CN103885335A - Decision-making method based on decision support system in sintering process - Google Patents
Decision-making method based on decision support system in sintering process Download PDFInfo
- Publication number
- CN103885335A CN103885335A CN201210559493.3A CN201210559493A CN103885335A CN 103885335 A CN103885335 A CN 103885335A CN 201210559493 A CN201210559493 A CN 201210559493A CN 103885335 A CN103885335 A CN 103885335A
- Authority
- CN
- China
- Prior art keywords
- decision
- proposition
- knowledge
- intelligent
- sintering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a decision-making method based on a decision support system in a sintering process. The method comprises the following steps: (1) utilizing a conventional zero level sensor device, a first-level PLC and an OPC server to carry out distributed sintering process data acquisition; (2) distributed data storing; (3) each decision-making unit carrying out data analysis, model calculation, proposition matching, knowledge searching and abnormity diagnosis and giving unit level decision support; and (4) five sintering process intelligent decision units distributed coprocessing, and giving global abnormity diagnosis and decision support.
Description
Technical field
The present invention relates to a kind of decision-making technique of sintering process, particularly a kind of sintering process abnormity diagnosis based on process decision support system and the method for distributed intelligence Coordination Decision.
Background technology
Sintering deposit is the main source of blast furnace ironmaking raw material, sintering production process is that a complicated mechanism, influence factor are numerous, the dynamic system of strong coupling, large time delay, being difficult to set up mathematical models controls, the experience of adding operative employee is uneven, operates decision-making like this with regard to a kind of means non-productive operation of needs work.
Sintering process equipment is various, and data volume is large and distributed more widely.The automatization level of current domestic sintering plant is also lower with respect to other links of smelting iron and steel, mostly only have one-level basic automatization to realize data acquisition centralized displaying and inquiry, substantially there is no secondary robotization, also link up and substantially go to make a phone call to realize by workman with the production of upstream process procedure blast furnace ironmaking.Just seem so rapidly relatively backward today in Informatization Development, so both caused the reduction of production efficiency, also operative employee's decision-making capability is had relatively high expectations.
A kind of decision support method of the sintering process quality management of analyzing based on control chart is provided in the patent that is CN201010521817.5 at application number " a kind of sintering process decision supporting system ", application principal component analysis (PCA), Grey Incidence Analysis, sintering process information is extracted, determined the major parameter that affects quality.Then, sinter quality data are carried out to control chart analysis, obtain abnormal quality information, and analyze abnormal cause, provide basis for estimation for instructing to produce, although this system can be by the operation support that extremely feeds back to production of sinter quality because the analysis of sinter quality be off-line, in this way can not be real-time online operation decision-making is provided.The directive significance of online decision support is stronger.The patent that the sintering decision support method of introducing in paper " design of sintering process decision supporting system and realization " and application number are CN201010521817.5 is basically identical.In the patent that is CN201010262557.4 at application number " a kind of self-tuning expert control method of burning trough point parameter based on operating mode identification ", invent one based on fuzzy method control sintering end point, regulated the method for sintering machine machine speed.Assessment rules has also adopted the expression-form of production rule, and this rule was not introduced the quantification of the confidence level of condition weight and result of determination at that time.
Summary of the invention
In order to overcome the shortcoming of above-mentioned prior art, technical matters to be solved by this invention is to provide a kind of method of sintering process intelligent diagnostics and decision-making, having solved operative employee judges by rule of thumb the one-sidedness problem of operating mode, helps it to save worry laborsaving by thinking deeply for operative employee, the combined action of performance Artificial intelligence and aid decision making, reduce the unusual service condition frequency of occurrences, ensure natural labor, provide a kind of real-time and high method of stability for operative employee carries out work condition abnormality diagnostic and decision making more rapidly and effectively.
