CN113792417B - Strong magnetic motor current optimization method based on ore feeding parameters and intelligent algorithm - Google Patents
Strong magnetic motor current optimization method based on ore feeding parameters and intelligent algorithm Download PDFInfo
- Publication number
- CN113792417B CN113792417B CN202110966579.7A CN202110966579A CN113792417B CN 113792417 B CN113792417 B CN 113792417B CN 202110966579 A CN202110966579 A CN 202110966579A CN 113792417 B CN113792417 B CN 113792417B
- Authority
- CN
- China
- Prior art keywords
- ore feeding
- strong magnetic
- follows
- machine
- magnetic
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Manufacture And Refinement Of Metals (AREA)
Abstract
The invention relates to a strong magnetic machine current optimization method based on ore feeding parameters and an intelligent algorithm, which is characterized by comprising the following steps: 1) Collecting ore feeding parameters, tailing grade and magnetic induction intensity data of a strong magnetic machine; 2) Establishing a data sample library; 3) Fitting a function model between the tailings grade and the ore feeding parameters and magnetic induction intensity through a neural network regression algorithm; 4) Establishing constraint conditions and establishing a strong magnetic machine excitation current and magnetic induction intensity target optimization model; 5) And inputting field ore feeding parameters, and calculating the optimal exciting current suitable for the current working condition through a target optimization model. The invention has the advantages that: according to the change of the ore feeding property, the optimal magnetic induction intensity of the strong magnetic machine is analyzed and judged by combining with an artificial intelligence algorithm, a corresponding exciting current value is calculated, guidance is provided for operators, and the selection process of the strong magnetic machine is always in an optimal working state.
Description
Technical Field
The invention belongs to the technical field of optimization of magnetic separation processes, and particularly relates to a strong magnetic motor current optimization method based on ore feeding parameters and an intelligent algorithm.
Background
In the strong magnetic tailing discarding operation of the concentrating mill, the ore feeding property of the strong magnetic machine is different, and besides the differences of internal factors such as mineral composition, embedding granularity and the like, the apparent appearance mainly shows that the parameters such as ore feeding grade, ore feeding granularity, ore feeding concentration and the like have fluctuation, and the index of the strong magnetic tailing grade is influenced. In theory, in the process of throwing qualified tailings by strong magnetic separation, reasonable exciting current of the strong magnetic machine needs to be set according to ore feeding parameters, so that the magnetic induction intensity generated by the strong magnetic machine reaches a range value suitable for the current working condition, and further the strong magnetic tailing throwing operation effect is improved, and the concept is widely accepted by laboratory researchers and engineering application workers. An experienced operator of an actual concentrating mill generally carries out judgment according to the assayed parameters of the granularity of the ore feeding, the ore feeding grade, the ore feeding concentration and the tailing grade, sets the proper value of the exciting current of the strong magnetic machine according to experience, or determines the optimal exciting current value of the strong magnetic machine by carrying out a comparison experiment of a plurality of groups of current set values and the tailing grade. At present, since the adjustment of the excitation current of the field intensity magnet machine at present is not an effective intelligent method, an auxiliary operator effectively judges the most suitable magnetic induction intensity of working conditions, and further sets the corresponding excitation current value in time, the field intensity magnet machine cannot be accurately and timely adjusted to be always in the optimal production state, and the technical and economic indexes of the field intensity magnet tail-throwing operation are adversely affected.
Disclosure of Invention
The invention aims to provide a strong magnetic machine current optimization method based on ore feeding parameters and an intelligent algorithm, which solves the problem that the setting of exciting current of a strong magnetic machine mainly depends on experience of technicians, and ensures that the magnetic separation process of the strong magnetic machine is always in a good state.
The invention aims at realizing the following technical scheme:
the invention discloses a strong magnetic machine current optimization method based on ore feeding parameters and an intelligent algorithm, which is characterized by comprising the following steps:
step 1: collecting ore feeding parameters and magnetic induction intensity data of the ferromagnetic machine, and collecting assay value data of the corresponding ferromagnetic machine tailings;
step 2: establishing a sample library according to the data in the step 1;
step 3: fitting the relation between the tailing grade and the ore feeding parameter and the magnetic induction intensity of samples in a sample library through a neural network regression algorithm, and storing the relation in a function model;
step 4: combining an intelligent optimization algorithm and the function model in the step 3, establishing constraint conditions, establishing a relationship model of exciting current and magnetic induction intensity of the strong magnetic machine, and establishing a target optimization model;
step 5: inputting on-site ore feeding parameters, and calculating the optimal exciting current suitable for the current working condition through the target optimization model obtained in the step 4.
In step 1, the feeding parameters include feeding grade, feeding granularity and feeding concentration.
In the step 3, the relation between the tailing grade, the ore feeding parameter and the magnetic induction intensity is fitted and stored in a function model, and the specific steps are as follows:
step 3.1: the method comprises the steps of scrambling all samples, randomly sequencing, taking a part of samples as training data, and taking the rest samples as test data;
step 3.2: fitting the data through a neural network, and testing the fitting result to obtain a function model as follows:
wherein: g w The grade of tailings, the concentration of C is the ore feeding concentration, g s For the ore feeding grade, M is the ore feeding granularity, and T is the magnetic induction intensity.
In step 4, the definite constraint condition is established, a target optimization model is established, and a function model of exciting current and magnetic induction intensity of the ferromagnetic machine is established, wherein the specific steps are as follows:
step 4.1: establishing constraints
The constraint conditions were established as follows:
ore feed concentration C: according to the technological requirements of the field intensity magnetic tail-casting operation, the feeding concentration constraint range of the strong magnetic machine is as follows:
C min ≤C≤C max
ore feed particle size M: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the constraint range of the ore feeding granularity of the strong magnetic machine is as follows:
M min ≤M≤M max
grade g of ore feed s : according to the technological requirements of the existing field intensity magnetic tailing-throwing operation, the feeding grade constraint range of the strong magnetic machine is as follows:
g smin ≤g s ≤g smax
magnetic induction T: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the magnetic induction intensity constraint range of the strong magnetic machine is as follows:
T min ≤T≤T max
excitation current a: according to the technological requirements of the field intensity magnetic tail-casting operation, the exciting current constraint range of the strong magnetic machine is as follows:
A min ≤A≤A max
step 4.2: establishing a function model of excitation current A and magnetic induction intensity T of the strong magnetic machine
The function model of the excitation current A and the magnetic induction intensity T of the ferromagnetic machine is as follows:
T＝f AT (A)
step 4.3 building a target optimization model
The target optimization model is as follows:
compared with the prior art, the invention has the advantages that:
according to the method, according to the change of the ore feeding property of the strong magnetic machine, the magnetic induction intensity most suitable for the current magnetic separation process is analyzed and judged by combining with an artificial intelligent algorithm, the corresponding exciting current value of the strong magnetic machine is calculated, guidance can be provided for setting a reasonable exciting current value for an operator, and the strong magnetic machine separation process is ensured to be always in an optimal working state.
Drawings
FIG. 1 is a schematic block diagram of the flow structure of the method of the present invention.
Detailed Description
The invention is further described with reference to the drawings and detailed description which follow:
example 1
As shown in fig. 1, taking the actual situation of strong magnetic tailing discarding operation of a certain concentrating mill i as an example, the invention relates to a strong magnetic current optimization method based on ore feeding parameters and an intelligent algorithm, which is characterized by comprising the following steps:
step 1: collecting ore feeding parameters and magnetic induction intensity data of a strong magnetic machine, wherein the ore feeding parameters comprise ore feeding concentration, ore feeding grade and ore feeding granularity; meanwhile, collecting assay value data of the grade of the corresponding strong magnetic tail ore;
step 2: establishing a sample library according to the data in the step 1;
step 3: fitting the relation between the tailing grade and the ore feeding parameter and the magnetic induction intensity of samples in a sample library through a neural network regression algorithm, and storing the relation in a function model;
step 3.1: the method comprises the steps of scrambling all samples, and randomly sequencing; taking a sample of the first fifth as training data and the second fifth as test data;
step 3.2: fitting the training data through a neural network, testing the fitting result, and considering that the training result is satisfactory when the testing error is less than 0.1%, so as to obtain a function model as follows:
wherein: g w The grade of tailings, the concentration of C is the ore feeding concentration, g s For the ore feeding grade, M is the ore feeding granularity, and T is the magnetic induction intensity.
Step 4: and (3) combining an intelligent optimization algorithm and the function model in the step (3), establishing constraint conditions, establishing a relation model of exciting current and magnetic induction intensity of the strong magnetic machine, and establishing a target optimization model, wherein the method comprises the following steps of:
step 4.1: establishing constraints
The constraint conditions were established as follows:
ore feed concentration C: according to the technological requirements of the field intensity magnetic tail-casting operation, the feeding concentration constraint range of the strong magnetic machine is specifically as follows:
26％≤C≤31％
ore feed particle size M: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the constraint range of the ore feeding granularity of the strong magnetic machine is specifically as follows:
M≤0.075mm
grade g of ore feed s : according to the technological requirements of the field intensity magnetic tailing-throwing operation, the ore feeding grade constraint range of the strong magnetic machine is specifically as follows:
25％≤g s ≤31％
magnetic induction T: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the magnetic induction intensity constraint range of the strong magnetic machine is specifically as follows:
1.0T≤T≤1.3T
excitation current a: according to the technological requirements of the field intensity magnetic tail-casting operation, the exciting current constraint range of the strong magnetic machine is specifically as follows:
700A≤A≤1300A
step 4.2: establishing a function model of excitation current A and magnetic induction intensity T of the strong magnetic machine
The function model of the excitation current A and the magnetic induction intensity T of the ferromagnetic machine is as follows:
T＝f AT (A)
step 4.3 building a target optimization model
The target optimization model is as follows:
step 5: and (3) inputting on-site ore feeding parameters, and calculating the optimal exciting current suitable for the current working condition through the target optimization model obtained in the step (4.3). The specific data of the on-site ore feeding parameters are shown in table 1:
table 1 ore feeding parameters
Inputting the on-site ore feeding parameters in table 1, calculating the magnetic induction intensity adapting to the current ore feeding property through the target optimization model in step 4, converting the magnetic induction intensity into an excitation current value, outputting the excitation current value, and outputting the predicted tailing grade under the magnetic field condition, wherein the final product grade result and the actual test result are shown in the following table 2:
TABLE 2 excitation current optimization results and tailings grade
Example 2
As shown in fig. 1, taking the actual situation of strong magnetic tailing discarding operation of a certain concentrating mill II as an example, the method for optimizing the strong magnetic current based on ore properties and intelligent algorithm has the specific steps the same as those of the embodiment 1. The difference is that:
step 4.1: establishing constraints
The constraint conditions were established as follows:
ore feed concentration C: according to the technological requirements of the field intensity magnetic tail-casting operation, the feeding concentration constraint range of the strong magnetic machine is specifically as follows:
26％≤C≤33％
ore feed particle size M: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the constraint range of the ore feeding granularity of the strong magnetic machine is specifically as follows:
M≤0.075mm
grade g of ore feed s : according to the technological requirements of the field intensity magnetic tailing-throwing operation, the ore feeding grade constraint range of the strong magnetic machine is specifically as follows:
23％≤g s ≤30％
magnetic induction T: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the magnetic induction intensity constraint range of the strong magnetic machine is specifically as follows:
1.0T≤T≤1.3T
excitation current a: according to the technological requirements of the field intensity magnetic tail-casting operation, the exciting current constraint range of the strong magnetic machine is specifically as follows:
700A≤A≤1300A
step 4.2: establishing a function model of excitation current A and magnetic induction intensity T of the strong magnetic machine
The function model of the excitation current A and the magnetic induction intensity T of the ferromagnetic machine is as follows:
T＝f AT (A)
step 4.3 building a target optimization model
The target optimization model is as follows:
step 5: and (3) inputting on-site ore feeding parameters, and calculating the optimal exciting current suitable for the current working condition through the target optimization model obtained in the step (4.3). The specific data of the on-site feeding parameters are shown in table 3:
TABLE 3 Ore feeding parameters
And (3) inputting the on-site ore feeding parameters in table 3, calculating the magnetic induction intensity adapting to the current ore feeding property through the target optimization model in step 4, and converting the magnetic induction intensity into an excitation current value to output. And outputting the predicted tailing grade under the magnetic field condition, wherein the final product grade result and the actual test result are shown in table 4:
TABLE 4 excitation current optimization results and tailings grade
Compared with the existing method, the strong-magnet current optimization method based on the ore feeding parameters and the intelligent algorithm has the following advantages: the industrial magnetic separation operation process parameter data is used as a drive, and the magnetic field environment most suitable for the current magnetic separation process working condition is analyzed and judged by combining with an artificial intelligent algorithm, so that the corresponding exciting current value is calculated, and guidance can be provided for setting a reasonable exciting current value for an operator; meanwhile, manual intervention is reduced, and unnecessary errors are avoided.
Claims (1)
1. The strong-magnet current optimization method based on the ore feeding parameters and the intelligent algorithm is characterized by comprising the following steps:
step 1: collecting ore feeding parameters and magnetic induction intensity data of the ferromagnetic machine, and collecting assay value data of the corresponding ferromagnetic machine tailings;
in the step 1, the ore feeding parameters comprise ore feeding grade, ore feeding granularity and ore feeding concentration;
step 2: establishing a sample library according to the data in the step 1;
step 3: fitting the relation between the tailing grade and the ore feeding parameter and the magnetic induction intensity of samples in a sample library through a neural network regression algorithm, and storing the relation in a function model;
in the step 3, the relation between the tailing grade, the ore feeding parameter and the magnetic induction intensity is fitted and stored in a function model, and the specific steps are as follows:
step 3.1: the method comprises the steps of scrambling all samples, randomly sequencing, taking a part of samples as training data, and taking the rest samples as test data;
step 3.2: fitting the data through a neural network, and testing the fitting result to obtain a function model as follows:
wherein: g w The grade of tailings, the concentration of C is the ore feeding concentration, g s For ore feeding grade, M is ore feeding granularity, and T is magnetic induction intensity;
step 4: combining an intelligent optimization algorithm and the function model in the step 3, establishing constraint conditions, establishing a relationship model of exciting current and magnetic induction intensity of the strong magnetic machine, and establishing a target optimization model;
in step 4, the definite constraint condition is established, a target optimization model is established, and a function model of exciting current and magnetic induction intensity of the ferromagnetic machine is established, wherein the specific steps are as follows:
step 4.1: establishing constraints
The constraint conditions were established as follows:
ore feed concentration C: according to the technological requirements of the field intensity magnetic tail-casting operation, the feeding concentration constraint range of the strong magnetic machine is as follows:
C min ≤C≤C max ，
ore feed particle size M: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the constraint range of the ore feeding granularity of the strong magnetic machine is as follows:
M min ≤M≤M max ，
grade g of ore feed s : according to the technological requirements of the existing field intensity magnetic tailing-throwing operation, the feeding grade constraint range of the strong magnetic machine is as follows:
g smin ≤g s ≤g smax ，
magnetic induction T: according to the technological requirements of the existing field intensity magnetic tail-casting operation, the magnetic induction intensity constraint range of the strong magnetic machine is as follows:
T min ≤T≤T max ，
excitation current a: according to the technological requirements of the field intensity magnetic tail-casting operation, the exciting current constraint range of the strong magnetic machine is as follows:
A min ≤A≤A max ，
step 4.2: the function model of the strong magnetic machine exciting current A and the magnetic induction intensity T is established as follows:
T＝f AT (A)，
step 4.3 building a target optimization model
The target optimization model is as follows:
step 5: inputting on-site ore feeding parameters, and calculating the optimal exciting current suitable for the current working condition through the target optimization model obtained in the step 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110966579.7A CN113792417B (en) | 2021-08-23 | 2021-08-23 | Strong magnetic motor current optimization method based on ore feeding parameters and intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110966579.7A CN113792417B (en) | 2021-08-23 | 2021-08-23 | Strong magnetic motor current optimization method based on ore feeding parameters and intelligent algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113792417A CN113792417A (en) | 2021-12-14 |
| CN113792417B true CN113792417B (en) | 2023-10-20 |
Family
ID=78876204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110966579.7A Active CN113792417B (en) | 2021-08-23 | 2021-08-23 | Strong magnetic motor current optimization method based on ore feeding parameters and intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792417B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115970883A (en) * | 2023-01-05 | 2023-04-18 | 鞍钢集团矿业有限公司 | Optimization method for hematite strong magnetic separation process parameters |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120109211A (en) * | 2011-03-28 | 2012-10-08 | 동아대학교 산학협력단 | Optimal design method of direct-driven pm wind generator for decreasing pm using rsm |
| CN103617456A (en) * | 2013-12-04 | 2014-03-05 | 东北大学 | Operating index optimization method in beneficiation process |
| CN103617470A (en) * | 2013-12-19 | 2014-03-05 | 东北大学 | Optimization method for mineral separation comprehensive production index under equipment capability changing condition |
| CN109543240A (en) * | 2018-10-30 | 2019-03-29 | 西安理工大学 | A kind of current transformer modeling method based on dynamic area saturation J-A theory |
-
2021
- 2021-08-23 CN CN202110966579.7A patent/CN113792417B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120109211A (en) * | 2011-03-28 | 2012-10-08 | 동아대학교 산학협력단 | Optimal design method of direct-driven pm wind generator for decreasing pm using rsm |
| CN103617456A (en) * | 2013-12-04 | 2014-03-05 | 东北大学 | Operating index optimization method in beneficiation process |
| CN103617470A (en) * | 2013-12-19 | 2014-03-05 | 东北大学 | Optimization method for mineral separation comprehensive production index under equipment capability changing condition |
| CN109543240A (en) * | 2018-10-30 | 2019-03-29 | 西安理工大学 | A kind of current transformer modeling method based on dynamic area saturation J-A theory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113792417A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111694320B (en) | Machine tool self-adaptive control method considering flutter suppression | |
| CN104965532B (en) | Cement raw material ingredient control system and method | |
| CN113792417B (en) | Strong magnetic motor current optimization method based on ore feeding parameters and intelligent algorithm | |
| CN1940781A (en) | Method and system for controlling a batch process | |
| CN103617456B (en) | A kind of ore dressing process operating index optimization method | |
| CN106814719B (en) | A kind of whole grinding Optimal Control System of cement joint half and method | |
| CN1285977C (en) | Grinding system intelligent optimization initialization method based on case ratiocination | |
| CN109592376B (en) | Automatic material distribution control device for magnetic roller | |
| CN102778843A (en) | Operation control method of high magnetic grading process | |
| CN114253219A (en) | Grinding force self-adaptive control method and system based on end face grinding | |
| CN109885900A (en) | A kind of Cutting parameters optimization method based on gray analysis | |
| CN110193427B (en) | Automatic control method for lime addition amount in copper flotation process | |
| CN1525153A (en) | Flexible measuring method for overflow particle size specification of ball mill grinding system | |
| CN205128169U (en) | Pulp density controlling means in column type mineral processing equipment | |
| CN111617876B (en) | Method for optimizing online comprehensive operation of coal mill | |
| CN116638511A (en) | Method for improving labor efficiency of production line robot based on machine tool refueling time model | |
| CN87108168A (en) | A kind of method of controlling grinding particle size | |
| CN110750074B (en) | Numerical control machining optimization system and method based on physical simulation | |
| CN110455781B (en) | LIBS (laser induced breakdown Spectroscopy) online detection system for phosphate ore dressing system and application of LIBS online detection system | |
| CN108802288B (en) | Method for analyzing product quality based on mineral characteristics | |
| CN104898563A (en) | Bowl mill control method | |
| CN109331984B (en) | Expert intelligent configuration cloud control system and control method for ball mill | |
| CN107344138A (en) | A kind of ore mill control method and device | |
| CN114861421B (en) | Intelligent optimization control system and method for air flow mill classifying wheel | |
| CN114653485B (en) | Flotation process fuzzy control method based on foam flow velocity |
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 |