CN110967974B - Coal flow balance self-adaptive control method based on rough set - Google Patents
Coal flow balance self-adaptive control method based on rough set Download PDFInfo
- Publication number
- CN110967974B CN110967974B CN201911220887.4A CN201911220887A CN110967974B CN 110967974 B CN110967974 B CN 110967974B CN 201911220887 A CN201911220887 A CN 201911220887A CN 110967974 B CN110967974 B CN 110967974B
- Authority
- CN
- China
- Prior art keywords
- attribute
- coal flow
- coal
- flow balance
- 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
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Abstract
The invention discloses a coal flow balance self-adaptive control method based on a rough set, which is characterized in that coal flow state information data is acquired according to set time, the coal flow state information is used as the input of a control system, the coal flow state information is subjected to data preprocessing firstly, then the condition attribute and the decision attribute which influence the coal flow balance self-adaptive control are analyzed and determined, the condition attribute is subjected to attribute reduction by using a rough set theory method, the self-adaptive speed control rule of a coal mining machine and a scraper conveyor is extracted from a reduced simplest attribute set, and finally the rule is extracted by using a random forest algorithm to form an effective coal flow balance self-adaptive control rule base so as to realize the coal flow balance self-adaptive control.
Description
Technical Field
The invention relates to a coal flow balance self-adaptive control method based on a rough set.
Background
At present, phenomena such as large load fluctuation, overload shutdown, long-time light-load operation and the like of the scraper conveyor commonly exist in the fully mechanized coal mining production process, the service life of equipment is influenced, and the coal yield is also seriously influenced. In order to avoid the phenomenon and ensure the continuous operation of the scraper conveyor, research on a self-adaptive speed regulation method between the coal mining machine and the scraper conveyor is urgently needed.
A plurality of variable factors in the coal flow balance self-adaptive control are mutually associated and mutually influence, for example, the traction current of a coal mining machine is closely related to information such as working condition information, coal rock characteristics and the like; the frequency of a frequency converter of the scraper conveyor is coupled with the coal mining amount information; the frequency of the frequency converter of the cutting motor of the coal mining machine is coupled with the coal rock characteristics and the cutting depth information of the coal mining machine. In addition, the position monitoring transmitter of the coal mining machine is arranged on the coal mining machine, but the position information receiver is arranged on the hydraulic support, so that the obtained position information of the coal mining machine is the No. X support, is not the accurate position information of the coal mining machine and is a fuzzy quantity; the operation of the coal mining machine along the fully mechanized mining face is a reciprocating process, the operation state is influenced by various information such as the coal flow state, the load of a scraper conveyor, the cutting depth of the coal mining machine and the feed amount of each time, and the operation state of the coal mining machine is changed continuously, is complex nonlinear motion and has uncertainty. Under the traditional working condition, the cooperative control of the coal mining machine and the scraper conveyor is realized by experienced workers.
Disclosure of Invention
In order to convert the control experience of experienced coal mining workers into a control method and a control model, the cooperative operation of the coal mining machine and the scraper conveyor can be realized in a self-adaptive manner. Considering the uncertainty, the ambiguity and the nonlinearity of the fully mechanized mining face work, the invention aims to provide a coal flow balance self-adaptive control method based on a rough set to extract the control knowledge of experienced coal miners, and extract a coal flow balance self-adaptive control rule by using attribute reduction and a random forest algorithm, thereby obtaining a concise and accurate coal flow balance self-adaptive control method.
The technical scheme of the invention is as follows: a coal flow balance self-adaptive control method based on a rough set is characterized in that coal flow state information data acquisition is carried out according to set time, the coal flow state information is used as input of a control system, data preprocessing is carried out on the coal flow state information, then condition attributes and decision attributes influencing coal flow balance self-adaptive control are analyzed and determined, attribute reduction is carried out on the condition attributes by using a rough set theory method, self-adaptive speed regulation control rules of a coal mining machine and a scraper conveyor are extracted from a reduced simplest attribute set, and finally rules are extracted by using a random forest algorithm to form an effective coal flow balance self-adaptive control rule base so as to realize coal flow balance self-adaptive control.