In order to realize the object of invention, the invention provides a kind of decision-making technique of sintering process, realize the method and comprise the following steps:
(1) utilize existing zero level sensor device, primary PLC and opc server carry out distributed sintering process data acquisition, comprise the data acquisition in raw material station, proportioning station, mixed once, two mixed granulations, sintering system, crushing and screening, finished product station and laboratory;
(2) Distributed Storage, is stored in raw material decision package database server, batching decision package database server, sintering decision package database server, finished product decision package database server and laboratory decision package database server by Industrial Ethernet communication;
(3) each decision package carries out data analysis, model calculating, proposition coupling, knowledge search and abnormity diagnosis and provides cell level decision support;
(4) 5 sintering process intelligent decision distributed unit associated treatment, provide abnormity diagnosis of overall importance and decision support.
It is characterized in that, the method realization that in step (1), in the each decision package data server of employing, Intelligent Information Collection device completes the seamless fusion of multi-source data is based on time triggering and Event triggered, autonomous and comprehensive data acquisition.
Further, the method also has following characteristics, and the analysis of described step (3) to real time data, is converted into knowledge by data.Knowledge adopts the production rule expression way of optimizing, the uncertainty of knowledge adopts rule intensity and proposition confidence level to identify, (as: IF proposition 1 (weights) (confidence level) AND proposition 2 (weights) (confidence level) AND ... THEN conclusion (confidence level) (lowest confidence)).Wherein, the calculating of confidence level is in the following way:
Rule intensity: CF
0=φ
0, 0< φ
0≤ 1
Proposition confidence level:
The weights that Power (N) is each proposition, rule intensity is that regular prerequisite own is released the degree that conclusion is set up.
If release the with a low credibility in lowest confidence (in the time creating rule, rule of thumb inputting lowest confidence value) of conclusion, this conclusion is false.
The storage of knowledge base adopts correlation multilist stored in association knowledge.Knowledge is decomposed into condition (IF) and conclusion (THEN), and its conditional is made up of the logical relation (AND, OR) of proposition, and conclusion is made up of proposition.Proposition=parameter+state.Divide and state is divided into (slightly by the normal value to technological parameter and exceptional value scope, moderate, seriously) Three Estate, the storage mode of this knowledge representation mode and knowledge base makes the method more accurate in the time that decision information and abnormity diagnosis are provided, reasoning process is more flexible, efficiency is higher, and the threshold value of state can be adjusted, solve the problem that in sintering process, technological parameter abnormal ranges changes, in knowledge base, store corresponding decision information ID for every rule, in decision table, searched acquisition decision support according to decision information ID simultaneously.
Further, the method also has following characteristics, in described step (4), in intelligent decision unit, intelligent decision module adopts self study knowledge search to calculate with adaptive model the method combining, qualitative and quantitative analysis is complemented each other, therefore more accurate and practical decision information can be provided.On inference mechanism, intelligent decision module is described by a four-tuple:
A={S，K，I，R}
Wherein S={S1, S2 ... Sn} represents all possible state set of intelligent decision modular environment, is the input set of intelligent decision module; K is Indigenous knowledge set, comprises all expertises in knowledge base.R represents the issuable decision set of intelligent decision module, is the output set of intelligent decision module; I is the Nonlinear Mapping of a state of knowledge to decision-making output:
I：S×K→R
And multiple intelligent decision distributed unit Coordination Decision, with respect to centralized decision-making technique, can make system more stable, if one of them intelligent decision unit breaks down, still can normally work in other intelligent decision unit.Further, the burden that distributed collaboration decision-making treatment method can mitigation system, makes the real-time of system higher, and decision information has more reference value.
Further, the method proposing by the present invention also has following characteristics: open structure, extensibility, improves knowledge base adaptively, realizes in real time and non real-time aid decision making.
The present invention has following beneficial effect: 1, record the data in sintering production process, for field staff provides flexibly, abnormity diagnosis the operation stable and technological process that real-time is high is supported comprehensively; 2, adapt to site environment, reliable operation, can be in real time, continuously, for a long time, independently on-line operation; 3, equipment cost is low, is easy to dispose.
