, and Program |
| US20170083012A1 (en) * | 2015-09-18 | 2017-03-23 | Fisher-Rosemount Systems, Inc. | Methods and apparatus to define stages for multi-variate batch control analytics |
| US20170097638A1 (en) * | 2015-10-01 | 2017-04-06 | Globalfoundries Inc. | Methods of error detection in fabrication processes |
| CN107390646A (en) * | 2016-05-17 | 2017-11-24 | 通用电气公司 | Intelligent management system for factory's balance |
| CN107479518A (en) * | 2017-08-16 | 2017-12-15 | 南京联成科技发展股份有限公司 | A kind of method and system for automatically generating alarm association rule |
| CN107958089A (en) * | 2017-12-19 | 2018-04-24 | 新疆金风科技股份有限公司 | Build the method and apparatus of model and the detection method and device of abnormal data |
-
2018
- 2018-09-11 CN CN201811058446.4A patent/CN109327330B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201222183Y (en) * | 2008-07-02 | 2009-04-15 | 南京金炼科技有限公司 | Optimized control system for heating stove |
| CN102053613A (en) * | 2010-12-31 | 2011-05-11 | 北京三博中自科技有限公司 | Energy real-time monitoring system of industrial process equipment and monitoring method thereof |
| CN102176221A (en) * | 2011-03-16 | 2011-09-07 | 中南大学 | Coke furnace temperature predicting method based on dynamic working conditions in coke furnace heating and burning process |
| WO2013116993A1 (en) * | 2012-02-08 | 2013-08-15 | Telefonaktiebolaget L M Ericsson | Method, computer program, computer program product and system for handling sensor data |
| US20160327417A1 (en) * | 2013-09-06 | 2016-11-10 | International Business Machines Corporation | Detecting Device, Detecting Method, and Program |
| CN103699118A (en) * | 2013-12-18 | 2014-04-02 | 北京航天测控技术有限公司 | Method and device for analyzing abnormal state of spacecraft in operating process |
| EP2919124A1 (en) * | 2014-03-12 | 2015-09-16 | Haltian Oy | Relevance determination of sensor event |
| CN104750072A (en) * | 2015-03-12 | 2015-07-01 | 用友网络科技股份有限公司 | Production process monitoring method and system, monitoring device and monitoring system |
| US20170083012A1 (en) * | 2015-09-18 | 2017-03-23 | Fisher-Rosemount Systems, Inc. | Methods and apparatus to define stages for multi-variate batch control analytics |
| US20170097638A1 (en) * | 2015-10-01 | 2017-04-06 | Globalfoundries Inc. | Methods of error detection in fabrication processes |
| CN105893700A (en) * | 2016-04-26 | 2016-08-24 | 陆新建 | Chemical production on-line fault detection and diagnosis technique based on physical-large data hybrid model |
| CN107390646A (en) * | 2016-05-17 | 2017-11-24 | 通用电气公司 | Intelligent management system for factory's balance |
| CN106020154A (en) * | 2016-07-12 | 2016-10-12 | 中国石油化工股份有限公司 | Safe dynamic health assessment method and assessment system for ethylene production |
| CN107479518A (en) * | 2017-08-16 | 2017-12-15 | 南京联成科技发展股份有限公司 | A kind of method and system for automatically generating alarm association rule |
| CN107958089A (en) * | 2017-12-19 | 2018-04-24 | 新疆金风科技股份有限公司 | Build the method and apparatus of model and the detection method and device of abnormal data |
Non-Patent Citations (2)
| Title |
|---|
| 孙勇: "DCS系统过程控制功能的设计与实现", 《中国优秀硕士学位论文全文数据库》 * |
| 朱群雄; 高慧慧; 徐圆: "工业过程报警管理研究进展", 《自动化学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899119A (en) * | 2020-06-16 | 2020-11-06 | 西安交通大学 | Intelligent alarm suppression method and system for coal-fired power plant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109327330B (en) | 2022-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102819239B (en) | Intelligent fault diagnosis method of numerical control machine tool | |
| CN103902643B (en) | Event resolver, storage medium and event analytic method | |
| CN110457184A (en) | Associated chemical industry exception causality analysis and figure methods of exhibiting are fluctuated based on timing | |
| CN106199276A (en) | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system | |
| CN103150473A (en) | Method and device for monitoring and diagnosing generating efficiency of wind turbine generator in real-time manner | |
| CN101446831A (en) | Decentralized process monitoring method | |
| CN101523316A (en) | Method and system for detecting faults in a process plant | |
| CN106610617B (en) | A kind of accumulation of energy unit trouble analysis system and method | |
| CN104994535A (en) | Sensor data flow abnormality detection method based on multidimensional data model | |
| CN105260823A (en) | Method and system for evaluating health status of major equipment | |
| CN107656156B (en) | A kind of equipment fault diagnosis and operating status appraisal procedure and system based on cloud platform | |
| CN108830335A (en) | Photovoltaic plant fault early warning method and system | |
| JP2015141513A (en) | Control device, management device, plant control system, and data processing method | |
| CN102789676A (en) | Method for designing industrial alarm on basis of alarm evidence fusion | |
| CN109327330A (en) | Chemical Manufacture Exceptional Slices management method based on data-driven | |
| CN103198232B (en) | The determination method and device of digitized master control room staff's human factors analysis | |
| CN103198231A (en) | Method and system for judging reliability of man-machine interfaces of DCS (digital control system) by means of HRA (human reliability analysis) | |
| CN115145252B (en) | Fault tree-based fault diagnosis method, system and medium for water turbine speed regulator | |
| CN110209144A (en) | Two layers of real-time monitoring and alarm source tracing method based on sound collaboration variance analysis | |
| CN104361242B (en) | Based on data-driven and the Method for Bearing Fault Diagnosis of random intuitionistic fuzzy strategy | |
| CN115860477A (en) | Pollutant real-time emission monitoring method and system based on electric power data | |
| CN107295553A (en) | A kind of base station maintenance method and device | |
| CN117170304B (en) | PLC remote monitoring control method and system based on industrial Internet of things | |
| CN109139388B (en) | Intelligent auxiliary monitoring system of wind driven generator | |
| CN109617740A (en) | A kind of method and device that application failure quickly positions |
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 | ||
| GR01 | Patent grant |