Determining 8 factors causing the change of the running states of the coal mining machine and the scraper machine as condition attributes, wherein the condition attributes comprise a discrete condition attribute and a continuous condition attribute; the purpose that the coal flow balance self-adaptive control system needs to achieve is determined as a decision attribute, and the number of the decision attributes is 4.
And performing attribute reduction on the 4 decision attributes by adopting an attribute-core-based minimum attribute reduction algorithm, analyzing the importance degree of the 8 condition attributes to each decision attribute, and removing unimportant condition attributes to obtain a minimum attribute set corresponding to each decision attribute.
And extracting self-adaptive speed regulation control rules of the coal mining machine and the scraper conveyor from the reduced simplest attribute set by adopting a random forest algorithm, taking the reduced simplest attribute set as a training set, wherein each group of data after attribute reduction is a decision rule, the same decision rule corresponds to different condition attributes, integrating the condition attributes to form a unique combination as a result set, and constructing the coal flow balance self-adaptive control rules.
In the control rules, each decision rule has a corresponding unique condition attribute set, when a group of data is input, the speed and the operation of the coal mining machine and the scraper conveyor can be adjusted according to the corresponding decision rule by only judging which condition attribute set belongs to the group of data under which decision rule, so that the self-adaptive speed regulation of the coal mining machine and the scraper conveyor is realized.
The coal flow state information comprises coal mining machine running state information and scraper conveyor state information.
The data preprocessing comprises a cleaning process and a discretization process based on Boolean logic, and the cleaning process comprises two aspects of data cleaning and data normalization.
Discretizing each continuous condition attribute by adopting a discretization method based on Boolean logic to obtain a breakpoint set of each continuous condition attribute, and classifying input data into an interval represented by a breakpoint with the closest distance when the input data is closest to the breakpoint, so that each continuous condition attribute is divided into a limited interval according to actual working conditions.
And normalizing the variable information of the coal flow balance self-adaptive control system by adopting a Z-score standardization method.
The coal mining machine running state information refers to information such as frequency of a traction motor frequency converter of a coal mining machine, frequency of a cutting motor frequency converter of the coal mining machine, running direction of the coal mining machine, position of the coal mining machine and the like, and is closely related to information such as geological state, coal rock characteristics, cutting depth of the coal mining machine, feed quantity, operation width of a fully mechanized mining face and the like during working, and the information is a source of coal flow of the fully mechanized mining face and directly contains coal mining quantity information.
The state information of the scraper conveyor comprises information such as scraper current, frequency of a scraper frequency converter, coal flow state of scraper transportation, load of the scraper conveyor and the like.
The coal flow balance self-adaptive control is to cooperatively match the coal mining quantity of the coal mining machine with the conveying capacity of the scraper conveyor and find out the corresponding control rule between the coal mining machine and the scraper conveyor, so that the coal mining machine and the scraper conveyor can perform self-adaptive speed regulation according to the control rule generated by the rough set theory.
Drawings
FIG. 1 is a flow diagram of a rough set based coal flow balance adaptive control method.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings. As shown in FIG. 1, the rough set-based coal flow balance adaptive control method specifically comprises the following steps.
The method comprises the following steps: data acquisition
In the actual coal mining process, factors influencing the coal flow balance adaptive speed regulation are very many, for example, the frequency of a scraper frequency converter, the current of a scraper conveyor, the coal flow state of a scraper conveyor, the frequency of a traction motor frequency converter of a coal mining machine, the frequency of a cutting motor frequency converter of a coal mining machine, the running direction of the coal mining machine, the position of the coal mining machine, the load of the scraper conveyor, the cutting depth of the coal mining machine, the working width of a fully mechanized mining face, the coal rock state and the like, and the data can be acquired through equipment such as a current sensor, a frequency sensor, a position detection device and the like. Taking partial data as an example, a coal flow balance adaptive control method is researched, and the data are explained as follows according to the theoretical requirement of a rough set:
TABLE 1 coal flow balance adaptive control System State information
Determination of conditional and decision attributes: the condition attribute of the coal flow balance self-adaptive control system is a factor which can cause the change of the running states of the coal mining machine and the scraper, and the decision attribute is the purpose which needs to be achieved by the coal flow balance self-adaptive control system, namely the self-adaptive speed regulation of the coal mining machine and the scraper is realized.
Step two: data pre-processing
(1) Data normalization processing
The variable information of the coal flow balance self-adaptive control system is normalized by adopting a Z-score standardization method, and the data of different dimensions, different magnitudes and different formats, such as the current of a scraper conveyor, the coal flow state of the scraper conveyor, the running direction of a coal mining machine, the position of the coal mining machine, the frequency of a frequency converter of the scraper conveyor, the frequency of a frequency converter of a traction motor of the coal mining machine, the frequency of a frequency converter of a cutting motor of the coal mining machine, and the like, are converted into a unified expression form, as shown in a formula 2-1:
in the above equation, μ is the mean of all sample data, and σ is the standard deviation of all sample data.
(2) Discretization processing
Since the data type required by the rough set theory method is discrete, it is necessary to discretize continuous data in the collected data before control rule extraction. The method is characterized in that original data of the frequency converter frequency of the traction motor of the coal mining machine, the frequency converter of the scraper conveyor, the current of the scraper conveyor and the like in the table 1 are converted into discrete values required for extracting the coal flow balance adaptive control rule, and the specific idea is that each continuous condition attribute is divided into a limited interval according to actual working conditions, and then the position of a breakpoint is determined from each interval, so that each breakpoint represents one interval. The condition attribute is discretized by adopting a discretization method based on Boolean logic. And a breakpoint set of each condition attribute can be obtained through a Boolean logic discretization algorithm, and the data is classified into an interval represented by the breakpoint closest to the input data and the breakpoint closest to the input data.
Step three: attribute reduction
And performing attribute reduction on the 4 decision attributes by adopting an attribute-core-based minimum attribute reduction algorithm. By the attribute-core-based minimum attribute reduction algorithm, the dependence degree of each decision attribute relative to 8 conditional attributes can be analyzed, and the conditional attributes with low dependence degree are removed on the premise of not changing the decision attributes, so that a minimum attribute set relative to each decision attribute is obtained.
Step four: adaptive speed regulation rule extraction for coal mining machine and scraper
After the attribute reduction is performed in the third step, the adaptive speed regulation control rule of the coal mining machine and the scraper conveyor needs to be extracted from the reduced simplest attribute set. The rules are extracted using a random forest algorithm, which was proposed by Leo Breiman in 2001.
And (3) taking the reduced simplest attribute set as a training set, wherein each group of data after attribute reduction is a decision rule, the same decision rule corresponds to different condition attributes, and the condition attributes are integrated to form a unique combination as a result set to construct the coal flow balance self-adaptive control rule.
As shown in table 1, 4 predicted actions such as frequency change of a scraper conveyor frequency converter, frequency change of a shearer traction motor frequency converter, frequency change of a shearer cutting motor frequency converter, and running direction of a shearer are taken as decision attributes, and the possibility of each predicted action is 3, that is, the frequency of the scraper conveyor frequency converter, the frequency of the shearer traction motor frequency converter, and the frequency of the shearer cutting motor frequency converter are increased, decreased or maintained, and the running direction of the shearer is forward, backward or maintained.
Each decision rule has a corresponding unique condition attribute set, when a group of data is input, the speed and the operation of the coal mining machine and the scraper can be adjusted according to the corresponding decision rule by only judging the condition attribute set under which decision rule the group of data belongs to, so that the self-adaptive speed regulation of the coal mining machine and the scraper is realized.
The coal flow balance self-adaptive control system based on the rough set is a dynamically changing system, the coal flow state information data is acquired according to set time, the input coal flow state information is changed all the time according to the time, then a control rule is generated according to the four steps to dynamically control a scraper and a coal mining machine in real time, and the running direction of the coal mining machine is determined to be forward, backward or the original position is kept; and determining that the frequency of the scraper conveyor frequency converter, the frequency of the coal cutter traction motor frequency converter and the frequency of the coal cutter cutting motor frequency converter are increased or decreased or the original frequency is maintained unchanged. In order to ensure that the change of the frequency does not cause the oscillation of the coal mining machine and the scraper, the change of the frequency can give a fixed value according to the actual working condition, so that the coal mining machine and the scraper can stably run.
Claims (3)
1. The coal flow balance self-adaptive control method based on the rough set is characterized in that coal flow state information data are acquired according to set time, the coal flow state information is used as input of a control system, the coal flow state information is subjected to data preprocessing firstly, then condition attributes and decision attributes influencing the coal flow balance self-adaptive control are analyzed and determined, the condition attributes are subjected to attribute reduction by using the rough set theory method, self-adaptive speed regulation control rules of a coal mining machine and a scraper conveyor are extracted from the reduced most-reduced attribute set, and finally, the rules are extracted by using a random forest algorithm to form an effective coal flow balance self-adaptive control rule base so as to realize the coal flow balance self-adaptive control;
determining factors causing the change of the running states of the coal mining machine and the scraper conveyor as condition attributes, including discrete condition attributes and continuous condition attributes; determining the purpose to be achieved by the coal flow balance self-adaptive control system as a decision attribute; attribute reduction is carried out on the decision attributes by adopting an attribute core-based minimum attribute reduction algorithm, the importance degree of a plurality of condition attributes to each decision attribute is analyzed, unimportant condition attributes are removed, and a minimum attribute set corresponding to each decision attribute is obtained; extracting self-adaptive speed regulation control rules of the coal mining machine and the scraper conveyor from the reduced simplest attribute set by adopting a random forest algorithm, taking the reduced simplest attribute set as a training set, wherein each group of data after attribute reduction is a decision rule, the same decision rule corresponds to different condition attributes, and the condition attributes are integrated to form a unique combination as a result set to construct a coal flow balance self-adaptive control rule; in the control rules, each decision rule has a corresponding unique condition attribute set, when a group of data is input, the speed and the operation of the coal mining machine and the scraper conveyor can be adjusted according to the corresponding decision rule only by judging which condition attribute set belongs to the group of data under which decision rule, so that the self-adaptive speed regulation of the coal mining machine and the scraper conveyor is realized;
the data preprocessing comprises cleaning processing and discretization processing based on Boolean logic, and the cleaning processing comprises two aspects of data cleaning and data normalization; the discretization method based on the Boolean logic is specifically that discretization is carried out on each continuous condition attribute to obtain a breakpoint set of each continuous condition attribute, the distance between input data and a breakpoint is the closest, the data is classified into an interval represented by the breakpoint with the closest distance, and therefore each continuous condition attribute is divided into a limited interval according to actual working conditions.
2. The adaptive rough set-based coal flow balance control method of claim 1, wherein the coal flow state information comprises shearer operating state information and scraper conveyor state information.
3. The rough set based coal flow balance adaptive control method according to claim 1, wherein variable information of the coal flow balance adaptive control system is normalized by a Z-score normalization method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911220887.4A CN110967974B (en) | 2019-12-03 | 2019-12-03 | Coal flow balance self-adaptive control method based on rough set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911220887.4A CN110967974B (en) | 2019-12-03 | 2019-12-03 | Coal flow balance self-adaptive control method based on rough set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110967974A CN110967974A (en) | 2020-04-07 |
| CN110967974B true CN110967974B (en) | 2022-05-17 |
Family
ID=70032706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911220887.4A Active CN110967974B (en) | 2019-12-03 | 2019-12-03 | Coal flow balance self-adaptive control method based on rough set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110967974B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897376A (en) * | 2020-06-10 | 2020-11-06 | 常州联力自动化科技有限公司 | Automatic speed regulation method for conveyor and coal mining machine without coal flow sensor |
| CN114215520B (en) * | 2021-10-25 | 2023-10-24 | 北京天玛智控科技股份有限公司 | Method and device for cooperatively controlling equipment in coal mine working face |
| CN113844861B (en) * | 2021-10-27 | 2023-04-07 | 陕西旬邑青岗坪矿业有限公司 | Automatic speed regulating method of belt and coal mining machine based on coal quantity detection |
| CN117272031B (en) * | 2023-11-21 | 2024-02-06 | 唐山智诚电气（集团）有限公司 | Multi-source-based coal flow balance self-adaptive control method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204453674U (en) * | 2015-01-12 | 2015-07-08 | 陕西远卓信息系统技术有限公司 | The many belt fortune coal flows of underground coal mine and belt speed comprehensive matching control system |
| CN204702158U (en) * | 2015-05-14 | 2015-10-14 | 中煤张家口煤矿机械有限责任公司 | Fully-mechanized mining working coal stream Monitoring and control system |
| CN109358582A (en) * | 2018-10-22 | 2019-02-19 | 西安科技大学 | The more equipment collaboration job control methods of high-seam working face based on big data |
| CN109871894A (en) * | 2019-02-20 | 2019-06-11 | 哈尔滨工程大学 | A kind of Method of Data Discretization of combination forest optimization and rough set |
-
2019
- 2019-12-03 CN CN201911220887.4A patent/CN110967974B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204453674U (en) * | 2015-01-12 | 2015-07-08 | 陕西远卓信息系统技术有限公司 | The many belt fortune coal flows of underground coal mine and belt speed comprehensive matching control system |
| CN204702158U (en) * | 2015-05-14 | 2015-10-14 | 中煤张家口煤矿机械有限责任公司 | Fully-mechanized mining working coal stream Monitoring and control system |
| CN109358582A (en) * | 2018-10-22 | 2019-02-19 | 西安科技大学 | The more equipment collaboration job control methods of high-seam working face based on big data |
| CN109871894A (en) * | 2019-02-20 | 2019-06-11 | 哈尔滨工程大学 | A kind of Method of Data Discretization of combination forest optimization and rough set |
Non-Patent Citations (2)
| Title |
|---|
| Rough set methods in feature selection and recognition;Roman W.等;《Pattern Recognition Letters》;20021015;第24卷(第6期);第833-849页 * |
| 综采工作面三机虚拟协同关键技术研究;谢嘉成 等;《工程设计学报》;20180228;第25卷(第1期);第85-93页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110967974A (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110967974B (en) | Coal flow balance self-adaptive control method based on rough set | |
| US11307327B2 (en) | Method and system for online monitoring and optimization of mining and mineral processing operations | |
| CN109918822B (en) | Shield tunneling parameter deviation calculation method and system based on random forest regression | |
| CN112613646A (en) | Equipment state prediction method and system based on multi-dimensional data fusion | |
| CN112182973B (en) | TBM (Tunnel boring machine) operation parameter optimization method considering cutter vibration and rock slag geometric information | |
| CN209485669U (en) | A kind of hobboing cutter information monitoring device | |
| Yan et al. | A hybrid method for on-line performance assessment and life prediction in drilling operations | |
| CN110119551A (en) | Shield machine cutter abrasion degeneration linked character analysis method based on machine learning | |
| CN111958321B (en) | Numerical control machine tool cutter wear degree identification method based on deep neural network | |
| CN116335925B (en) | Data enhancement-based intelligent regulation and control system for underground coal mine emulsification pump station | |
| CN116187725B (en) | Forging equipment management system for forging automatic line | |
| Stefaniak et al. | Multidimensional signal analysis for technical condition, operation and performance understanding of heavy duty mining machines | |
| CN115628930A (en) | Method for predicting underground cutting working condition of heading machine based on RBF neural network | |
| Sikora et al. | Improving prediction models applied in systems monitoring natural hazards and machinery | |
| CN104790948A (en) | Control method for automatic vertical steering of coal winning machine drum | |
| CN108956783A (en) | A kind of grinding sound wheel loading condition detection method based on HDP-HSMM | |
| CN114722924A (en) | Pressure prediction method and device, storage medium and terminal | |
| CN109711642A (en) | Desulphurization system running optimizatin method and system based on big data | |
| CN107506831A (en) | Blasting parameters determination method and system | |
| CN114294045B (en) | Dust removing method and dust remover for mining tunneling working face | |
| CN113158562A (en) | TBM rock machine mapping construction method and system based on physical constraint and data mining | |
| CN105653615A (en) | Big data based computer data mining discovery method | |
| CN116933409B (en) | Digital twinning-oriented coal mine underground equipment model compression design method | |
| Sharma | Fleet imbalance analysis in large open pit coal mines in India | |
| Esmael et al. | Automated system for drilling operations classification using statistical features |
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 |