Accompanying drawing explanation
Fig. 1 is: the intelligent coordinated decision-making physical topological structure of sintering process figure;
Fig. 2 is: intelligent decision modular structure figure;
Fig. 3 is: intelligent decision cellular construction figure;
Fig. 4 is: many intelligent decisions of sintering process unit synergetic structure figure;
Fig. 5 is: sintering process decision guidance realization flow figure;
Embodiment
Describe below in conjunction with specific embodiment:
Fig. 1 is the intelligent coordinated decision-making physical topological structure of sintering process figure, and the PLC of basic automatization station image data comprises raw material system PLC, feed proportioning system PLC, sintering system PLC, finished product system PLC and laboratory system PLC.Different automation of sintering plant system differences, wherein raw material system can be by solvent PLC, fuel PLC and concentrate PLC composition.In this case a raw material decision package server is joined at raw material station, for saving resource raw material data server and raw material decision package server are located in same computer server.Proportioning station is joined a batching decision package server, for saving resource batching database server and batching decision package server are located in a computer server.According to the difference of design, sintering system can be by mixed once PLC, two mixed granulation PLC, grate-layer material system PLC, the compositions such as sintering PLC and broken and the cold PLC of ring.In this case sintering system is joined a sintering decision package server, for saving resource sintering system data server and sintering system decision package server are located in same computer server.A finished product system decision-making unit is joined at finished product station, for saving resource finished product system data server and finished product system decision-making cell server are located in same computer server.System decision-making unit, a laboratory is joined in laboratory, for saving resource laboratory data server and laboratory system decision-making cell server are located in same computer server.Its corresponding PLC of each website decision package server connects with Industrial Ethernet form by switch.Sintering mill (plant) master-control room configuration sintering intelligent coordinated decision-making global server, sintering intelligent coordinated decision-making global data base server and intelligent coordinated decision-making man-machine interaction client.The intelligent coordinated decision-making global data base of sintering server is that all detection data in each station, sintering mill (plant) gather.The intelligent coordinated decision-making global server of sintering is carried out sintering mill (plant) abnormity diagnosis decision support of overall importance, and its result shows in the intelligent coordinated decision-making man-machine interaction of sintering client.
Fig. 2 is intelligent decision modular structure figure, is responsible for the decision task of place decision package, and different intelligent decision modules has different decision model storehouses, and the knowledge base corresponding with decision model.Knowledge base is set up in SQL SERVER or ORACLE.Model bank is packaged as dynamic link library dll file.Knowledge in knowledge base adopts the production rule expression way of optimizing, (as: IF sintering end point slightly in advance (0.7) AND exhaust gas temperature omits the slightly burning (0.95) (0.6) of the flourishing layer of (0.2) AND tail slightly thin (0.1) THEN that raises).The storage of knowledge base adopts correlation multilist stored in association knowledge.Knowledge is decomposed into condition (IF) and conclusion (THEN), and its conditional is made up of the logical relation (AND, OR) of proposition, and wherein AND is weighting logic, and OR is or logic that conclusion is made up of proposition.Proposition is made up of parameter (as: sintering end point) and state (as: slightly in advance).Divide and state is divided into (slightly by the normal value to technological parameter and exceptional value scope, moderate, seriously) Three Estate, for example (sintering end point slightly shifts to an earlier date (22.3,23), sintering end point (21.4,22.6) in advance, sintering end point seriously shifts to an earlier date (0,21.4)).Model bank of the present invention and knowledge base have been done complementary combination, and can apply separately also can be in conjunction with application.For example sintering decision package comprises sintering end point model, according to the particular location of specifying the temperature value of bellows to carry out corresponding calculating can to release sintering end point, for example sintering end point=22.5, this value is stored in the database of sintering decision package and shows in the anomaly parameter list of sintering decision package man-machine interface.According to (the slightly slightly burning (0.95) (0.6) of the flourishing layer of rising (0.2) AND tail slightly thin (0.1) THEN of (0.7) AND exhaust gas temperature slightly in advance of IF sintering end point) this rule, and the abnormal threshold value division of sintering end point sintering end point slightly shifts to an earlier date (22.3,23), can release " slightly burning ", confidence level is 0.95 so abnormality diagnostic conclusion.According to " slightly burning " such abnormity diagnosis, in knowledge base in decision table coupling can obtain decision-making assistant information (1, improve the bed of material, take suitable binder operation.2, suitably close main exhausting door, reduce by sintering machine air quantity.)
Intelligent decision module is to realize the main body of sintering process aid decision making, is the scheme generation module for decision problem, and in sintering plant, the decision package in each field has intelligent decision module, and it and collaborative process device complete decision task jointly.Wherein knowledge base is the Knowledge Management System of intelligent decision module, the knowledge of mainly storing intelligent decision module self-ability and environment of living in, and it is carried out to Dynamic Maintenance.
The external information that inference machine transmits according to Intelligent Information Collection device and the domain knowledge possessing carry out problem solving.Task buffer is used for depositing some middle multidate informations that need and produce in intelligent decision module reasoning process.All behaviors of intelligent decision module are all carried out under the management of coordinating control module.Coordination and control module is the internal core of intelligent decision module, is responsible for the task process of each module and coordinates, and the operation result of other module is judged and passed on.First behavior evaluation module carries out inner emulation to the decision behavior of intelligent decision module, and the result of implementation of decision behavior is carried out to on-line evaluation, for coordinating control module and self study/adaptation module provide foundation.Self study/adaptation module is optimized the decision behavior of intelligent decision module, make it to have autonomous evolvability, under the guidance of behavior evaluation mechanism, adopt the intelligent learning algorithms such as intensified learning, Bayesian learning to carry out knowledge base update to intelligent decision module.Communication interface module is responsible for intelligent decision module and other unit of system carries out alternately.
Fig. 3 is an intelligent decision cellular construction figure, and intelligent decision unit comprises information acquisition device, local collaborative process device, man-machine interface and intelligent decision module.Local collaborative process device is responsible for the coordination of inside, intelligent decision unit, and external interface is provided, by overall collaborative process device and other intelligent decision unit Coordination Decision.Man-machine interface provides demonstration and real-time parameter curve and anomaly parameter demonstration and the warning etc. of decision information.
Fig. 4 is many intelligent decisions of sintering process unit Coordination Decision structural drawing, the configuration of intelligent decision unit is according to the Different Dynamic configuration of sintering process flow process, workstation etc., and the present invention has configured raw material intelligent decision unit, dispensing intelligent decision package, sintering intelligent decision unit, finished product intelligent decision unit and intelligent decision unit, laboratory etc.Many intelligent decisions unit carries out the distributed way combining with centralized management, (wherein global information collector is configured in information collection server for master-control room configuration global information acquisition server and decision system server, man-machine interface, overall collaborative process device and overall intelligent decision block configuration are in decision system server), workstation configuration intelligent decision cell server (database server that local message collector can be related to, local collaborative process device, man-machine interface and intelligent decision block configuration in a main frame with saving resource).Each intelligent decision unit is converted into reasoning prerequisite according to the value of each parameter and reaches a conclusion according to the rule of knowledge base.These conclusions are transferred to overall intelligent decision module to carry out reasoning according to the rule of global knowledge base by overall collaborative process device again as the precondition of reasoning and are obtained final conclusion, and show in man-machine interface, give the decision support of sintering process operating personnel to assist.
Fig. 5 is sintering process decision guidance realization flow figure, before global collaborative reasoning, step is the algorithm flow of each distributed decision making unit, wherein analysis data and the model calculation data that the data basis that is is actual acquired data are mated in proposition, proposition is after the match is successful, can be stored in activity proposition table, within the life cycle of activity proposition, activity proposition meeting exists always, activity proposition is the basis that each decision package carries out knowledge search and reasoning, is also the basis of global collaborative reasoning.The abnormity diagnosis information that each decision package obtains can become the basis of global collaborative reasoning equally.And then draw Operating Guideline by the result of global collaborative reasoning.
