CN112327608B - Self-learning control method and device applied to semi-autogenous mill - Google Patents
Self-learning control method and device applied to semi-autogenous mill Download PDFInfo
- Publication number
- CN112327608B CN112327608B CN202011346547.9A CN202011346547A CN112327608B CN 112327608 B CN112327608 B CN 112327608B CN 202011346547 A CN202011346547 A CN 202011346547A CN 112327608 B CN112327608 B CN 112327608B
- Authority
- CN
- China
- Prior art keywords
- semi
- autogenous mill
- control
- current operation
- self
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
- G05B13/024—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a self-learning control method applied to a semi-autogenous mill, which comprises the following steps: s1: acquiring a process parameter set of the semi-autogenous mill and corresponding running state data, and performing normalization processing on the process parameter set to obtain a multi-dimensional data set; s2: processing the multidimensional data set by combining a control strategy adopted by the running state of the semi-autogenous mill based on a fuzzy C-means clustering algorithm to obtain a multi-classification center of the multidimensional data set; s3: optimizing and screening the multi-classification centers, and constructing a control library of the semi-autogenous mill; s4: and acquiring the current operation state of the semi-autogenous mill in real time, matching the current operation state with the control library, and controlling the process parameters of the semi-autogenous mill in real time by updating the current operation parameters. The invention is based on the control self-learning method and the self-learning operation control, realizes the real-time optimization of the working state of the semi-autogenous mill equipment so as to obtain the maximum economic benefit and obtain the maximum utilization rate of the semi-autogenous mills of different types and sizes, and has high stability.
Description
Technical Field
The invention belongs to the field of intelligent control of miners, and particularly relates to a self-learning control method and device applied to a semi-autogenous mill.
Background
The control algorithm based on the method represents the organic combination of the conventional control algorithm and the expert experience, is suitable for some controlled objects which are difficult to control or have poor control effect by using the conventional control algorithm alone, forms advanced control and intelligent control, including the control on a production process or mechanical equipment, and is difficult to extract the expert experience to represent, and forms an expert library which is hot. Researchers always search a method for self-learning and self-organizing a library, particularly, in the period of rapid updating of the prior art, researches on intelligent control and industrial big data analysis, deep learning and data mining become hot points in the fields of artificial intelligence and machine learning, unsupervised feature learning shows strong potential, a multi-dimensional structure and hidden features thereof are mined by using the multi-dimensional structure, different expression forms of knowledge can be obtained, rules hidden in data information are obtained, empirical knowledge with expert attributes is extracted and expressed to be effective, a control library is formed, a more effective and better control effect is obtained, and corresponding economic benefits are brought.
For example, ore grinding is a key step for screening high-quality ores in a beneficiation plant, a semi-autogenous mill is an important component of the SABC process, the semi-autogenous mill has the characteristics of multiple variables, nonlinearity, strong coupling, large hysteresis, time-varying property and the like, a good effect is difficult to obtain by a traditional control method, and automatic control in the prior art is difficult to achieve.
In the prior art, a plurality of mine plants realize control through conventional PID regulation, and the feeding quantity regulation automatically regulates the heavy plate frequency through PID to realize the optimal feeding quantity. The PID can automatically adjust the opening of the water supply valve through the water quantity detected by a water supply flowmeter of the semi-automatic grinding machine, thereby adjusting the concentration of the ground ore. The ores with different coarse grain grades on the heavy plate can influence the frequency data of the heavy plate to a certain extent, and the granularity of the ores is screened by adjusting and controlling the output frequency. In practice, however, a control library with comparable expert experience is lacking to implement control optimization to accommodate different variations in operating conditions.
Therefore, there is a strong need for an automatic control method, which processes the collected process parameter set of the semi-autogenous mill, compares the collected process parameter set with the experience of field advanced technical workers, finds out the relationship among the power, grinding noise, axial pressure, grinding concentration, ore feeding amount, etc. when the semi-autogenous mill is working, and makes the semi-autogenous mill self-learn to form a control library, so as to replace manual control to make the semi-autogenous mill operate in an optimal operation state, thereby improving the economic benefit of the ore dressing plant, improving the enterprise income, and promoting the technical transformation of the mining industry.
