CN106406257B - A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning - Google Patents
A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning Download PDFInfo
- Publication number
- CN106406257B CN106406257B CN201610902423.1A CN201610902423A CN106406257B CN 106406257 B CN106406257 B CN 106406257B CN 201610902423 A CN201610902423 A CN 201610902423A CN 106406257 B CN106406257 B CN 106406257B
- Authority
- CN
- China
- Prior art keywords
- case
- flotation
- floatation
- new
- concentrate grade
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacture And Refinement Of Metals (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the floatation of iron ore concentrate grade flexible measurement method and system of a kind of case-based reasioning.This method comprises: extracting historical production data from floatation of iron ore production process；Construct flotation case library；Case Retrieval is carried out in flotation case library, obtains one group of similarity value；Similarity value is arranged from big to small, the corresponding case of n similarity value describes the reference case as current working before choosing；The weighted average that every kind of case of n reference case illustrates is sought, case reuses the new case of acquisition and illustrates；Case Retrieval finds the description of the case with maximum similarity value and gives up new flotation case if the maximum similarity value is greater than similarity threshold, otherwise, replaces the case with maximum similarity value with new flotation case and describes.The present invention surveys creation data by means of floatation of iron ore concentrate grade is relevant, provides the Floatation Concentrate Grade hard measurement value under different operating conditions, and safety, reliability and the economy of floatation of iron ore production can be improved.
Description
Technical field
The invention belongs to soft-measuring technique fields, and in particular to a kind of floatation of iron ore concentrate grade of case-based reasioning is soft
Measurement method and system.
Background technique
In Floating Production Process, concentrate grade is the key that characterization floatation of iron ore process product quality and production efficiency work
Skill index.For the detection method of concentrate grade mostly by artificial offline chemical examination detection, this method can make data exist at present
Very serious hysteresis quality cannot make corresponding adjustable strategies when operating condition changes, it is more likely that will cause ore pulp in time
Middle useful component is not sorted adequately or floating agent is excessive, is caused flotation efficiency low, is resulted in waste of resources.It is few
Number iron ore beneficiating factories carry out on-line checking to concentrate grade by ore grade analyzer, but ore grade analyzer is expensive and maintenance expense
With height, increase beneficiation cost.
Summary of the invention
In view of the deficienciess of the prior art, the floatation of iron ore concentrate grade that the present invention provides a kind of case-based reasioning is soft
Measurement method and system.
A kind of floatation of iron ore concentrate grade flexible measurement method of case-based reasioning, includes the following steps:
Step 1: historical production data, including Floatation Concentrate Grade and flotation boundary are extracted from floatation of iron ore production process
Condition；
The flotation boundary condition, comprising: to mine grade, feed ore concentration, flotation time, flotation temperature, floatation concentration, fill
Tolerance, floating agent dosage；
Step 2: the abnormal point in removal historical production data, and with the previous point value of abnormal point and latter point value
Average value, which is used as, replaces value；
Step 3: according to the historical production data of removal abnormal point, constructing flotation case library, be case by flotation boundary condition
Example description, Floatation Concentrate Grade illustrate for case, and case description is deconstructed into flotation case with case；
Step 4: being described the flotation boundary condition obtained in real time in floatation of iron ore production process as new case, floating
It selects and carries out Case Retrieval in case library, obtain one group of phase between new case description and each case description for recording in case library
Like angle value；
Step 5: similarity value being arranged from big to small, the case before choosing in the corresponding flotation case library of n similarity value
Reference case of the example description as current working；
Step 6: according to the reference case being retrieved from case library, seeking what every kind of case of n reference case illustrated
Weighted average, wherein weighting coefficient is the similarity of each case and new case, thus completes case and reuses, obtains new case
Illustrate, i.e., for the Floatation Concentrate Grade hard measurement of current working as a result, the description of new case and new case be deconstructed into it is new
Flotation case；
Step 7: Case Retrieval being carried out in flotation case library to the case description of new flotation case, finds and is floated with new
The case of case is selected to describe the case description for having in the flotation case library of maximum similarity value, if the maximum similarity value is greater than
Similarity threshold then gives up new flotation case, otherwise, replaces the flotation with maximum similarity value with new flotation case
Case description in case library, completes the update of flotation case library.
The floatation of iron ore concentrate grade that the floatation of iron ore concentrate grade flexible measurement method of the case-based reasioning uses
Hard measurement system, comprising:
Acquire the data acquisition module of real-time flotation creation data；
By the data forwarding of data collecting module collected to the wireless Zigbee transmission module of Ethernet industrial personal computer；
The Data Concurrent that wireless Zigbee transmission module transmits is received to send to the Ethernet industrial personal computer of concentrate grade computer；
Receive the concentrate grade computer that the data that Ethernet industrial personal computer is sent carry out concentrate grade hard measurement and display；
The output end of data acquisition module connects the input terminal of wireless Zigbee transmission module, wireless Zigbee transmission module
Output end connection Ethernet industrial personal computer input terminal, Ethernet industrial personal computer output end connection concentrate grade computer input
End.
The utility model has the advantages that
The floatation of iron ore concentrate grade flexible measurement method of case-based reasioning of the invention, by means of floatation of iron ore concentrate product
The relevant Floatation Concentrate Grade hard measurement value surveyed creation data, provide under different operating conditions in position, it is raw to can be improved floatation of iron ore
Safety, reliability and the economy of production.Compared to present artificial offline chemical examination detection method, it is raw that the present invention improves flotation
Efficiency is produced, the probability of error is reduced；Compared to ore grade analyzer, The present invention reduces the maintenance costs of equipment, reduce life
Produce cost；Field data automatically saves, and does not need manual record, reduces loss of data, misregistration probability.
Detailed description of the invention
Fig. 1 is the floatation of iron ore concentrate grade flexible measurement method process of specific embodiment of the invention case-based reasioning
Figure；
Fig. 2 is specific embodiment of the invention step 7 flow chart；
Fig. 3 is specific embodiment of the invention floatation of iron ore concentrate grade hard measurement system block diagram.
Specific embodiment
It elaborates with reference to the accompanying drawing to specific implementation of the invention.
A kind of floatation of iron ore concentrate grade flexible measurement method of case-based reasioning, as shown in Figure 1, including the following steps:
Step 1: historical production data, including Floatation Concentrate Grade and flotation boundary are extracted from floatation of iron ore production process
Condition；
The flotation boundary condition, comprising: to mine grade, feed ore concentration, flotation time, flotation temperature, floatation concentration, fill
Tolerance, floating agent dosage, present embodiment flotation boundary condition such as table 1:
1 flotation boundary condition of table
In conjunction with historical data, production scene investigation and floatation process theory analysis, above-mentioned flotation boundary condition is to flotation essence
Mine grade has direct influence, and proportion is very big.Flotation is directly reflected to mine to mine grade, feed ore concentration
Matter；Flotation time, flotation temperature directly affect flotation effect；Floatation concentration, aeration quantity, floating agent dosage can directly affect floating
Concentrate selection grade, positive correlation.
Step 2: the abnormal point in removal historical production data, and with the previous point value of abnormal point and latter point value
Average value, which is used as, replaces value；
Pass through analysis of history data, it can be seen that (such as artificially record) for some reason, meeting in collected data
There is abnormal point, the especially severe of the data mutation of certain point removes the abnormal point in Floatation Concentrate Grade data, with abnormal point
Previous point value and latter point value average value be used as replace value；
Step 3: according to the historical production data of removal abnormal point, constructing flotation case library, be case by flotation boundary condition
Example description, Floatation Concentrate Grade illustrate for case, and case description is deconstructed into flotation case with case；
The hard measurement value of Floatation Concentrate Grade in order to obtain, needs to consider current working condition.The structure of case is by case
Example description and case illustrate two parts composition, and case description is by mine grade z1, feed ore concentration %z2, flotation time z3, flotation temperature
Spend z4, floatation concentration %z5, aeration quantity z6, floating agent dosage z7Composition；Case illustrates as Floatation Concentrate Grade hard measurement value x1.This
Flotation case is shown in Table 2 in embodiment:
2 flotation case of table
The case of case-based reasioning technology can be expressed as follows:
Ck={ Fk, Jk}.
In formula, Ck(k=1 ..., m) indicates kth case, and m is growing number；Fk={ zk.1, zk.2, zk.3, zk.4, zk.5,
zk.6, zk.7It is k-th of case description, case description is abbreviated as Fk={ fk.1..., fk.8}；Jk={ xk.1It is k-th of case
Case illustrate, case is illustrated and is abbreviated as Jk。
Step 4: being described the flotation boundary condition obtained in real time in floatation of iron ore production process as new case, floating
Select and carry out Case Retrieval in case library, obtain new case describe each case recorded in F and case library description between one group
Similarity value, similarity are the number between one 0 to 1, such as 0.88；
Wherein, ωiWeight is described for case, m is the case number of cases in case library, SIM (fi, fk.i) be current working case
F is describediCase corresponding with kth case in case library describes fk.iSimilarity, is defined as:
Step 5: similarity value being arranged from big to small, the case before choosing in the corresponding flotation case library of n similarity value
Reference case of the example description as current working, the value of n is 3 in the present embodiment；
Step 6: according to the reference case being retrieved from case library, seeking what every kind of case of n reference case illustrated
Weighted average, wherein weighting coefficient is the similarity of each reference case and new case, thus completes case and reuses, and is obtained new
Case illustrateIt is directed to the Floatation Concentrate Grade hard measurement result of current working, wherein J is
New case illustrates (such as 68.82), JkIt is illustrated for the case of reference case, n is the quantity of reference case, new case description and new
Case is deconstructed into new flotation case；
The selection of n value can generate significant impact to result.The smaller history case for meaning only to be closer to new case of n value
Example, which can just illustrate new case, to work, but is easy to happen over-fitting；If n value is larger, with new case compared with the history kept off
Case can also work to prediction, make prediction that mistake occur.In practical applications, n value is typically chosen a lesser numerical value, leads to
Optimal n value is selected frequently with the method for cross validation.
Step 7: Case Retrieval being carried out in flotation case library to the case description of new flotation case, finds and is floated with new
The case of case is selected to describe the case description for having in the flotation case library of maximum similarity value, if the maximum similarity value is greater than
Similarity threshold then gives up new flotation case, otherwise, replaces the flotation with maximum similarity value with new flotation case
Case description in case library, completes the update of flotation case library.
As shown in Fig. 2, specific step is as follows for step 7:
Step 7.1: one similarity threshold of setting；The specific value of similarity threshold depends on history case in case library
Quantity, if the quantity of history case be c, similarity threshold v, the v=0.9 if c < 200；The v=if 200 < c < 500
0.8；The v=0.7 if c > 500.
Step 7.2: Case Retrieval is carried out in flotation case library to the description of the case of new flotation case, find with it is new
The case description of flotation case has the case description in the flotation case library of maximum similarity value；
Step 7.3: if the maximum similarity value is greater than similarity threshold, giving up new flotation case, otherwise, with new
Flotation case replaces the description of the case in the flotation case library with maximum similarity value, completes the update of flotation case library.
The floatation of iron ore concentrate grade that the floatation of iron ore concentrate grade flexible measurement method of the case-based reasioning uses
Hard measurement system, as shown in Figure 3, comprising:
Acquire the data acquisition module of real-time flotation creation data；
By the data forwarding of data collecting module collected to the wireless Zigbee transmission module of Ethernet industrial personal computer；
The Data Concurrent that wireless Zigbee transmission module transmits is received to send to the Ethernet industrial personal computer of concentrate grade computer；
The concentrate grade computer that the data that Ethernet industrial personal computer is sent carry out concentrate grade hard measurement and display is received, is led to
It crosses human-computer interaction interface and shows concentrate grade hard measurement result；
The output end of data acquisition module connects the input terminal of wireless Zigbee transmission module, wireless Zigbee transmission module
Output end connection Ethernet industrial personal computer input terminal, Ethernet industrial personal computer output end connection concentrate grade computer input
End.
The floatation of iron ore concentrate grade flexible measurement method of case-based reasioning of the invention and present artificial offline chemical examination
Detection method, which compares, to be had the advantage that and improves flotation production efficiency, and the probability of error is reduced.With ore grade analyzer
It compares and has the advantage that the maintenance cost for reducing equipment, reduce production cost；Field data automatically saves, no
Manual record is needed, loss of data, misregistration probability are reduced.
Claims (2)
1. a kind of floatation of iron ore concentrate grade flexible measurement method of case-based reasioning, characterized by the following steps:
Step 1: historical production data, including Floatation Concentrate Grade and flotation perimeter strip are extracted from floatation of iron ore production process
Part；
The flotation boundary condition, comprising: give mine grade, feed ore concentration, flotation time, flotation temperature, floatation concentration, inflation
Amount, floating agent dosage；
Step 2: the abnormal point in removal historical production data, and with the previous point value of abnormal point and being averaged for latter point value
Value is as replacement value；
Step 3: according to the historical production data of removal abnormal point, constructing flotation case library, flotation boundary condition is retouched for case
It states, Floatation Concentrate Grade illustrates for case, and case description is deconstructed into flotation case with case；
Step 4: being described the flotation boundary condition obtained in real time in floatation of iron ore production process as new case, in flotation case
Example library in carry out Case Retrieval, obtain new case describe each case recorded in F and case library description between one group it is similar
Angle value；
Wherein, FkIt is described for k-th of case, ωiWeight is described for case, m is the case number of cases in case library, SIM (fi, fk.i) be
The case of current working describes fiCase corresponding with kth case in case library describes fk.iSimilarity, is defined as:
Step 5: similarity value being arranged from big to small, the case before choosing in the corresponding flotation case library of n similarity value is retouched
State the reference case as current working；Optimal n value is selected using the method for cross validation；
Step 6: according to the reference case being retrieved from case library, seeking the weighting that every kind of case of n reference case illustrates
Average value, wherein weighting coefficient is the similarity of each case and new case, thus completes case and reuses, obtains new case
Solution, i.e., for the Floatation Concentrate Grade hard measurement of current working as a result, new case description and new case are deconstructed into new float
Select case；
Step 7: Case Retrieval being carried out in flotation case library to the case description of new flotation case, is found and new flotation case
The case description of example has the case description in the flotation case library of maximum similarity value, if the maximum similarity value is greater than similar
Threshold value is spent, then gives up new flotation case, otherwise, replaces the flotation case with maximum similarity value with new flotation case
Case description in library, completes the update of flotation case library.
2. the floatation of iron ore that the floatation of iron ore concentrate grade flexible measurement method of case-based reasioning as described in claim 1 uses
Concentrate grade hard measurement system characterized by comprising
Acquire the data acquisition module of real-time flotation creation data；
By the data forwarding of data collecting module collected to the wireless Zigbee transmission module of Ethernet industrial personal computer；
The Data Concurrent that wireless Zigbee transmission module transmits is received to send to the Ethernet industrial personal computer of concentrate grade computer；
Receive the concentrate grade computer that the data that Ethernet industrial personal computer is sent carry out concentrate grade hard measurement and display；
The output end of data acquisition module connects the input terminal of wireless Zigbee transmission module, wireless Zigbee transmission module it is defeated
Outlet connects the input terminal of Ethernet industrial personal computer, the input terminal of the output end connection concentrate grade computer of Ethernet industrial personal computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610902423.1A CN106406257B (en) | 2016-10-17 | 2016-10-17 | A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610902423.1A CN106406257B (en) | 2016-10-17 | 2016-10-17 | A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106406257A CN106406257A (en) | 2017-02-15 |