Embodiment:
(1) distributed data acquisition
Adopt OPC communications protocol to carry out data acquisition
The partial data that sintering decision package collects is as follows
| No. 22 box temperature | No. 23 box temperature | No. 24 box temperature | The flourishing layer thickness of tail |
| 392.9524 | 409.5194 | 315.4566 | 0.6 |
The partial data that laboratory decision package collects is as follows:
FeO content: 9.6
(2) Distributed Storage
The data that sintering decision package collects are stored in sintering decision package database, and the data that laboratory decision package collects are stored in the decision package database of laboratory.
(3) data analysis
Sintering decision package and laboratory decision package be respectively to being stored in the data analysis in database separately, preference pattern Branch Computed or proposition coupling branch.Determine that No. 22 box temperature, No. 23 box temperature, No. 24 box temperature data are model computational data, participate in sintering end point model and calculate, can obtain sintering end point=23 according to these three process parameter value.The flourishing layer thickness of tail and FeO content participate in proposition coupling.
(4) proposition coupling
Sintering decision package proposition coupling:
According to sintering end point=23, in knowledge base, search for coupling proposition " sintering end point is normal ";
According to flourishing layer=0.6 of tail, in knowledge base, search for coupling proposition " the flourishing layer of tail moderate is thick ";
Laboratory decision package proposition coupling:
According to FeO content=9.6, in knowledge base, search for coupling proposition " FeO content is slightly high ";
(5) activity proposition storage
By proposition " sintering end point is normal ", " the flourishing layer of tail moderate is thick " is stored in sintering decision package activity proposition table, the initial value of setting proposition disappearance counting is 1, set proposition disappearance counting maximal value=5 (this value can be revised according to on-site actual situations), carrying out in the process of follow-up reasoning, activity proposition is employed once, and disappearance counting can add 1 processing accordingly, if disappeared, counting is greater than 5, in activity proposition table, deletes this proposition.
Proposition " FeO content is slightly high " is stored in laboratory decision package activity proposition table, the initial value of setting proposition disappearance counting is 1, set proposition disappearance counting maximal value=5 (this value can be revised according to on-site actual situations), carrying out in the process of follow-up reasoning, activity proposition is employed once, disappearance counting can add 1 processing accordingly, if the counting that disappears is greater than 5, in activity proposition table, deletes this proposition.
(6) global collaborative reasoning
In global collaborative reasoning process, can in distributed decision making cell data storehouse activity proposition table, search for, and the rule that search is mated in global knowledge base rule list:
Large (0.92) (0.6) of the flourishing layer of normal (0.4) (0.95) of IF sintering end point AND tail moderate thick (0.3) (0.85) AND FeO content slightly high (0.3) (0.95) THEN fuel ratio
Wherein, decision confidence=0.4 × 0.95+0.3 × 0.85+0.3 × 0.95=0.92, the conclusion " fuel ratio is large " of this rule is as abnormality diagnostic result.
(7) decision guidance
The result that global collaborative infers, " fuel ratio is large " confidence level 0.92 is greater than lowest confidence 0.6, and a unique corresponding decision information ID, according to this ID search decision guidance result " 1, note dirt mud supplied materials color and luster.2, reduce fuel ratio ".
So far, the distributed abnormity diagnosis of sintering process and the process of decision guidance have been completed.
Claims (4)
1. the decision-making technique based on sintering process back-up system, comprises the following steps:
(1) utilize existing zero level sensor device, primary PLC and opc server carry out distributed sintering process data acquisition, comprise the data acquisition in raw material station, proportioning station, mixed once, two mixed granulations, sintering system, crushing and screening, finished product station and laboratory;
(2) Distributed Storage, is stored in raw material decision package database server, batching decision package database server, sintering decision package database server, finished product decision package database server and laboratory decision package database server by Industrial Ethernet communication;
(3) each decision package carries out data analysis, model calculating, proposition coupling, knowledge search and abnormity diagnosis and provides cell level decision support;
(4) 5 sintering process intelligent decision distributed unit associated treatment, provide abnormity diagnosis of overall importance and decision support.
2. a kind of decision-making technique based on sintering process back-up system according to claim 1, it is characterized in that, the method realization that in step (1), in the each decision package data server of employing, Intelligent Information Collection device completes the seamless fusion of multi-source data is based on time triggering and Event triggered.