Disclosure of Invention
The invention aims to provide a self-learning control method and device applied to a semi-automatic mill, so as to achieve the technical effect of autonomously controlling semi-automatic mill equipment to be in an optimal working state.
In order to solve the problems, the technical scheme of the invention is as follows:
a self-learning control method applied to a semi-autogenous mill comprises the following steps:
s1: acquiring a process parameter set and corresponding operating state data of the semi-autogenous mill, performing normalization processing on the process parameter set, and combining the corresponding operating state data to obtain a multi-dimensional data set;
s2: processing the multidimensional data set based on a fuzzy C-means clustering algorithm in combination to obtain a multi-classification center of the multidimensional data set;
s3: optimally screening the multi-classification centers, removing redundancy of the multi-classification centers, and constructing a control library of the semi-autogenous mill;
s4: and providing the current operation parameters for the semi-autogenous mill in real time through the control library so as to realize the process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the control library obtains the current operation parameters and updates the current operation parameters to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters.
Further preferably, step S4 further comprises: and updating the control library, wherein the weight in the modification control intelligence library is configured and modified according to the operation result corresponding to the current operation state, so that the control library is updated.
In step S1, the normalization processing on the process parameter set specifically includes: the process parameter set is converted into a dimensionless value of 0 to 1, the calculation formula is as follows,
wherein X' is a normalized value, X is data of a process parameter set, and X is max Is the maximum value, X, in the process parameter set min Is the minimum value of the process parameter set.
Specifically, in step S2, the fuzzy C-means clustering algorithm has a calculation formula of
Wherein x is j Sample space, j = (1, 2, \8230;, N), w) i As a clustering center, i = (1, 2, \8230;, C), μ = ji For the sample space x j For the cluster center w i The degree of membership of (a) is,
wherein, i =1,2, \8230 \8230C; j =1,2, \8230;, N; and is provided with
m is a fuzzy index, and m belongs to (1, ∞);
further preferably, step S2 further comprises: correcting the fuzzy C-mean clustering algorithm to obtain a sample space x j In the form of data sets
Realizing extension, wherein l is the number of the parameter types of the process parameter set, so that the fuzzy C-means clustering algorithm can implement multi-dimensional data processing, and effectively distinguishing multi-classification centers with multi-level relation by using a multi-dimensional data set, namely clustering centers
Wherein, in step S4, the current operation parameters include: ore feed, feed water and heavy plate frequency of the semi-autogenous mill.
A self-learning control device for use in a semi-autogenous mill, comprising:
the data extraction module is used for acquiring a process parameter set and corresponding running state data of the semi-autogenous mill, carrying out normalization processing on the process parameter set and combining the corresponding running state data to obtain a multidimensional data set;
the data processing module is used for processing the multi-dimensional data set by combining a control strategy adopted by the running state of the semi-autogenous mill based on a fuzzy C-means clustering algorithm to obtain a multi-classification center of the multi-dimensional data set;
the data optimization module is used for carrying out optimization screening on the multi-classification centers, removing redundancy of the multi-classification centers and constructing a control library of the semi-autogenous mill;
and the process control module is used for providing the current operation parameters for the semi-autogenous mill in real time through the control library so as to realize the process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the current operation parameters are obtained and updated to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters.
Further preferably, the system further comprises a correction module for correcting the fuzzy C-means clustering algorithm, so that the fuzzy C-means clustering algorithm can implement multi-dimensional data processing, and multi-classification centers with a multi-level relation are effectively distinguished.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects:
the method is based on self-learning control, the influence of the running parameters of the semi-autogenous mill equipment on the motion form of the load particles is researched, and the effective relation between the parameters is established. And comparing the control strategies adopted by the running state of the semi-autogenous mill, finding out the relation among the data such as power, grinding sound, axial pressure, grinding ore concentration, ore feeding amount and the like when the semi-autogenous mill works, realizing self-learning operation control, forming a control library, replacing manual control, reducing manual labor force, optimizing the working state of the semi-autogenous mill equipment in real time, and obtaining the maximum economic benefit.
In addition, the library in the invention can realize self-updating optimization to adapt to different semi-autogenous mills so as to achieve the maximum utilization rate of the semi-autogenous mills of different models and sizes, and has the technical effects of small image caused by external factors and high stability.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.
FIG. 1 is a schematic flow chart of a self-learning control method applied to a semi-autogenous mill according to the present invention;
FIG. 2 is a schematic diagram of a self-learning control method applied to a semi-autogenous mill according to the present invention;
FIG. 3 is a schematic diagram of a self-learning control device applied to a semi-autogenous mill according to the present invention;
FIG. 4 is a schematic diagram of a multi-dimensional data set obtained by the self-learning control method applied to the semi-autogenous mill.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "one" means not only "only one" but also a case of "more than one".
The self-learning control method applied to the semi-autogenous mill provided by the invention is further described in detail by combining the attached drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims.
Example 1
Referring to fig. 1 and 2, the present embodiment provides a self-learning control method applied to a semi-autogenous mill, including the steps of:
s1: acquiring a process parameter set and corresponding running state data of the semi-autogenous mill, carrying out normalization processing on the process parameter set, and combining the corresponding running state data to obtain a multidimensional data set;
s2: processing the multi-dimensional data set by combining a control strategy adopted by the running state of the semi-autogenous mill based on a fuzzy C-means clustering algorithm to obtain a multi-classification center of the multi-dimensional data set;
s3: carrying out optimization screening on the multiple classification centers, removing redundancy of the multiple classification centers, and constructing a control library of the semi-autogenous mill;
s4: and providing the current operation parameters for the semi-autogenous mill in real time through the control library so as to realize the process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the control library obtains the current operation parameters and updates the current operation parameters to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters.
The running conditions of the semi-autogenous mill are researched a lot, the running efficiency of the equipment is improved from different angles, but the universality effect on different working conditions is poor. In the semi-autogenous mill equipment, ore and steel balls are used as ore grinding media, and meanwhile, in order to compensate the influences of full load, under load and over crushing, a proper amount of steel balls can enhance the ore grinding capacity and accelerate the ore grinding efficiency. The main control means for optimizing the running process of the semi-autogenous mill comprises 3 means of controlling the lumpiness, the ore quantity and the ore grinding concentration.
Specifically, referring to fig. 1, in this embodiment, step S1 specifically includes: acquiring multiple groups of process parameter sets and corresponding running state data of the semi-autogenous mill, wherein the number of the process parameter sets is more and more optimal, and the process parameter sets comprise: the size of the lump degree, the ore quantity and the ore grinding concentration, the operating condition data are the working condition of the semi-autogenous mill during operation, including: overload, overload trend, underload and underload trend. The multi-dimensional data set is obtained by converting the multi-group process parameter sets into dimensionless values from 0 to 1 through normalization processing and combining the corresponding running state data, the dimensionless calculation formula is as follows,
wherein X' is a normalized value, X is data of a process parameter set, and X is max Is the maximum value, X, in the process parameter set min Is the minimum value of the process parameter set.
Referring to fig. 1 to 4, in the present embodiment, step S2 is: and processing the multi-dimensional data set by combining a control strategy adopted by the running state of the semi-autogenous mill based on a fuzzy C-means clustering algorithm to obtain a multi-classification center of the multi-dimensional data set. Wherein, the control strategy comprises: the frequency of the heavy plate is adjusted to change the ore feeding amount, the opening degree of the water feeding valve is adjusted to change the concentration of ore grinding, and the output frequency is adjusted and controlled to screen the granularity of ore to change the size of the lump size. That is, the present embodiment mainly aims to find the relationship among the data such as power, grinding sound, axial pressure, grinding ore concentration, ore feeding amount and the like when the semi-autogenous mill works.
In this embodiment, a fuzzy C-means clustering algorithm is adopted, but other clustering algorithms may be selected. Specifically, the fuzzy C-means clustering algorithm has a calculation formula of
Wherein x is j Sample space, j = (1, 2, \8230;, N), w) i As a clustering center, i = (1, 2, \8230;, C), μ = ji For the sample space x j For the cluster center w i The degree of membership of (a) to (b),
wherein, i =1,2, \8230 \8230C; j =1,2, \8230;, N; and is
m is a fuzzy index, and m is an element (1, ∞))；
In this step, selecting a suitable learning algorithm is an extremely important step. The learning algorithm in the embodiment needs to have high convergence rate, can solve the problem of big data, and effectively obtains the deep level relation among data samples. For example, the fuzzy clustering algorithm performs deep feature learning in the clustering process, and the features to be extracted are structures that retain the original data while fully mining class patterns in the data. For high dimensional data, feature learning may be performed to eliminate redundant information, facilitating data class structure mining. For low-dimensional data, too little information or too low dimensionality cannot represent complete features, resulting in erroneous data mining, and therefore, only the links between data are found from fewer attributes to enrich the data information deeply and make the clustering analysis accurate and simple.
In addition, the method also comprises the step of correcting the learning method while the multi-classification center of the multi-dimensional data set is obtained by the learning algorithm, so that the multi-classification center of the multi-dimensional data set for distinguishing the multi-level relationship is obtained by effectively processing the multi-dimensional data by the learning method. Because the number of the process parameters influencing the operation of the equipment can be more than 3, every time when the number of the process parameters is more than 3, the clustering center obtained by the learning algorithm is more than one multi-classification center, and the subscript of the learning method is modified to adapt to the processing of the added multi-dimensional data set.
Referring to fig. 1 and fig. 2, in this embodiment, step S3 specifically is: based on the extraction, the multiple multi-classification centers in the step 2 are optimized and screened, and the judgment method is expressed as if (the condition is satisfied, namely w is i ) then (corresponding optimization operation), judging effectiveness, removing redundancy and constructing a control library. In addition, the effectiveness and the repeatability are judged according to the prior empirical operation, and an optimized control library is formed.
Referring to fig. 1 and 2, in the present embodiment, step S4 is: and providing the current operation parameters for the semi-autogenous mill in real time through a control library to realize the process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the control library obtains the current operation parameters and updates the current operation parameters to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters. In this example, the parameter range [0-0.5 ] is set to L for low, M for [0.5-0.8] for normal, and H for 0.8-1.0] for high, for example, and the optimization of ore grinding is similar to that in Table 1 compared to the prior empirical operation
TABLE 1 Ore grinding optimization
According to the ore grinding optimization, a currently sampled process data set is compared with a control library, the control library is a multi-classification center of a multi-dimensional data set, working conditions are judged, the most similar operation parameters are selected as the current operation parameters, and optimal control operation is implemented. The control operation comprises the steps of adjusting ore feeding amount, water feeding amount, heavy plate frequency and the like, and selecting the most suitable one from the control library according to the current working condition of the semi-autogenous mill, namely, the semi-autogenous mill obtains a set of optimal current operation parameters. The ore feeding amount is changed by adjusting the frequency of the heavy plate, so that the optimal ore feeding amount is realized; the opening degree of a water supply valve is adjusted through the water quantity detected by a water supply flowmeter of the semi-automatic grinding machine, so that the concentration of the ground ore is changed; the different ore of coarse fraction can cause certain influence to heavy board frequency data on the heavy board, sieves the ore granularity through adjusting control output frequency to change the lump size of grinding ore. The technological parameters of the semi-autogenous mill are controlled in real time by updating the current operating parameters, namely the ore feeding amount, the ore grinding concentration and the ore block size, so that the optimization of the working state of the semi-autogenous mill equipment is realized.
Referring to fig. 1, in this embodiment, step S4 further includes updating the control library, processing the operation result based on the operation result corresponding to the current operation state, and modifying the configuration and modifying the weight in the control intelligence library, so as to update the control library.
Example 2
Referring to fig. 3, the present embodiment provides a self-learning control device applied to a semi-autogenous mill based on the above embodiment 1, including:
the data extraction module is used for acquiring a process parameter set and corresponding running state data of the semi-autogenous mill, carrying out normalization processing on the process parameter set and combining the corresponding running state data to obtain a multidimensional data set;
the data processing module is used for processing the multi-dimensional data set by combining a control strategy adopted by the running state of the semi-autogenous mill based on a fuzzy C-means clustering algorithm to obtain a multi-classification center of the multi-dimensional data set;
the data optimization module is used for carrying out optimization screening on the multi-classification centers, removing redundancy of the multi-classification centers and constructing a control library of the semi-autogenous mill;
and the process control module is used for providing the current operation parameters for the semi-autogenous mill in real time through the control library so as to realize the process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the current operation parameters are obtained and updated to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters.
Preferably, the system further comprises a correction module for correcting the fuzzy C-means clustering algorithm, so that the fuzzy C-means clustering algorithm can implement multi-dimensional data processing and effectively distinguish multi-classification centers with multi-level relations.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, they are still within the scope of the present invention provided that they fall within the scope of the claims of the present invention and their equivalents.
Claims (7)
1. A self-learning control method applied to a semi-autogenous mill is characterized by comprising the following steps:
s1: acquiring a process parameter set and corresponding running state data of the semi-autogenous mill, carrying out normalization processing on the process parameter set, and combining the corresponding running state data to obtain a multidimensional data set;
s2: processing the multi-dimensional data set based on a fuzzy C-means clustering algorithm by combining a control strategy adopted by the running state of the semi-autogenous mill to obtain a multi-classification center of the multi-dimensional data set;
s3: optimally screening the multi-classification centers, removing redundancy of the multi-classification centers, and constructing a control library of the semi-autogenous mill;
s4: providing current operation parameters for the semi-autogenous mill in real time through the control library to realize process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the control library obtains the current operation parameters and updates the current operation parameters to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters;
in step S2, the fuzzy C-means clustering algorithm is modified to obtain a sample space x j In the form of data sets
Realizing extension, wherein l is the number of the parameter types of the process parameter set, so that the fuzzy C-means clustering algorithm can implement multi-dimensional data processing, and the multi-classification centers, namely clustering centers, in a multi-level relation are effectively distinguished by using a multi-dimensional data set
2. The self-learning control method applied to the semi-autogenous mill according to claim 1, wherein the step S4 further includes: and updating the control library, wherein the weight in the control library is configured and modified according to the operation result corresponding to the current operation state, so that the control library is updated.
3. The self-learning control method applied to the semi-autogenous mill according to claim 1, characterized in that in step S1, the normalization processing on the set of process parameters is specifically: converting the process parameter set into a dimensionless value of 0 to 1, the calculation formula is as follows,
wherein X' is a normalized value, X is data of the process parameter set, and X is max Is the maximum value, X, of the set of process parameters min Is the minimum value of the process parameter set.
4. The self-learning control method applied to the semi-autogenous mill according to claim 1, wherein in the step S2, the fuzzy C-means clustering algorithm has a calculation formula of
Wherein x is j Is the sample space, j = (1, 2, \8230;, N), w i As clustering center, i = (1, 2, \8230;, C), μ ji For the sample space x j For the cluster center w i The degree of membership of (a) is,
wherein, i =1,2, \8230:; j =1,2, \8230;, N; and is
m is a fuzzy index, and m belongs to (1, ∞);
5. the self-learning control method applied to a semi-autogenous mill according to claim 1, wherein in the step S4, the current operating parameters include: the feed amount, feed water amount and heavy plate frequency of the semi-autogenous mill.
6. A self-learning control apparatus for a semi-autogenous mill, configured with the self-learning control method for a semi-autogenous mill according to any one of claims 1 to 5, comprising:
the data extraction module is used for acquiring a process parameter set and corresponding operating state data of the semi-autogenous mill, performing normalization processing on the process parameter set, and combining the corresponding operating state data to obtain a multi-dimensional data set;
the data processing module is used for processing the multi-dimensional data set by combining a control strategy adopted by the running state of the semi-autogenous mill based on a fuzzy C-mean clustering algorithm to obtain a multi-classification center of the multi-dimensional data set;
the data optimization module is used for carrying out optimization screening on the multi-classification centers, removing redundancy of the multi-classification centers and constructing a control base of the semi-autogenous mill;
and the process control module is used for providing the current operation parameters for the semi-autogenous mill in real time through the control library so as to realize the process parameter control of the semi-autogenous mill, wherein the current operation state of the semi-autogenous mill is obtained in real time, the current operation state is matched with the control library, the current operation parameters are obtained and updated to the semi-autogenous mill, and the process parameters of the semi-autogenous mill are controlled in real time through updating the current operation parameters.
