CN103377247A - Intelligent extraction method for ore grinding control cases - Google Patents
Intelligent extraction method for ore grinding control cases Download PDFInfo
- Publication number
- CN103377247A CN103377247A CN201210129285XA CN201210129285A CN103377247A CN 103377247 A CN103377247 A CN 103377247A CN 201210129285X A CN201210129285X A CN 201210129285XA CN 201210129285 A CN201210129285 A CN 201210129285A CN 103377247 A CN103377247 A CN 103377247A
- Authority
- CN
- China
- Prior art keywords
- case
- ore
- ore grinding
- grinding
- concentration
- 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
Abstract
The invention relates to an intelligent extraction method for ore grinding control cases. The intelligent extraction method for the ore grinding control cases comprises respectively installing information collection terminals on the ore grinding feeding opening, the ore grinding discharging opening and a laboratory in a raw ore field; sending collected signals of ore categories, ore grades, ore distributing granularity, grindability, ore grinding granularity, ball grinder inlet supplementary flow, classifier overflow density, hydrocyclone feeding density, hydrocyclone feeding pressures to a database of a case extraction computer through the information collection terminals; analyzing and processing the signals through the case extraction computer to extract valid and optimized ore grinding control cases; sending the extracted ore grinding control cases to a process control system of the ore grinding process. The intelligent extraction method for the ore grinding control cases has the advantages of overcoming the defects that manual confirming ore grinding control initial case base is redundant or the degree of coverage is insufficient, effectively improving ore grinding production granularity yield, enabling ore grinding production to be stable and having remarkable economic benefits.
Description
Technical field
The present invention relates to a kind of extracting method of case, relate in particular to a kind of intelligent extract method that utilizes a large amount of historical datas to extract ore grinding control case under the complex working condition.
Background technology
Grinding process is the important component part of mineral processing production, and its task is that solution is left, and provides qualified selected material for follow-up sorting operation.The quality of grinding process control is directly connected to the production targets such as metal recovery rate, concentrate grade, finally can have influence on the macroeconomic technical indicator in ore dressing plant.In recent years, be difficult to guarantee uniformity for ore properties in the mineral processing production, the boundary condition fluctuation range of producing is large, equipment attrition and the repeatedly rear device characteristics appearance of maintenance variation, poor controllability, operating condition change the characteristics such as frequent and the optimal control based on reasoning by cases adopted has obtained preferably effect.Good initial case is the correct effectively key of operation of whole control system, initial case library is normally determined input by the domain expert in actual applications, but because the comprehensive complex nature that grinding process has, so that artificial definite initial control case, redundancy or the coverage that may cause controlling case are inadequate, for avoiding these problems, the present invention has provided a kind of intelligent extract method of ore grinding control case.
Summary of the invention
In order to solve the problems of the technologies described above the intelligent extract method that the invention provides a kind of ore grinding control case, purpose is automatically to extract the Optimal Control case of grinding process in the database that has accumulated a large amount of historical datas.
For reaching the intelligent extract method of above-mentioned purpose ore grinding control of the present invention case, comprise the steps: at former mining site, the ore grinding material inlet, the ore grinding discharge gate, the laboratory is the mount message acquisition terminal respectively; The signal that ore kind, the grade of ore, ore disseminated grain size, grindability, grinding particle size, the bowl mill entrance that information acquisition terminal will gather added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydrocyclone feed force is sent in the database of case extraction computing machine, case is extracted computing machine signal is carried out analyzing and processing, extract effectively, then the ore grinding control case of optimizing is sent to the ore grinding control case that extracts in the Process Control System of grinding process.
Described case extraction computing machine carries out analyzing and processing to signal and comprises: determine that control case structure, case are extracted pretreatment, case is extracted the classification of data and is combined into the case that then case extracts all categories, then consisted of initial case library.
Described definite control case structure comprises two parts, namely comprises the operating mode description of case and the solution of case; It is to affect the factor of ore grinding that the operating mode of case is described, and comprises that ore kind, head grade, ore disseminated grain size fineness, grindability and grinding particle size are as the operating mode description of case; The solution of case is the factor that ore grinding need to be controlled, and comprises that new mine-supplying quantity, bowl mill entrance add discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force as the solution of case.