3. a kind of decision-making technique based on sintering process back-up system according to claim 1, it is characterized in that, the analysis of described step (3) to real time data, data are converted into knowledge, knowledge adopts the production rule expression way of optimizing, the uncertainty of knowledge adopts rule intensity and proposition confidence level to identify, wherein, the calculating of confidence level in the following way:
Rule intensity: CF
0=φ
0, 0< φ
0≤ 1
Proposition confidence level:
The weights that Power (N) is each proposition, rule intensity is that regular prerequisite own is released the degree that conclusion is set up;
If release the with a low credibility in lowest confidence of conclusion, this conclusion is false;
The storage of knowledge base adopts correlation multilist stored in association knowledge, and knowledge is decomposed into condition IF and conclusion THEN, and its conditional is by the logical relation AND of proposition, and OR forms, and conclusion is made up of proposition; Proposition=parameter+state; Divide state is divided into slightly by the normal value to technological parameter and exceptional value scope, moderate, serious Three Estate.
4. a kind of decision-making technique based on sintering process back-up system according to claim 1, it is characterized in that, in described step (4), in intelligent decision unit, intelligent decision module adopts self study knowledge search to calculate with adaptive model the method combining, on inference mechanism, intelligent decision module is described by a four-tuple:
A={S，K，I，R}
Wherein S={S1, S2 ... Sn} represents all possible state set of intelligent decision modular environment, is the input set of intelligent decision module; K is Indigenous knowledge set, comprises all expertises in knowledge base; R represents the issuable decision set of intelligent decision module, is the output set of intelligent decision module; I is the Nonlinear Mapping of a state of knowledge to decision-making output:
I：S×K→R
And multiple intelligent decision distributed unit Coordination Decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210559493.3A CN103885335A (en) | 2012-12-21 | 2012-12-21 | Decision-making method based on decision support system in sintering process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210559493.3A CN103885335A (en) | 2012-12-21 | 2012-12-21 | Decision-making method based on decision support system in sintering process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103885335A true CN103885335A (en) | 2014-06-25 |
Family
ID=50954286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210559493.3A Pending CN103885335A (en) | 2012-12-21 | 2012-12-21 | Decision-making method based on decision support system in sintering process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103885335A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105093928A (en) * | 2015-08-25 | 2015-11-25 | 中南大学 | Intelligent sintering process state control method based on main exhauster frequency conversion regulation |
| CN105956037A (en) * | 2016-04-26 | 2016-09-21 | 成都智慧凌云科技有限公司 | Factory database system |
| CN110411229A (en) * | 2019-07-30 | 2019-11-05 | 山东莱钢永锋钢铁有限公司 | One kind burning integrated sintering based on five and is formulated adjustment system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0383911A1 (en) * | 1988-06-17 | 1990-08-29 | Hitachi, Ltd. | System for forming knowledge data |
| US5121467A (en) * | 1990-08-03 | 1992-06-09 | E.I. Du Pont De Nemours & Co., Inc. | Neural network/expert system process control system and method |
| JP2002132304A (en) * | 2000-10-27 | 2002-05-10 | Mitsubishi Chemicals Corp | Model structuring method and plant control method |
| CN1940793A (en) * | 2006-02-14 | 2007-04-04 | 上海工程技术大学 | Integrated focus intelligent controlling system |
| CN101907867A (en) * | 2010-08-25 | 2010-12-08 | 中南大学 | Self-tuning expert control method of burning trough point parameter based on working condition recognition |
| CN102456164A (en) * | 2010-10-28 | 2012-05-16 | 张伟 | Sintering process decision supporting system |
-
2012
- 2012-12-21 CN CN201210559493.3A patent/CN103885335A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0383911A1 (en) * | 1988-06-17 | 1990-08-29 | Hitachi, Ltd. | System for forming knowledge data |
| US5121467A (en) * | 1990-08-03 | 1992-06-09 | E.I. Du Pont De Nemours & Co., Inc. | Neural network/expert system process control system and method |
| JP2002132304A (en) * | 2000-10-27 | 2002-05-10 | Mitsubishi Chemicals Corp | Model structuring method and plant control method |
| CN1940793A (en) * | 2006-02-14 | 2007-04-04 | 上海工程技术大学 | Integrated focus intelligent controlling system |
| CN101907867A (en) * | 2010-08-25 | 2010-12-08 | 中南大学 | Self-tuning expert control method of burning trough point parameter based on working condition recognition |
| CN102456164A (en) * | 2010-10-28 | 2012-05-16 | 张伟 | Sintering process decision supporting system |
Non-Patent Citations (2)
| Title |
|---|
| 李桃: "烧结过程智能实时操作指导系统的研究", 《中国博士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 杨春雨等: "鞍钢烧结生产过程综合智能控制系统", 《冶金自动化》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105093928A (en) * | 2015-08-25 | 2015-11-25 | 中南大学 | Intelligent sintering process state control method based on main exhauster frequency conversion regulation |
| CN105093928B (en) * | 2015-08-25 | 2018-02-16 | 中南大学 | A kind of sintering process condition intelligent control method based on main exhauster frequency conversion control |
| CN105956037A (en) * | 2016-04-26 | 2016-09-21 | 成都智慧凌云科技有限公司 | Factory database system |
| CN110411229A (en) * | 2019-07-30 | 2019-11-05 | 山东莱钢永锋钢铁有限公司 | One kind burning integrated sintering based on five and is formulated adjustment system |
| CN110411229B (en) * | 2019-07-30 | 2022-01-25 | 山东莱钢永锋钢铁有限公司 | Sintering formula adjustment system based on five-burning integration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Digital twin and big data-driven sustainable smart manufacturing based on information management systems for energy-intensive industries | |
| WO2021189739A1 (en) | Production plan-based iron and steel plant oxygen load prediction method | |
| CN104102212B (en) | Dispatching method, apparatus and system for gas and steam system in iron and steel enterprises | |
| CN102147273A (en) | Data-based blast-furnace gas dynamic predication method for metallurgical enterprises | |
| CN110824923A (en) | Sewage treatment control method and system based on deep learning and cloud computing | |
| CN113234874A (en) | Blast furnace fault monitoring and self-healing control system based on dynamic Bayesian network | |
| CN103885335A (en) | Decision-making method based on decision support system in sintering process | |
| CN110428053A (en) | A kind of steam produces the dynamic prediction method of consumption | |
| CN114169669A (en) | Power generation industry carbon emission prediction method, platform, computing equipment and medium | |
| Lao et al. | The optimized multivariate grey prediction model based on dynamic background value and its application | |
| Tong et al. | The digitization work of cement plant in China | |
| CN102592004B (en) | System and method for on-line analysis and diagnosis of whole-process energy-consuming conditions of integrated iron and steel works | |
| CN101957942A (en) | Accident planning expert system applied to steel mill | |
| Yan et al. | Reliability prediction of CNC machine tool spindle based on optimized cascade feedforward neural network | |
| Zhang et al. | An integrated energy efficiency evaluation method for forging workshop based on IoT and data-driven | |
| Zhai et al. | Associative reasoning-based interpretable continuous decision making in industrial production process | |
| Palchevskyi et al. | Strategy of construction of intellectual production systems | |
| Li et al. | Two-stage multi-level equipment grey state prediction model and application | |
| Niekurzak et al. | Production line modelling in accordance with the industry 4.0 concept as an element of process management in the iron and steel industry | |
| Gabitov et al. | Indicators of resource efficiency and safety of production organization | |
| Sun et al. | A master production schedule warning approach for cement equipment manufacturing enterprises | |
| Xiong et al. | Embodied energy of parts in sheet metal forming: modeling and application for energy saving in the workshop | |
| Zhang et al. | Research on intelligent health management technology of opto-electronic equipment | |
| Guan et al. | PDCA Cycle of Environmental Management Accounting Under The Background of Data Mining and Intelligent Systems | |
| Liu et al. | Research and application of the sintering whole process intelligent manufacturing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140625 |