7. The self-learning control device applied to the semi-autogenous mill according to claim 6, further comprising a modification module for modifying the fuzzy C-means clustering algorithm so that the fuzzy C-means clustering algorithm can implement multi-dimensional data processing to effectively distinguish the multi-classification centers in a multi-level relationship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011346547.9A CN112327608B (en) | 2020-11-26 | 2020-11-26 | Self-learning control method and device applied to semi-autogenous mill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011346547.9A CN112327608B (en) | 2020-11-26 | 2020-11-26 | Self-learning control method and device applied to semi-autogenous mill |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112327608A CN112327608A (en) | 2021-02-05 |
| CN112327608B true CN112327608B (en) | 2023-01-20 |
Family
ID=74308985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011346547.9A Active CN112327608B (en) | 2020-11-26 | 2020-11-26 | Self-learning control method and device applied to semi-autogenous mill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327608B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113762386B (en) * | 2021-09-08 | 2023-04-18 | 矿冶科技集团有限公司 | Matching method and device for ore grinding control parameters and electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485326A (en) * | 2016-10-17 | 2017-03-08 | 鞍钢集团矿业有限公司 | A kind of hardness detection method in ore reduction production process |
-
2020
- 2020-11-26 CN CN202011346547.9A patent/CN112327608B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485326A (en) * | 2016-10-17 | 2017-03-08 | 鞍钢集团矿业有限公司 | A kind of hardness detection method in ore reduction production process |
Non-Patent Citations (2)
| Title |
|---|
| 基于子集融合与规则简约的磨矿过程模糊建模;乔峥等;《控制理论与应用》;20150630;第32卷(第6期);第770-777页 * |
| 基于子集融合与规则约简的磨矿过程模糊建模;乔峥;《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅰ辑》;20160315;第B021-188页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112327608A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101158693B (en) | Bulk production process malfunction detection method based on multiple nucleus independent elements analysis | |
| CN112327608B (en) | Self-learning control method and device applied to semi-autogenous mill | |
| JP2021534055A (en) | How to determine the total alumina production index based on a multi-scale deep convolutional neural network | |
| CN109847916B (en) | Energy-saving optimization method of cement raw material vertical mill system | |
| CN102489450A (en) | Intelligent separation method and system | |
| CN107247412B (en) | Fuzzy control method for powder selecting system of cement mill | |
| CN108380380A (en) | Product dry type fine crushing sorts Iron concentrate technique | |
| CN103617456A (en) | Operating index optimization method in beneficiation process | |
| Liu et al. | Reinforcement learning based decision making of operational indices in process industry under changing environment | |
| CN114506933A (en) | Sewage multi-stage treatment system | |
| CN112699926A (en) | Method for identifying saturated grinding abnormity of cement raw material vertical mill based on artificial intelligence technology | |
| CN2865852Y (en) | Rice refining machine Set | |
| CN110302888A (en) | Cement mill Optimization of Energy Saving system | |
| CN113093674A (en) | Cement production comprehensive unit consumption automatic analysis optimization system based on big data analysis | |
| Sun et al. | The application of nonstandard support vector machine in tool condition monitoring system | |
| CN202516782U (en) | Intelligent sorting system | |
| Giridhar et al. | Model based constant feed fed-batch L-Sorbose production process for improvement in L-Sorbose productivity | |
| CN110221587A (en) | A kind of ore properties and process matching countermeasure | |
| CN113762386B (en) | Matching method and device for ore grinding control parameters and electronic equipment | |
| CN112699896A (en) | Crop disease fine-grained identification method based on MDFC-ResNet neural network | |
| Wang et al. | Multi-objective optimization for an industrial grinding and classification process based on PBM and RSM | |
| Chai et al. | Multi-objective hybrid intelligent optimization of operational indices for industrial processes and application | |
| Wang et al. | Optimization of SAG Control Rule Based on Clustering Learning Algorithm | |
| CN106779216A (en) | A kind of mining production automatic arrangement program optimization method under unsaturated order | |
| CN111125082A (en) | Cement process parameter data analysis method based on association rule mining |
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 |