It is that the historical data in the database in a period of time is organized according to top definite case structure that described case is extracted pretreatment, is namely added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force and is consisted of a pending data group by ore kind, head grade, ore disseminated grain size fineness, grindability, grinding particle size, new mine-supplying quantity, bowl mill entrance; And filter unusual record, completion missing values and utilize running mean to process denoising is added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force data recording with the underproof new mine-supplying quantity of grinding particle size on the same day, bowl mill entrance and is removed.
The classification that described case is extracted data is that the data recording that it is good that case is extracted pretreatment is utilized Self-Organizing Feature Maps, by self training, automatically input pattern is classified.
The described case that is combined into is to extract the good record of classification automatic classification of data according to case, in the record that it is good that each class is classified, find out a best record of time in grinding production effect, the ore kind that this record is corresponding, head grade, ore disseminated grain size fineness, grindability and grinding particle size are described as the operating mode of case, the new mine-supplying quantity that this record is corresponding, the bowl mill entrance is added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force are as the solution of case, the operating mode description of case and the solution of case correspond to a new case, deposit in the case library.
Advantageous effect of the present invention: the present invention can avoid manually determining that ore grinding controls initial case library redundancy or the inadequate shortcoming of coverage, and qualification rate that can Effective Raise time in grinding production granularity is stablized time in grinding production, has significant economic benefit.
Embodiment
The intelligent extract method of ore grinding control case of the present invention comprises the steps: at former mining site, the ore grinding material inlet, and the ore grinding discharge gate, the laboratory is the mount message acquisition terminal respectively; The signal that ore kind, the grade of ore, ore disseminated grain size, grindability, grinding particle size, the bowl mill entrance that information acquisition terminal will gather added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydrocyclone feed force is sent in the database of case extraction computing machine, case is extracted computing machine signal is carried out analyzing and processing, extract effectively, then the ore grinding control case of optimizing is sent to the ore grinding control case that extracts in the Process Control System of grinding process.
Case extraction computing machine carries out analyzing and processing to signal and comprises: determine that control case structure, case are extracted pretreatment, case is extracted the classification of data and is combined into the case that then case extracts all categories, then consisted of initial case library.
Determine that control case structure comprises two parts, namely comprises the operating mode description of case and the solution of case; It is to affect the factor of ore grinding that the operating mode of case is described, and comprises that ore kind, head grade, ore disseminated grain size fineness, grindability and grinding particle size are as the operating mode description of case; The solution of case is the factor that ore grinding need to be controlled, and comprises that new mine-supplying quantity, bowl mill entrance add discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force as the solution of case.For example with ore kind K, head grade
, ore disseminated grain size fineness
, grindability
Describe as the operating mode of case with grinding particle size Rs, use respectively f1, f2 ..., f5 with the factor that ore grinding need to be controlled, comprises new mine-supplying quantity
, the bowl mill entrance adds discharge
, overflow concentration in classifier
, the hydrocyclone feed ore concentration
With the solution of hydraulic cyclone feed force P as case, use respectively fs1, fs2 ... fs5 represents that then the structure of ore grinding control case is as shown in the table:
It is that the historical data in the database in a period of time is organized according to top definite case structure that case is extracted pretreatment, is namely added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force and is consisted of a pending data group by ore kind, head grade, ore disseminated grain size fineness, grindability, grinding particle size, new mine-supplying quantity, bowl mill entrance; And filter unusual record, completion missing values and utilize running mean to process denoising is added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force data recording with the underproof new mine-supplying quantity of grinding particle size on the same day, bowl mill entrance and is removed.To guarantee that the case of excavating can both guarantee the qualified of time in grinding production.
The classification that case is extracted data is that the data recording that it is good that case is extracted pretreatment is utilized Self-Organizing Feature Maps, by self training, automatically input pattern is classified.
Being combined into case is the good record of classification automatic classification that extracts data according to case, in the record that it is good that each class is classified, finds out a best record of time in grinding production effect, ore kind K, head grade that this record is corresponding
, ore disseminated grain size fineness
, grindability
With grinding particle size Rs the new mine-supplying quantity that this record is corresponding is described as the operating mode of case
, the bowl mill entrance adds discharge
, overflow concentration in classifier
, the hydrocyclone feed ore concentration
With the solution of hydraulic cyclone feed force P as case, the solution of the description of the operating mode of case and case corresponds to a new case, deposits in the case library.Then extract the case of all categories, then consisted of initial case library.
Claims (6)
1. the intelligent extract method of ore grinding control case is characterized in that comprising the steps: at former mining site, the ore grinding material inlet, and the ore grinding discharge gate, the laboratory is the mount message acquisition terminal respectively; The signal that ore kind, the grade of ore, ore disseminated grain size, grindability, grinding particle size, the bowl mill entrance that information acquisition terminal will gather added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydrocyclone feed force is sent in the database of case extraction computing machine, case is extracted computing machine signal is carried out analyzing and processing, extract effectively, then the ore grinding control case of optimizing is sent to the ore grinding control case that extracts in the Process Control System of grinding process.
2. ore grinding according to claim 1 is controlled the intelligent extract method of case, it is characterized in that described case extraction computing machine carries out analyzing and processing to signal and comprises: determine that control case structure, case are extracted pretreatment, case is extracted the classification of data and is combined into the case that then case extracts all categories, then consisted of initial case library.
3. the intelligent extract method of ore grinding control case according to claim 2 is characterized in that described definite control case structure comprises two parts, namely comprises the operating mode description of case and the solution of case; It is to affect the factor of ore grinding that the operating mode of case is described, and comprises that ore kind, head grade, ore disseminated grain size fineness, grindability and grinding particle size are as the operating mode description of case; The solution of case is the factor that ore grinding need to be controlled, and comprises that new mine-supplying quantity, bowl mill entrance add discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force as the solution of case.
4. ore grinding according to claim 2 is controlled the intelligent extract method of case, it is characterized in that it is that the historical data in the database in a period of time is organized according to top definite case structure that described case is extracted pretreatment, namely add discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force and consist of a pending data group by ore kind, head grade, ore disseminated grain size fineness, grindability, grinding particle size, new mine-supplying quantity, bowl mill entrance; And filter unusual record, completion missing values and utilize running mean to process denoising is added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force data recording with the underproof new mine-supplying quantity of grinding particle size on the same day, bowl mill entrance and is removed.
5. ore grinding according to claim 2 is controlled the intelligent extract method of case, it is characterized in that it is that the data recording that it is good that case is extracted pretreatment is utilized Self-Organizing Feature Maps that described case is extracted the classification of data, by self training, automatically input pattern is classified.
6. ore grinding according to claim 2 is controlled the intelligent extract method of case, it is characterized in that the described case that is combined into is to extract the good record of classification automatic classification of data according to case, in the record that it is good that each class is classified, find out a best record of time in grinding production effect, the ore kind that this record is corresponding, head grade, ore disseminated grain size fineness, grindability and grinding particle size are described as the operating mode of case, the new mine-supplying quantity that this record is corresponding, the bowl mill entrance is added discharge, overflow concentration in classifier, hydrocyclone feed ore concentration and hydraulic cyclone feed force are as the solution of case, the operating mode description of case and the solution of case correspond to a new case, deposit in the case library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210129285.XA CN103377247B (en) | 2012-04-28 | 2012-04-28 | The intelligent extract method of grind mineral control case |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210129285.XA CN103377247B (en) | 2012-04-28 | 2012-04-28 | The intelligent extract method of grind mineral control case |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103377247A true CN103377247A (en) | 2013-10-30 |
| CN103377247B CN103377247B (en) | 2016-11-02 |
Family
ID=49462373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210129285.XA Active CN103377247B (en) | 2012-04-28 | 2012-04-28 | The intelligent extract method of grind mineral control case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103377247B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103713619A (en) * | 2013-12-20 | 2014-04-09 | 东北大学 | Test method for ore grinding process operation control method |