| CN106406257B true CN106406257B (en) | 2019-01-15 |
Family
ID=58011998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610902423.1A Active CN106406257B (en) | 2016-10-17 | 2016-10-17 | A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106406257B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108469797B (en) * | 2018-04-28 | 2020-09-29 | 东北大学 | Neural network and evolutionary computation based ore grinding process modeling method |
| CN111198550A (en) * | 2020-02-22 | 2020-05-26 | 江南大学 | Cloud intelligent production optimization scheduling on-line decision method and system based on case reasoning |
| CN112905632A (en) * | 2021-01-19 | 2021-06-04 | 浙江中控技术股份有限公司 | Atmospheric and vacuum equipment configuration method and device based on parameter cases |
| CN115128950B (en) * | 2022-06-16 | 2023-04-07 | 矿冶科技集团有限公司 | Crushing and screening control method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5581664A (en) * | 1991-03-04 | 1996-12-03 | Inference Corporation | Case-based reasoning system |
| CN1749891A (en) * | 2005-10-19 | 2006-03-22 | 东北大学 | Intelligent optimized control method for comprehensive production index in ore dressing process |
| CN104318313A (en) * | 2014-09-19 | 2015-01-28 | 东北大学 | Intelligent decision system and method for ore dressing total flow operation index on the basis of case-based reasoning |
-
2016
- 2016-10-17 CN CN201610902423.1A patent/CN106406257B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5581664A (en) * | 1991-03-04 | 1996-12-03 | Inference Corporation | Case-based reasoning system |
| CN1749891A (en) * | 2005-10-19 | 2006-03-22 | 东北大学 | Intelligent optimized control method for comprehensive production index in ore dressing process |
| CN104318313A (en) * | 2014-09-19 | 2015-01-28 | 东北大学 | Intelligent decision system and method for ore dressing total flow operation index on the basis of case-based reasoning |
Non-Patent Citations (3)
| Title |
|---|
| 基于案例推理的浮选过程智能优化设定;耿增显;《东北大学学报》;20080615;第29卷(第6期);第761-764页 |
| 浮选药剂智能优化设定控制方法的研究;耿增显;《仪器仪表学报》;20081215;第29卷(第12期);第2447-2491页 |
| 浮选过程混合智能优化设定控制方法;李海波;《东北大学学报》;20120115;第33卷(第1期);第1-5页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106406257A (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106406257B (en) | A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning | |
| CN109297689B (en) | Large-scale hydraulic machinery intelligent diagnosis method introducing weight factors | |
| CN111340791A (en) | Photovoltaic module unsupervised defect detection method based on GAN improved algorithm | |
| CN111208793B (en) | State monitoring method of non-stationary industrial process based on slow characteristic analysis | |
| CN110110780B (en) | Image classification method based on antagonistic neural network and massive noise data | |
| CN110033141B (en) | Method for establishing desulfurization system operation condition database | |
| CN110596506A (en) | Converter fault diagnosis method based on time convolution network | |
| CN103631681A (en) | Method for online restoring abnormal data of wind power plant | |
| CN101908214B (en) | Moving object detection method with background reconstruction based on neighborhood correlation | |
| CN106292292A (en) | The floatation of iron ore dosing Optimal Setting method and system of case-based reasioning | |
| CN102778843A (en) | Operation control method of high magnetic grading process | |
| CN101738998A (en) | System and method for monitoring industrial process based on local discriminatory analysis | |
| CN110889441A (en) | Distance and point density based substation equipment data anomaly identification method | |
| CN113283491A (en) | Fault diagnosis method of electric vehicle alternating current charging pile based on optimized deep confidence network | |
| CN116992385B (en) | Abnormal detection method and system for water meter consumption of Internet of things | |
| CN105425777B (en) | A kind of chemical process failure monitoring method based on Active Learning | |
| Yan et al. | Estimation of copper concentrate grade for copper flotation | |
| CN103823461A (en) | Industrial circulating water concentration multiple acquisition system capable of conducting online fault diagnosis | |
| CN111338310B (en) | Industrial process steady-state working condition identification and classification method | |
| CN111204867B (en) | Membrane bioreactor-MBR membrane pollution intelligent decision-making method | |
| CN116089843B (en) | New energy settlement data anomaly detection and early warning method based on data clustering | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN107121490A (en) | The evaluation method of running status in a kind of hydrometallurgy process | |
| CN114692922B (en) | Ore grindability acquisition method, acquisition device and prediction model | |
| CN114065651A (en) | Fault time prediction method for rotary equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |