CN112916432B - Intelligent magnetic ore sorting method and equipment - Google Patents
Intelligent magnetic ore sorting method and equipment Download PDFInfo
- Publication number
- CN112916432B CN112916432B CN202110314908.XA CN202110314908A CN112916432B CN 112916432 B CN112916432 B CN 112916432B CN 202110314908 A CN202110314908 A CN 202110314908A CN 112916432 B CN112916432 B CN 112916432B
- Authority
- CN
- China
- Prior art keywords
- magnetite
- sorted
- ore
- magnetic
- iron ore
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 116
- SZVJSHCCFOBDDC-UHFFFAOYSA-N iron(II,III) oxide Inorganic materials O=[Fe]O[Fe]O[Fe]=O SZVJSHCCFOBDDC-UHFFFAOYSA-N 0.000 claims abstract description 90
- 229910052742 iron Inorganic materials 0.000 claims abstract description 58
- 238000000926 separation method Methods 0.000 claims abstract description 36
- 238000012360 testing method Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000013136 deep learning model Methods 0.000 claims abstract description 15
- 230000009466 transformation Effects 0.000 claims abstract description 8
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 7
- 239000011707 mineral Substances 0.000 claims abstract description 7
- 239000002245 particle Substances 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 17
- 238000005192 partition Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000000429 assembly Methods 0.000 claims description 8
- 230000000712 assembly Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000035699 permeability Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 3
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 239000002699 waste material Substances 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003437 trachea Anatomy 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/344—Sorting according to other particular properties according to electric or electromagnetic properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/20—Recycling
Landscapes
- Sorting Of Articles (AREA)
Abstract
An intelligent magnetic iron ore sorting method and equipment, wherein the method comprises the following steps: determining the lowest grade and the particle size range of the magnetite ore to be sorted; determining the magnetic field intensity and the position of a magnetic source which can enable the lowest-grade magnetic iron ore in the magnetic iron ore to be sorted to generate a detectable signal; carrying out signal acquisition on ores randomly selected from magnetite ores to be sorted to obtain signal acquisition data, and preprocessing the signal acquisition data to obtain preprocessed data; performing dimension transformation on the preprocessed data to generate corresponding ore samples, and dividing the ore samples into a training set and a testing set; training the training set, and testing the model through the testing set to judge whether the testing result meets the current mineral separation standard; if yes, the deep learning model is successfully trained, and the deep learning model and the data acquisition system are embedded into automatic sorting equipment to sort the magnetic iron ore. The invention enlarges the selection grade of the magnetite ore to be selected and improves the utilization rate of the ore.
Description
Technical Field
The invention relates to the technical field of intelligent ore sorting, in particular to an intelligent magnetite ore sorting method and equipment.
Background
The iron ore resources in China are rich, but the rich ore is less, the lean ore and the refractory ore are more, and foreign iron ore needs to be imported continuously to guarantee the domestic iron ore production, so that the dependence on foreign iron ore is too high, and the development of mineral separation enterprises in China is influenced. Therefore, domestic enterprises improve the comprehensive utilization rate of the iron ore by a mode of pre-selecting and discarding the waste, thereby reducing the waste of mineral resources and the mineral separation cost.
The waste pre-separation and discarding method specifically comprises the steps of separating magnetic ores of different grades in the same magnetic field by using different magnetic forces, so that the ore utilization rate is improved to a certain extent, and the economic benefits of enterprises are improved. However, due to the fact that iron ore resources in China are not natural and have the characteristics of 'poor, fine and miscellaneous' and the like, the adaptability of the waste pre-selecting and discarding method is not enough, and the problems of low comprehensive utilization rate, single product structure, high energy consumption, environmental pollution and the like of the iron ore resources in the development process still exist.
With the arrival of the intelligent era, most of industries have successfully entered intelligent roads, but the field of magnetic iron ore separation still stagnates at the aspect of utilizing force fields to carry out separation, so that the field of magnetic iron ore separation has important significance in advancing to intelligent gates.
Disclosure of Invention
Based on the above, the invention aims to provide an intelligent magnetic iron ore sorting method and equipment, which are convenient for automatically sorting magnetic iron ores to be sorted and improving the ore utilization rate.
On one hand, the invention provides an intelligent magnetic iron ore sorting method, which comprises the following steps:
step S11, determining the lowest grade and the particle size range of the magnetic iron ore to be sorted;
step S12, determining the magnetic field intensity and position of the magnetic source which can enable the lowest grade magnetic iron ore in the magnetic iron ore to be sorted to generate detectable signals;
step S13, acquiring signals of a plurality of ores randomly selected from magnetite ores to be sorted by using a data acquisition system to obtain signal acquisition data, and preprocessing the signal acquisition data to obtain preprocessed data;
step S14, performing dimension transformation on each preprocessed data to generate corresponding ore samples, and dividing the ore samples into a training set and a testing set;
step S15, training a training set by adopting a deep learning model, and testing the model by a test set to judge whether a test result meets the current mineral separation standard;
and step S16, if yes, successfully training the deep learning model, embedding the deep learning model and the data acquisition system into automatic sorting equipment, and sorting the magnetite through the automatic sorting equipment.
Further, the step S12 specifically includes:
step S121, establishing a magnetite model which corresponds to the lowest-grade magnetite and has uniformly distributed relative permeability to replace real ore in multi-physical-field simulation software;
step S122, applying magnetic sources with different magnetic field strengths to the magnetite ore model in a simulation environment, and determining the magnetic field strength and the position of a simulation magnetic source which enables the magnetite ore model to generate a detectable signal according to the granularity range of the magnetite ore model;
step S123, taking a permanent magnet as a magnetic source, and actually testing the lowest-grade magnetic iron ore in the magnetic iron ore to be sorted to determine the magnetic field intensity and the position of the actual magnetic source;
and step S124, analyzing and comparing the magnetic field intensity and the position of the analog magnetic source and the actual magnetic source to determine the magnetic field intensity and the position of the final magnetic source.
Further, the step S13 specifically includes:
s131, collecting the voltage value of each magnetite to be sorted to establish a relative reference line of each magnetite to be sorted
Wherein,
the difference value of the jth sampling point of the ith magnetite to be sorted and the reference line of the ith magnetite to be sorted is obtained,
the voltage value of the jth sampling point of the ith magnetite to be sorted is the voltage value of the jth sampling point of the ith magnetite to be sorted, and n is the number of sampling points of the ith magnetite to be sorted;
step S132, relative reference line of each magnetite to be sorted
Make absolute value change
Wherein,
is composed of
Absolute value of (d);
step S133, sequentially selecting voltage critical values of different sizes to make corresponding category labels for each absolute value magnetic iron ore to be sorted,
wherein L (Max (| Δ)i|)) is the category of the ith magnetite to be sorted, Max (| Delta)iI) is all sampling points of ith magnetite ore to be sorted
The maximum values a, b and c are respectively voltage critical values for classifying the magnetite to be classified;
step S134, establishing absolute reference lines of all magnetite ores to be sorted
Wherein Min (| Delta)all|)、Max(|Δall|) are respectively the minimum value and the maximum value of all sampling points of the ith magnetite ore to be sorted after absolute value conversion,
the value of the j sampling point of the ith magnetite to be sorted after the absolute reference line is established.
Further, in the step S15, the deep learning model includes one of a convolutional neural network model, a modified convolutional networked model, a cyclic neural network model, or a modified cyclic neural network model.
On the other hand, the invention also provides magnetic iron ore intelligent sorting equipment which adopts the magnetic iron ore intelligent sorting method to sort magnetic iron ores and comprises a primary conveying assembly, a multi-channel partition plate, a secondary separation conveying assembly and a multi-stage storage box which are sequentially arranged, wherein one end of the multi-channel partition plate is arranged at an outlet of the primary conveying assembly, and the other end of the multi-channel partition plate is arranged at an inlet of the secondary separation conveying assembly;
the top transmission surface of the secondary separation conveying assembly is provided with two groups of sensor assemblies, a support frame is arranged above the two groups of sensor assemblies in a crossing mode, the support frame is provided with a magnetic field generating assembly and a data collecting assembly, the two groups of sensor assemblies are respectively positioned on two sides of the support frame, a data collecting area is formed on the top transmission surface of the secondary separation conveying assembly, the magnetic field generating assembly is positioned above the data collecting area, and the data collecting assembly is positioned below the data collecting area;
the bottom of second grade partition conveying subassembly is equipped with the bottom plate, the side is equipped with central processing unit, the exit is equipped with selects separately the executive component, central processing unit respectively with select separately executive component, data acquisition subassembly, magnetic field generation subassembly and two sets of sensor assembly electric connection.
Further, the magnetic field generating assembly comprises a permanent magnet arranged on the top of the support frame, and the distance between the bottom of the permanent magnet and the top conveying surface of the secondary separation conveying assembly is larger than the granularity of magnetite ore to be sorted.
Furthermore, the data acquisition assembly comprises a hollow guide rod transversely arranged on the support frame, a plurality of Hall sensors arranged in the hollow guide rod, a signal isolator and a data acquisition card arranged on the bottom plate, and the Hall sensors are respectively and sequentially electrically connected with the central processing unit through the signal isolator, the data acquisition card.
Further, the number of the Hall sensors corresponds to the number of channels of the secondary separation conveying assembly and the number of channels of the multi-channel partition plate respectively, and the distance between the Hall sensors and the lower surface of the top transmission surface of the secondary separation conveying assembly is 1mm-2 mm.
Further, select separately the execute subassembly and be located the below of conveying subassembly is separated to the second grade, including locating the air supply system of cylinder and relay, side on the bottom plate is located the mounting panel of conveying subassembly exit below is separated to the second grade, and is located a plurality of nozzles on the mounting panel, each the nozzle passes through trachea and high speed solenoid valve and cylinder intercommunication, cylinder and air supply system intercommunication, every high speed solenoid valve pass through the relay with central processing unit electric connection, the quantity of nozzle with hall sensor's quantity corresponds.
Further, the sorting execution assembly is located above the two-stage separation conveying assembly and comprises a plurality of mechanical arms, and the number of the mechanical arms corresponds to the number of the Hall sensors.
Compared with the prior art, the technical scheme of the invention has the following advantages:
1. the selection grade of the magnetite ore to be selected is enlarged, and the ore utilization rate is improved;
2. the magnetite ores to be sorted with different iron contents can be classified in real time, so that the subsequent process of the sorted magnetite ores can be conveniently carried out, and the ore dressing cost is reduced;
3. the modularization degree is higher, easily imbeds automatic sorting facilities, has improved intelligent degree.
Drawings
Fig. 1 is a schematic flow chart of an intelligent magnetic iron ore sorting method according to an embodiment of the present invention;
FIG. 2 is a signal diagram of four types of magnetite after an absolute reference line has been established in accordance with one embodiment of the present invention;
FIG. 3 is a diagram of dimension transformation in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a loss curve during training using a convolutional neural network model according to an embodiment of the present invention;
FIG. 5 is a graph of a confusion matrix during a test using a convolutional neural network model according to an embodiment of the present invention;
FIG. 6 is a schematic structural view of an intelligent magnetic iron ore sorting apparatus according to an embodiment of the present invention;
FIG. 7 is a schematic view of the installation of a Hall sensor in a hollow guide rod according to an embodiment of the invention;
fig. 8 is a schematic view of the installation of the sorting actuating element on the base plate according to an embodiment of the present invention.
Description of the main element symbols:
| |
10 | |
11 |
| Two-stage separated |
12 | Multi-stage |
13 |
| |
14 | |
15 |
| Magnetic |
16 | |
17 |
| |
171 | |
172 |
| |
173 | |
174 |
| |
18 | |
19 |
| |
20 | |
201 |
| |
202 | |
21 |
| |
211 | Relay with a |
212 |
| |
213 | |
214 |
| Nozzle with a |
215 | High-speed |
216 |
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are presented in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, an embodiment of the present invention provides an intelligent magnetic iron ore sorting method, including the following steps:
step S11, determining the lowest grade and the particle size range of the magnetite to be sorted according to the magnetite selected by the beneficiation enterprises;
step S12, determining the magnetic field intensity and position of the magnetic source which can make the lowest grade magnetic iron ore in the magnetic iron ore to be sorted generate detectable signals through off-line experiments;
in the present invention, step S12 specifically includes:
step S121, establishing a magnetite model which corresponds to the lowest-grade magnetite and has uniformly distributed relative permeability to replace real ore in multi-physical-field simulation software;
step S122, applying magnetic sources with different magnetic field strengths to the magnetite ore model in a simulation environment, and determining the magnetic field strength and the position of a simulation magnetic source which enables the magnetite ore model to generate a detectable signal according to the granularity range of the magnetite ore model;
step S123, taking a permanent magnet as a magnetic source, and actually testing the lowest-grade magnetic iron ore in the magnetic iron ore to be sorted to determine the magnetic field intensity and the position of the actual magnetic source;
and step S124, analyzing and comparing the magnetic field intensity and the position of the analog magnetic source and the actual magnetic source to determine the magnetic field intensity and the position of the final magnetic source.
Step S13, acquiring signals of a plurality of ores randomly selected from magnetite ores to be sorted by using a data acquisition system to obtain signal acquisition data, and preprocessing the signal acquisition data to obtain preprocessed data;
in the present invention, step S13 specifically includes:
s131, collecting the voltage value of each magnetite to be sorted to establish a relative reference line of each magnetite to be sorted
Wherein,
the difference value of the jth sampling point of the ith magnetite to be sorted and the reference line of the ith magnetite to be sorted is obtained,
the voltage value of the jth sampling point of the ith magnetite to be sorted is the voltage value of the jth sampling point of the ith magnetite to be sorted, and n is the number of sampling points of the ith magnetite to be sorted;
step S132, relative reference line of each magnetite to be sorted
Make absolute value change
Wherein,
is composed of
Absolute value of (d);
step S133, sequentially selecting voltage critical values of different sizes to make corresponding category labels for each absolute value magnetic iron ore to be sorted,
wherein L (Max (| Δ)i|)) is the category of the ith magnetite to be sorted, Max (| Delta)i|) is all sampling points of ith magnetite ore to be sorted
The maximum values a, b and c are respectively voltage critical values for classifying the magnetite to be classified;
step S134, establishing absolute reference lines of all magnetite ores to be sorted
Wherein Min (| Delta)all|)、Max(|Δall|) are respectively the minimum value and the maximum value of all sampling points of the ith magnetite to be sorted after absolute value conversion,
the value of the j sampling point of the ith magnetic iron ore to be sorted after the absolute reference line is established.
Referring to fig. 2, after establishing the absolute reference lines, the signal intensities of four types of magnetite to be sorted show inconsistency, where 1 is waste ore in the magnetite to be sorted, 2 is weak ore in the magnetite to be sorted, 3 is medium-strong ore in the magnetite to be sorted, and 4 is strong ore in the magnetite to be sorted.
Step S14, performing dimension transformation on each preprocessed data to generate corresponding ore samples, and dividing the ore samples into a training set and a testing set;
referring to fig. 3, it should be noted that the signals initially acquired by the data acquisition system in the present invention are one-dimensional signals, and since the acquired signals are processed by using the convolutional neural network in the subsequent steps and the convolutional neural network is good at processing two-dimensional signals, in order to fully exert the advantages of the convolutional neural network, dimension transformation needs to be performed on the preprocessed data to convert the one-dimensional signals into two-dimensional signals. Specifically, the method for performing the dimension transformation on each preprocessed data includes:
N＝i×j
wherein N represents all sampling points of a sample, i and j represent rows and columns, respectively, and the dimension transformation method is shown in fig. 3.
Specifically, the dimension transformation is performed on each preprocessed data to generate corresponding ore samples, for example, 1200 samples are manufactured in the present invention, and the sample set is divided into a training set and a testing set according to a ratio of 7:3, where a sample distribution table is shown in table 1.
TABLE 1 sample distribution Table
Step S15, training a training set by adopting a deep learning model, and testing the model by a test set to judge whether a test result meets the current mineral separation standard;
in step S15, the deep learning model includes one of a convolutional neural network model, a modified convolutional neural network model, a cyclic neural network model, or a modified cyclic neural network model.
Referring to fig. 4 and 5, in particular, the convolutional neural network model is adopted to train the training set, and the trained convolutional neural network model is tested through the test set. When the values corresponding to a, b and c are respectively 2mV, 4mV and 8mV, the training result of the training set by the convolutional neural network model is shown in figure 4, the loss curve gradually tends to 0, which indicates that the training result of the model is better, and the test result of the trained convolutional neural network model by the test set is shown in figure 5, so that the model has better recognition effect on weak ores, medium-strong ores and strong ores, the recognition accuracy is over 85%, especially for the recognition of the weak ores, only 2 times of error prediction are performed, the recognition accuracy is as high as 97.78%, but the recognition effect on the waste ores is poor, 21 times of error prediction are performed, and the recognition accuracy is only 76.67%.
And step S16, if yes, successfully training the deep learning model, embedding the deep learning model and the data acquisition system into automatic sorting equipment, and sorting the magnetite through the automatic sorting equipment.
Referring to fig. 6, on the other hand, the present invention further provides an intelligent magnetic iron ore sorting apparatus, which uses the above intelligent magnetic iron ore sorting method to perform magnetic iron ore sorting, and includes a first-stage conveying assembly 10, a multi-channel partition plate 11, a second-stage separation conveying assembly 12, and a multi-stage storage box 13, which are sequentially disposed, where one end of the multi-channel partition plate 11 is installed at an outlet of the first-stage conveying assembly 10, and the other end is installed at an inlet of the second-stage separation conveying assembly 12;
the top transmission surface of the secondary separation conveying component 12 is provided with two groups of sensor components 14, a support frame 15 is spanned above the two groups of sensor components, the support frame 15 is provided with a magnetic field generating component 16 and a data acquisition component 17, the two groups of sensor components 14 are respectively positioned at two sides of the support frame 15, a data acquisition area 18 is formed on the top transmission surface of the secondary separation conveying component 12, the magnetic field generating component 16 is positioned above the data acquisition area 18, and the data acquisition component 17 is positioned below the data acquisition area 18;
the bottom of the second-stage separating and conveying assembly 12 is provided with a bottom plate 19, the side edge of the second-stage separating and conveying assembly is provided with a central processing unit 20, the outlet of the second-stage separating and conveying assembly is provided with a separating and executing assembly 21, and the central processing unit 20 is electrically connected with the separating and executing assembly 21, the data acquisition assembly 17, the magnetic field generating assembly 16 and the two groups of sensor assemblies 15 respectively.
In the invention, the magnetite ore to be sorted passes through the multi-channel partition plate 12 from the primary conveying assembly 10 and sequentially enters the secondary partition conveying assembly 12; when the magnetic ore to be sorted passes below the data acquisition area 18, the magnetic field generation assembly 16 generates a detectable signal for the magnetic ore to be sorted, the data acquisition assembly 17 acquires the detectable signal, the central processing unit 20 performs calculation and analysis on the acquired signal and sends a sorting instruction according to an analysis result, and finally the sorting execution assembly 21 executes a sorting command to sort the magnetic ore to be sorted into the multistage storage box 13.
Specifically, in a preferred embodiment of the present invention, the primary conveying assembly 10 uses a conveyor belt to transport the magnetic ore to be sorted. The effect of multichannel division board 11 is in order to make waiting to sort the magnetite ore arrange the entering in proper order from each passageway in the second grade separates transfer module 12, transfer module 12 is separated in order to waiting to sort the magnetite ore to the effect of second grade is in order to separate the magnetite ore to carry out voltage value signal acquisition to the waiting to sort that arranges in proper order to data acquisition subassembly 17, avoids taking place signal interference in the data acquisition in-process.
In an embodiment of the present invention, the sensor assembly 14 is a photoelectric sensor, and includes a photoelectric sensor emitting end and a photoelectric sensor receiving end respectively disposed at two sides of the two-stage separating and conveying assembly 12, that is, the photoelectric sensor emitting end and the photoelectric sensor receiving end determine whether the magnetite to be sorted passes below the data collecting area 18.
Further, the magnetic field generating assembly 16 includes a permanent magnet disposed on the top of the supporting frame 15, and the distance between the bottom of the permanent magnet and the top conveying surface of the second-stage separation conveying assembly 12 is greater than the particle size of the magnetite to be sorted, so as to facilitate the passage of the magnetite to be sorted.
Referring to fig. 7, the data acquisition assembly 17 includes a hollow guide rod 171 transversely disposed on the support frame 15, a plurality of hall sensors 172 disposed in the hollow guide rod 171, a signal isolator 173 and a data acquisition card 174 disposed on the bottom plate 19, and the plurality of hall sensors 172 are respectively and sequentially electrically connected to the central processing unit 20 through the signal isolator 173, the data acquisition card 174.
Further, the number of the hall sensors 172 corresponds to the number of channels of the secondary separating and conveying assembly 12 and the number of channels of the multi-channel partition plate 11, respectively, and the distance between the hall sensors and the lower surface of the top conveying surface of the secondary separating and conveying assembly 12 is 1mm to 2 mm.
Referring to fig. 7, the sorting performing assembly 21 is located below the second-stage separating and conveying assembly 12, and includes an air cylinder 211 and a relay 212 which are arranged on the bottom plate 19, a side air supply system 213, a mounting plate 214 which is arranged below an outlet of the second-stage separating and conveying assembly 12, and a plurality of nozzles 215 which are arranged on the mounting plate 214, each nozzle 215 is communicated with the air cylinder 211 through an air pipe and a high-speed electromagnetic valve 216, the air cylinder and each high-speed electromagnetic valve 216 are electrically connected with the air supply system 213 through the relay 212, and the number of the nozzles 215 corresponds to the number of the hall sensors 172.
It should be noted that, in this embodiment, the cpu 20 calculates the position of each magnetic ore to be sorted, which falls from the outlet of the secondary separation and transport assembly 12, to the corresponding nozzle 215, and controls the corresponding high-speed solenoid valve 216 to open, so that the nozzle 215 blows air to sort the magnetic ore to be sorted into the corresponding storage area of the multi-stage storage box 13.
In a preferred embodiment of the present invention, the sorting performing assembly 21 is located above the two-stage separation conveying assembly 12, and includes a plurality of manipulators, the number of the manipulators corresponds to the number of the hall sensors 172, and the manipulators are used for grabbing the magnetic iron ore after the signal acquisition and placing the magnetic iron ore into the corresponding storage areas of the storage boxes 13.
In another preferred embodiment of the present invention, the cpu 20 includes an upper computer 201 disposed on a side of the second-stage separating and conveying assembly 12, and a lower computer 202 disposed on the bottom plate 19 and electrically connected to the upper computer 201, and the lower computer is electrically connected to the sorting performing assembly 21 and controls the sorting performing operation of the sorting performing assembly 21.
It is further clear that the specific operation steps of using the above-mentioned magnetite intelligent separation device are as follows:
firstly, adjusting the installation position of a permanent magnet according to the granularity range of the magnetite ore to be sorted;
a second part, embedding a corresponding deep learning model according to the grade characteristics of the magnetite ore to be selected;
thirdly, starting the gas supply system 213 and adjusting the gas pressure;
fourthly, starting the first-stage conveying assembly 10, the second-stage separating conveying assembly 12, the two groups of sensor assemblies 14, the data acquisition assembly 17, the central processing unit 20 and the sorting execution assembly 21, and starting the sorting equipment;
fifthly, when the magnetite to be sorted enters the lower part of the data acquisition area 18, the data acquisition assembly 17 starts to acquire data, and stops acquiring after leaving the data acquisition area, or starts to acquire when the magnetite to be sorted passes the lower part of the data acquisition area 18, otherwise stops acquiring;
sixthly, the central processing unit 20 performs calculation analysis on the collected ore data, and if the collected ore data meet the sorting conditions, a sorting instruction is issued, otherwise, the sorting instruction is not issued;
seventhly, the sorting execution component 21 executes the command of the central processing unit 20 to complete one-time sorting;
and step eight, circulating the step four to the step seven.
In summary, the technical scheme of the invention has the following advantages:
1. the selection grade of the magnetite ore to be selected is enlarged, and the ore utilization rate is improved;
2. the magnetic ores to be sorted with different iron contents can be classified in real time, so that the subsequent process of the sorted magnetic ores is convenient to carry out, and the ore dressing cost is reduced;
3. the modularization degree is higher, easily imbeds automatic sorting facilities, has improved intelligent degree.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (9)
1. The intelligent magnetic iron ore sorting method is characterized by comprising the following steps:
step S11, determining the lowest grade and the particle size range of the magnetic iron ore to be sorted;
step S12, determining the magnetic field intensity and the position of a magnetic source which can enable the lowest grade magnetic ore in the magnetic ore to be sorted to generate a detectable signal;
step S13, signal acquisition is performed on a plurality of ores randomly selected from magnetite ores to be sorted using a data acquisition system to obtain signal acquisition data, and the signal acquisition data is preprocessed to obtain preprocessed data, wherein,
step S131, collecting the voltage value of each magnetic iron ore to be sorted to establish a relative reference line of each magnetic iron ore to be sorted
Wherein,
the difference value of the jth sampling point of the ith magnetite to be sorted and the reference line of the ith magnetite to be sorted is obtained,
the voltage value of the jth sampling point of the ith magnetite to be sorted is the voltage value of the jth sampling point of the ith magnetite to be sorted, and n is the number of sampling points of the ith magnetite to be sorted;
step S132, relative reference line of each magnetite to be sorted
Make absolute value change
Wherein,
is composed of
Absolute value of (d);
step S133, sequentially selecting voltage critical values of different sizes to make corresponding category labels for each absolute value magnetic iron ore to be sorted,
wherein L (Max (| Δ)i|)) is the category of the ith magnetite to be sorted, Max (| Delta)iI) is all sampling points of ith magnetite ore to be sorted
The maximum values a, b and c are respectively voltage critical values for classifying the magnetite to be classified;
step S134, establishing absolute reference lines of all magnetite ores to be sorted
Wherein Min (| Delta)all|)、Max(|ΔallI) are all sampling points of the ith magnetite ore to be sorted respectivelyThe minimum value and the maximum value after absolute value conversion,
setting the value of the jth sampling point of the ith magnetite to be sorted after the absolute reference line is established;
step S14, performing dimension transformation on each preprocessed data to generate corresponding ore samples, and dividing the ore samples into a training set and a testing set;
step S15, training a training set by adopting a deep learning model, and testing the model by a test set to judge whether a test result meets the current mineral separation standard;
and step S16, if yes, successfully training the deep learning model, embedding the deep learning model and the data acquisition system into automatic sorting equipment, and sorting the magnetite through the automatic sorting equipment.
2. The intelligent magnetic iron ore sorting method according to claim 1, wherein the step S12 specifically includes:
step S121, establishing a magnetite model which corresponds to the lowest-grade magnetite and has uniformly distributed relative permeability to replace real ore in multi-physical-field simulation software;
step S122, applying magnetic sources with different magnetic field strengths to the magnetite ore model in a simulation environment, and determining the magnetic field strength and the position of a simulation magnetic source which enables the magnetite ore model to generate a detectable signal according to the granularity range of the magnetite ore model;
step S123, taking a permanent magnet as a magnetic source, and actually testing the lowest-grade magnetic iron ore in the magnetic iron ore to be sorted to determine the magnetic field intensity and the position of the actual magnetic source;
and step S124, analyzing and comparing the magnetic field intensity and the position of the analog magnetic source and the actual magnetic source to determine the magnetic field intensity and the position of the final magnetic source.
3. The intelligent sorting method for magnetite ores according to claim 1, wherein in step S15, the deep learning model comprises one of a convolutional neural network model, a modified convolutional neural network model, a cyclic neural network model or a modified cyclic neural network model.
4. An intelligent magnetic iron ore sorting device, which is used for sorting magnetic iron ores by adopting the intelligent magnetic iron ore sorting method of any one of claims 1 to 3, and is characterized by comprising a primary conveying assembly, a multi-channel partition plate, a secondary separation conveying assembly and a multi-stage storage box which are sequentially arranged, wherein one end of the multi-channel partition plate is arranged at an outlet of the primary conveying assembly, and the other end of the multi-channel partition plate is arranged at an inlet of the secondary separation conveying assembly;
the top transmission surface of the secondary separation conveying assembly is provided with two groups of sensor assemblies, a support frame is arranged above the two groups of sensor assemblies in a crossing mode, the support frame is provided with a magnetic field generating assembly and a data collecting assembly, the two groups of sensor assemblies are respectively positioned on two sides of the support frame, a data collecting area is formed on the top transmission surface of the secondary separation conveying assembly, the magnetic field generating assembly is positioned above the data collecting area, and the data collecting assembly is positioned below the data collecting area;
the bottom of second grade partition conveying subassembly is equipped with the bottom plate, the side is equipped with central processing unit, the exit is equipped with selects separately the executive component, central processing unit respectively with select separately executive component, data acquisition subassembly, magnetic field generation subassembly and two sets of sensor assembly electric connection.
5. An intelligent magnetic iron ore sorting apparatus as claimed in claim 4, wherein the magnetic field generating assembly comprises a permanent magnet disposed on top of the support frame, the distance between the bottom of the permanent magnet and the top transport surface of the secondary separation transport assembly being greater than the grain size of the magnetic iron ore to be sorted.
6. The intelligent magnetic iron ore sorting device according to claim 5, wherein the data collection assembly comprises a hollow guide rod transversely disposed on the support frame, a plurality of Hall sensors disposed in the hollow guide rod, and a signal isolator and a data collection card disposed on the bottom plate, wherein the plurality of Hall sensors are electrically connected to the central processing unit through the signal isolator, the data collection card, respectively.
7. An intelligent magnetic iron ore sorting apparatus according to claim 6, wherein the number of the Hall sensors corresponds to the number of the channels of the secondary separation transport assembly and the number of the channels of the multi-channel partition plate, respectively, and the distance between the Hall sensors and the lower surface of the top transport surface of the secondary separation transport assembly is 1mm to 2 mm.
8. The intelligent magnetic iron ore sorting device according to claim 6, wherein the sorting actuator is located below the second-stage separation conveying assembly, and comprises an air supply system provided with an air cylinder, a relay and a side edge on the bottom plate, a mounting plate provided below the outlet of the second-stage separation conveying assembly, and a plurality of nozzles provided on the mounting plate, each nozzle is communicated with the air cylinder through an air pipe and a high-speed electromagnetic valve, the air cylinder is communicated with the air supply system, each high-speed electromagnetic valve is electrically connected with the central processing unit through the relay, and the number of the nozzles corresponds to the number of the Hall sensors.
9. The intelligent magnetic iron ore sorting equipment as claimed in claim 6, wherein the sorting execution assembly is located above the secondary separation conveying assembly and comprises a plurality of manipulators, and the number of the manipulators corresponds to the number of the Hall sensors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110314908.XA CN112916432B (en) | 2021-03-24 | 2021-03-24 | Intelligent magnetic ore sorting method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110314908.XA CN112916432B (en) | 2021-03-24 | 2021-03-24 | Intelligent magnetic ore sorting method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112916432A CN112916432A (en) | 2021-06-08 |
| CN112916432B true CN112916432B (en) | 2022-06-03 |
Family
ID=76175807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110314908.XA Active CN112916432B (en) | 2021-03-24 | 2021-03-24 | Intelligent magnetic ore sorting method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112916432B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114089056B (en) * | 2021-10-23 | 2023-07-04 | 天通精电新科技有限公司 | Anti-interference performance testing device of microwave circulator |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19522547A1 (en) * | 1994-06-22 | 1996-01-11 | Hitachi Metals Ltd | Magnetic carrier for electrophotographic carriers |
| CN104350429A (en) * | 2012-05-31 | 2015-02-11 | 户田工业株式会社 | Magnetic carriers for electrophotographic developer, processes for producing same, and two-component developer |
| CN106944225A (en) * | 2017-03-31 | 2017-07-14 | 东北大学 | The high electric field pulse preprocess method that a kind of strong permanent magnet ore deposit is crushed and sorted |
| CN110614158A (en) * | 2019-10-28 | 2019-12-27 | 中国地质科学院郑州矿产综合利用研究所 | Dense medium sorting system |
| CN111289413A (en) * | 2020-03-02 | 2020-06-16 | 电子科技大学 | Be applied to sensor that heavy metal particle detected in air |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7129918B2 (en) * | 2000-03-10 | 2006-10-31 | Semiconductor Energy Laboratory Co., Ltd. | Electronic device and method of driving electronic device |
| CN2698453Y (en) * | 2003-11-04 | 2005-05-11 | 首钢总公司 | Combination type flashing magnetic field selection machine |
| CN102778843B (en) * | 2012-07-23 | 2014-08-20 | 东北大学 | Operation control method of high magnetic grading process |
| CN102915447B (en) * | 2012-09-20 | 2015-07-08 | 西安科技大学 | Binary tree-based SVM (support vector machine) classification method |
| AU2014234959A1 (en) * | 2013-03-20 | 2015-10-29 | Technological Resources Pty. Limited | Processing mined material |
| CN203908983U (en) * | 2014-05-21 | 2014-10-29 | 哈尔滨理工大学 | Rapid testing device for iron ore grade |
| WO2017044863A1 (en) * | 2015-09-10 | 2017-03-16 | University Of Utah Research Foundation | Variable frequency eddy current metal sorter |
| CN206924889U (en) * | 2017-01-24 | 2018-01-26 | 成都利君实业股份有限公司 | A kind of variable magnetic field belt type magnetic separator |
| CN107169205B (en) * | 2017-05-17 | 2020-02-11 | 东北大学 | Iron ore classification modeling method |
| US11215732B2 (en) * | 2017-09-25 | 2022-01-04 | Baker Hughes Holdings Llc | Geological constraint using probability functions in stochastic mineralogy modeling |
| CN110398534A (en) * | 2019-08-28 | 2019-11-01 | 井冈山大学 | A kind of the automatic identification method for separating and its detection identification device of tungsten ore primary election |
| CN111739108B (en) * | 2020-06-12 | 2023-09-15 | 鞍钢集团矿业有限公司 | Rapid iron ore powder grade estimation method based on convolutional neural network |
-
2021
- 2021-03-24 CN CN202110314908.XA patent/CN112916432B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19522547A1 (en) * | 1994-06-22 | 1996-01-11 | Hitachi Metals Ltd | Magnetic carrier for electrophotographic carriers |
| CN104350429A (en) * | 2012-05-31 | 2015-02-11 | 户田工业株式会社 | Magnetic carriers for electrophotographic developer, processes for producing same, and two-component developer |
| CN106944225A (en) * | 2017-03-31 | 2017-07-14 | 东北大学 | The high electric field pulse preprocess method that a kind of strong permanent magnet ore deposit is crushed and sorted |
| CN110614158A (en) * | 2019-10-28 | 2019-12-27 | 中国地质科学院郑州矿产综合利用研究所 | Dense medium sorting system |
| CN111289413A (en) * | 2020-03-02 | 2020-06-16 | 电子科技大学 | Be applied to sensor that heavy metal particle detected in air |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112916432A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112916432B (en) | Intelligent magnetic ore sorting method and equipment | |
| Mendonça et al. | Decision tree search methods in fuzzy modeling and classification | |
| CN109540978A (en) | Odor identification equipment | |
| US11192146B2 (en) | System and method for sorting scrap materials | |
| CN112651579B (en) | Flotation recovery rate prediction method based on ore genetic characteristics | |
| CN108355986A (en) | A kind of two-way feeding towards material detection and the unmanned autonomous intelligence equipment of sorting | |
| CN105032791A (en) | Method for utilizing battery automatic testing and sorting device to perform battery testing and sorting | |
| Anstey et al. | Biometric procedures in taxonomic studies of Paleozoic bryozoans | |
| CN114048880A (en) | Particle swarm optimization-based fault diagnosis method for opening valve | |
| Nakhaei et al. | Recovery and grade prediction of pilot plant flotation column concentrate by a hybrid neural genetic algorithm | |
| CN110586502A (en) | Green plum sorting device and method | |
| CN105354170A (en) | CEEMD and singular value decomposition based recognition method | |
| CN106503735A (en) | The recognition methodss of wiring board item number and device | |
| CN103592326A (en) | Nuclear magnetic resonance multichannel detection system used for rapidly sorting oil-containing seeds | |
| CN205380079U (en) | Coloured material letter sorting system | |
| CN104964873B (en) | The fixture and method of Rolling compund material thermal modeling test sample mechanics properties testing | |
| CN212944142U (en) | Magnetic core automatic separation equipment | |
| Kolacz | Advanced separation technologies for pre-concentration of metal ores and the additional process control | |
| CN113128502A (en) | Single piece separation system, method and device based on deep learning and machine vision | |
| CN210572103U (en) | Automatic detection and identification device for tungsten ore primary selection | |
| CN203587530U (en) | Nuclear magnetic resonance multi-channel detection system for quick separation of oil seeds | |
| CN101556646B (en) | Iris sorting scheme based on kernel clustering | |
| CN215103219U (en) | Cell sorter | |
| CN107321632A (en) | Bamboo and wood material sorter control system and method | |
| CN114357873A (en) | Soft measurement method for excitation current of strong magnetic machine |
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 |