| CN109214415A (en) * | 2018-07-19 | 2019-01-15 | 西安建筑科技大学 | A kind of ore reduction grinding effect evaluation method |
| CN112598618A (en) * | 2020-11-16 | 2021-04-02 | 鞍钢集团矿业有限公司 | Mill ore feeding amount prediction method based on image recognition technology |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1598534A (en) * | 2004-07-28 | 2005-03-23 | 东北大学 | Soft investigating method for overflow grain index of ore grinding system based on case inference |
| CN1603986A (en) * | 2004-10-29 | 2005-04-06 | 东北大学 | Grinding system intelligent optimization initialization method based on case ratiocination |
| US20100258660A1 (en) * | 2007-12-14 | 2010-10-14 | University Of Kwazulu-Natal | Method of Grinding a Mineral Containing Ore |
-
2012
- 2012-04-28 CN CN201210129285.XA patent/CN103377247B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1598534A (en) * | 2004-07-28 | 2005-03-23 | 东北大学 | Soft investigating method for overflow grain index of ore grinding system based on case inference |
| CN1603986A (en) * | 2004-10-29 | 2005-04-06 | 东北大学 | Grinding system intelligent optimization initialization method based on case ratiocination |
| US20100258660A1 (en) * | 2007-12-14 | 2010-10-14 | University Of Kwazulu-Natal | Method of Grinding a Mineral Containing Ore |
Non-Patent Citations (2)
| Title |
|---|
| 杨新等: "选矿过程工艺指标确定方法及应用", 《控制工程》, vol. 16, no. 3, 20 May 2009 (2009-05-20) * |
| 柴天佑等: "选矿生产过程综合自动化系统", 《首届全国有色金属自动化技术与应用学术年会论文集》, 1 November 2003 (2003-11-01), pages 1 - 5 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103713619A (en) * | 2013-12-20 | 2014-04-09 | 东北大学 | Test method for ore grinding process operation control method |
| CN103713619B (en) * | 2013-12-20 | 2016-05-25 | 东北大学 | A kind of method of testing of grinding process progress control method |
| CN109214415A (en) * | 2018-07-19 | 2019-01-15 | 西安建筑科技大学 | A kind of ore reduction grinding effect evaluation method |
| CN109214415B (en) * | 2018-07-19 | 2021-11-02 | 西安建筑科技大学 | Method for judging ore crushing and grinding effect |
| CN112598618A (en) * | 2020-11-16 | 2021-04-02 | 鞍钢集团矿业有限公司 | Mill ore feeding amount prediction method based on image recognition technology |
| CN112598618B (en) * | 2020-11-16 | 2023-11-17 | 鞍钢集团矿业有限公司 | Image recognition technology-based ore feeding amount prediction method for mill |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103377247B (en) | 2016-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101559403B (en) | Method for concentrating extremely low-grade refractory magnetite | |
| CN102698871B (en) | Ore dressing technology for treating vanadium titano-magnetite | |
| CN104134120B (en) | System and method for monitoring ore-dressing production indexes | |
| CN105413842B (en) | The ore-dressing technique of Ultra-low-grade magnetite and system | |
| CN103736584B (en) | A kind of beneficiation method of high-grade copper-nickel sulphide ore | |
| CN104162475A (en) | High-efficiency and energy-saving new lean magnetite combined milling magnetic separation method | |
| CN103041920A (en) | Ore dressing method and ore dressing system suitable for lean magnetite ores | |
| AU2017422813B2 (en) | Iron fine removal and sorting system for magnetic hard rocks | |
| CN103827445A (en) | Sorting in mining operation | |
| CN101579654A (en) | Iron ore powder mineral dressing process | |
| CN102824956B (en) | Poor hematite grading level and narrow level sorting process | |
| CN104722396A (en) | Comprehensive utilization method of magnetite-containing country rock | |
| CN103203280A (en) | Dense-medium preparation technology for optimizing coal slime | |
| CN103377247A (en) | Intelligent extraction method for ore grinding control cases | |
| CN104815736A (en) | Preselecting process for surrounding rock containing magnetite | |
| CN107413517A (en) | A kind of beneficiation method for improving micro fine particle magnetite stone stage grinding and stage separation sorting index | |
| CN104056714A (en) | Beneficiation process for refractory micro-fine particle-graded iron-copper ore | |
| CN103920582B (en) | A kind of closed circuit grading technology being applicable to Bed for Fine Coal classification | |
| CN112588431A (en) | Ore grinding-weak magnetic strong magnetic-gravity separation-reverse flotation process for magnetic hematite | |
| CN104492615A (en) | Grinding classification method | |
| CN112330653A (en) | Online ore granularity detection method based on image recognition technology | |
| CN111495576A (en) | Ore dressing method for separating and separating garnet ores with uneven embedded particle sizes in split flow mode | |
| CN102000630B (en) | Technology for preparing iron ore concentrate | |
| CN103433122B (en) | A kind of medium tin ore sub-prime classification and sorting technique | |
| CN108993760A (en) | A kind of low-grade difficulty of weathering selects manganese ore sorting process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |