CN114515705B - Gangue sorting system based on multi-mode imaging analysis - Google Patents
Gangue sorting system based on multi-mode imaging analysis Download PDFInfo
- Publication number
- CN114515705B CN114515705B CN202111531791.7A CN202111531791A CN114515705B CN 114515705 B CN114515705 B CN 114515705B CN 202111531791 A CN202111531791 A CN 202111531791A CN 114515705 B CN114515705 B CN 114515705B
- Authority
- CN
- China
- Prior art keywords
- gangue
- module
- coal
- positioning information
- mode
- 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
- 238000003384 imaging method Methods 0.000 title claims abstract description 77
- 238000004458 analytical method Methods 0.000 title claims abstract description 27
- 239000003245 coal Substances 0.000 claims abstract description 125
- 239000012535 impurity Substances 0.000 claims abstract description 55
- 238000001514 detection method Methods 0.000 claims abstract description 51
- 238000012216 screening Methods 0.000 claims abstract description 43
- 238000010191 image analysis Methods 0.000 claims description 24
- 238000003331 infrared imaging Methods 0.000 claims description 10
- 238000010438 heat treatment Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 230000002787 reinforcement Effects 0.000 claims description 4
- 238000004846 x-ray emission Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 claims description 2
- 239000010879 coal refuse Substances 0.000 claims 3
- 238000000926 separation method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000002817 coal dust Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 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
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The application provides a gangue sorting system based on multi-mode imaging analysis, which comprises the following components: the system comprises a coal gangue primary screening module, a coal gangue check module and a motion planning module; the coal gangue preliminary screening module is used for carrying out preliminary screening on the coal gangue to be detected to obtain first positioning information and target information, sending the first positioning information to the motion planning module and sending the target information to the coal gangue check module; the coal gangue check module is used for acquiring a multi-mode image according to the target information, inputting the multi-mode image into a multi-mode coal gangue detection model to check the coal gangue, obtaining second positioning information, and sending the second positioning information to the motion planning module; the motion planning module is used for carrying out multi-mechanical arm cooperative motion planning according to the first positioning information and the second positioning information so as to control the multi-mechanical arm to sort out gangue and impurities through cooperative motion.
Description
Technical Field
The application relates to the technical field of gangue sorting, in particular to a gangue sorting system based on multi-mode imaging analysis.
Background
Along with the development of social economy, clean coal technology is receiving more attention, so that the problem of coal gangue separation is very important. At present, coal gangue separation mainly depends on two technologies of dense medium coal separation and manual gangue separation, but in actual production, dense medium coal separation has the problems of large occupied area, great water resource waste and the like, and manual gangue separation has the problems of high labor intensity, poor working environment, easiness in occurrence of accidents and the like. Therefore, the intelligent separation of the coal gangue is urgently needed to replace the traditional separation method.
Under the prior art, coal gangue separation mostly adopts a single detection method, and is mainly divided into ray detection, electromagnetic detection, vibration detection, optical detection and the like. These single detection methods all have obvious disadvantages, wherein the X-ray detection method faces the problem that the quality and thickness of coal and gangue have certain influence on the setting of the separation threshold value; the detection methods such as electromagnetism, vibration and the like are difficult to adapt to the characteristics of complex geology in China; the optical detection method faces the problem that ash and coal dust with different thickness are wrapped on the surface of the gangue to influence the recognition accuracy.
Therefore, the current single detection method is difficult to realize high-precision gangue separation.
Disclosure of Invention
The application provides a gangue sorting system based on multi-mode imaging analysis, which is used for solving the problem of single detection method in the prior art and realizing high-precision gangue sorting.
The application provides a gangue sorting system based on multi-mode imaging analysis, which comprises the following components: the system comprises a coal gangue primary screening module, a coal gangue check module and a motion planning module; the coal gangue preliminary screening module is used for carrying out preliminary screening on the raw coal to be detected to obtain first positioning information and target information, sending the first positioning information to the motion planning module and sending the target information to the coal gangue check module; the first positioning information is gangue and impurity positioning information determined by the gangue screening module, and the target information is positioning information of a target deviating from a set threshold determined by the gangue screening module; the coal gangue check module is used for acquiring a multi-mode image according to the target information, inputting the multi-mode image into a multi-mode coal gangue detection model to check the coal gangue, obtaining second positioning information, and sending the second positioning information to the motion planning module; the second positioning information is gangue and impurity positioning information determined by the gangue check module; the motion planning module is used for carrying out multi-mechanical arm cooperative motion planning according to the first positioning information and the second positioning information so as to control the multi-mechanical arm to sort out gangue and impurities through cooperative motion.
According to the coal gangue sorting system based on multi-mode imaging analysis, the coal gangue preliminary screening module comprises an X-ray imaging module and an X-ray image analysis module; the X-ray imaging module is used for emitting X-rays to the raw coal to be detected and generating an X-ray image of the raw coal to be detected; the X-ray image analysis module is used for judging the coal-gangue-impurity of the X-ray image of the raw coal to be detected based on a preset coal-gangue-impurity judgment threshold value, and the first positioning information and the target information are obtained.
According to the gangue sorting system based on multi-mode imaging analysis, the relative positions of the X-ray imaging module and the raw coal to be detected and the X-ray emission intensity of the X-ray imaging module are adjusted according to the characteristic parameters of the raw coal to be detected.
According to the coal gangue sorting system based on multi-mode imaging analysis, the coal gangue check module comprises a multi-mode imaging module and a multi-mode image analysis module; the multi-modal imaging module comprises at least two of a visible light imaging module, an infrared imaging module and a depth imaging module and is used for generating multi-modal images corresponding to the targets deviating from the set threshold according to the target information; the multi-mode image analysis module is used for inputting the multi-mode image into a multi-mode gangue detection model to obtain a multi-mode detection result, and fusing the multi-mode detection result to obtain second positioning information.
According to the coal gangue sorting system based on multi-mode imaging analysis, the multi-mode coal gangue detection model is obtained by training according to the multi-mode image sample and the actual detection result corresponding to the multi-mode image sample.
According to the coal gangue sorting system based on multi-mode imaging analysis, which is provided by the application, the system further comprises a transmission system, wherein the transmission system is used for transmitting the raw coal to be detected through a belt; the number and the angle of the imaging modules contained in the multi-mode imaging module are determined according to the width of the belt, the transmission speed of the belt and the characteristic parameters of the raw coal to be detected.
According to the coal gangue sorting system based on multi-mode imaging analysis, provided by the application, under the condition that the multi-mode imaging module comprises an infrared imaging module, the system further comprises heating modules arranged on two sides of the belt and used for heating raw coal corresponding to the target information.
According to the coal gangue sorting system based on multi-mode imaging analysis, the multi-mechanical arm collaborative motion planning is performed according to the first positioning information and the second positioning information, so as to control the multi-mechanical arm to sort out gangue and impurities through collaborative motion, and the system comprises the following components:
according to the coal gangue sorting system based on multi-mode imaging analysis, the first positioning information and the second positioning information construct a multi-mechanical arm collaborative motion planning optimization model; solving the multi-mechanical arm cooperative motion planning optimization model by using a deep reinforcement learning algorithm to obtain a multi-mechanical arm cooperative motion planning result; and sending a control instruction to each mechanical arm in the multiple mechanical arms according to the cooperative motion planning result of the multiple mechanical arms, wherein the control instruction is used for indicating the action of each mechanical arm to sort gangue and impurities.
According to the gangue sorting system based on multi-mode imaging analysis, provided by the application, the raw coal is screened twice by arranging the gangue primary screening module, the gangue check module and the motion planning module, so that the gangue can be precisely sorted out on line, the gangue sorting precision is improved, meanwhile, the multi-mechanical arm can be timely controlled to sort out the gangue and impurities, the reasonable layout of the imaging equipment can be carried out according to different working conditions, and the intelligent detection equipment can be better realized to replace manual gangue sorting.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a coal gangue sorting system based on multi-modality imaging analysis;
FIG. 2 is a second schematic diagram of a coal gangue sorting system based on multi-modality imaging analysis according to the present application;
reference numerals:
101, a coal gangue primary screening module; 102: a coal gangue check module; 103: a motion planning module;
1: an X-ray imaging module; 2: an X-ray image analysis module; 3: a visible light module;
an infrared imaging module; 5: a depth imaging module; 6: a multi-modality image analysis module;
7: a motion planning module; 8: multiple mechanical arms.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
The gangue sorting system based on multi-modal imaging analysis of the present application is described below with reference to fig. 1-2.
Fig. 1 is a schematic structural diagram of a gangue sorting system based on multi-mode imaging analysis, which is provided by the application, and as shown in fig. 1, the gangue sorting system comprises: a coal gangue prescreening module 101, a coal gangue check module 102 and a motion planning module 103; wherein,,
the coal gangue preliminary screening module 101 is configured to perform preliminary screening on coal gangue to be detected to obtain first positioning information and target information, send the first positioning information to the motion planning module 103, and send the target information to the coal gangue check module 102; the first positioning information is gangue and impurity positioning information determined by the gangue screening module 101, and the target information is positioning information of a target deviating from a set threshold determined by the gangue screening module 101;
the gangue check module 102 is configured to obtain a multi-mode image according to the target information, input the multi-mode image into a multi-mode gangue detection model to check gangue, obtain second positioning information, and send the second positioning information to the motion planning module 103; wherein, the second positioning information is gangue and impurity positioning information determined by the gangue check module 102;
the motion planning module 103 is configured to perform multi-mechanical arm collaborative motion planning according to the first positioning information and the second positioning information, so as to control the multi-mechanical arm to sort out gangue and impurities through collaborative motion.
It should be noted that, the set threshold is three preset optimal thresholds for distinguishing coal gangue impurities, when the detection target passes through the gangue primary screening module, the obtained detection value is not within the three threshold ranges, that is, the detection target deviates from the set threshold, the gangue primary screening module fails to detect, and the gangue primary screening module needs to screen the target again. The set threshold may be customized as desired.
It should be noted that the multi-modal image is an image acquired by a pointer to the same target using devices of different imaging principles.
It is understood that the multimodal image includes images acquired by devices that utilize at least two different imaging principles.
For example, the multimodal image includes at least two of a visible light image, an infrared image, and a depth image.
It can be understood that the multi-mechanical arm at least comprises two mechanical arms, and cooperative motion planning is needed to be carried out when the gangue and the impurities are sorted, so that collision between the mechanical arms during sorting is avoided.
Specifically, the whole gangue sorting system consists of three major parts: the system comprises a coal gangue primary screening module 101, a coal gangue check module 102 and a motion planning module 103. Firstly, a coal gangue primary screening module 101 is utilized to perform primary screening on raw coal to be detected, a batch of coal gangue-impurities is screened out, positioning information of the gangue and the impurities is sent to a motion planning module 103, so that the motion planning module 103 controls a plurality of mechanical arms to sort out the gangue and the impurities through cooperative motion, and meanwhile, positioning information of the raw coal deviating from a set threshold value during primary screening is sent to a coal gangue check module, so that the coal gangue check module 102 performs secondary screening on the raw coal deviating from the set threshold value; then, the coal gangue check module 102 is utilized to screen the raw coal which is preliminarily screened but is not successfully detected again, another batch of coal gangue-impurity is screened, positioning information of the gangue and the impurity in the raw coal gangue is sent to the motion planning module 103, and the motion planning module 103 controls a plurality of mechanical arms to sort out the gangue and the impurity through cooperative motion; the motion planning module 103 is mainly used for receiving positioning information of the gangue and the impurities screened by the gangue preliminary screening module and the gangue check module and sorting the gangue and the impurities in time.
In the above embodiment, through setting up gangue prescreening module 101, gangue check module 102 and motion planning module 103, twice screening has been carried out to the raw coal, can select gangue in online accurate separation, has improved gangue and has selected the precision, control that simultaneously can be timely goes out gangue and impurity by multiple mechanical arms letter sorting to can carry out imaging device's reasonable layout according to different operating modes, better realization intellectual detection system replaces artifical gangue selection.
Optionally, the gangue prescreening module 101 comprises an X-ray imaging module and an X-ray image analysis module; wherein,,
the X-ray imaging module is used for emitting X-rays to the raw coal to be detected and generating an X-ray image of the raw coal to be detected;
the X-ray image analysis module is used for judging the coal-gangue-impurity of the X-ray image of the raw coal to be detected based on a preset coal-gangue-impurity judgment threshold value, and the first positioning information and the target information are obtained.
The X-ray detection is realized according to different absorption conditions of coal or gangue to rays, and has stronger anti-interference capability.
Before the gangue is screened by using the gangue pre-screening module 101, a large amount of data of coal, gangue and impurities needs to be collected to build an X-ray database, and three optimal thresholds for distinguishing coal, gangue and impurities are determined.
It can be understood that when the detection value obtained by the X-ray image analysis module is within any one threshold range of coal, gangue and impurities, the type of the raw coal to be detected is judged to be the type corresponding to the threshold value; when the detected value is not within the three threshold ranges, it is indicated that the detected value is correspondingly deviated from the target of the set threshold.
Specifically, when raw coal to be detected passes through the gangue preliminary screening module 101, firstly, an X-ray imaging module sends X-rays to the raw coal to be detected to generate an X-ray image of the raw coal to be detected, then an X-ray image analysis module performs image data processing on the generated X-ray image of the raw coal to be detected, the gangue, the coal and targets deviating from a set threshold value are distinguished, then the locating information of the distinguished gangue and impurities is sent to the motion planning module 103, the gangue and impurities are sorted, and the locating information of the distinguished targets deviating from the set threshold value is sent to the gangue check module 102 for screening again.
In the above embodiment, the detected raw coal is primarily screened by using the X-ray imaging module and the X-ray image analysis module, so that the coal-gangue-impurity can be determined to a great extent, and then the raw coal which fails to be detected by the gangue primary screening module 101 is screened again, and meanwhile, the positioning information of the gangue and the impurity can be timely generated and sent to the motion planning module 103, so that the gangue and the impurity can be quickly sorted out.
Optionally, the relative positions of the X-ray imaging module and the raw coal to be detected and the X-ray emission intensity of the X-ray imaging module are adjusted according to the characteristic parameters of the raw coal to be detected.
It can be understood that the quality, thickness, volume and material of the coal and gangue have a certain influence on the acquisition of images during the X-ray detection, so that the position of a ray imaging module and the X-ray emission intensity need to be adjusted according to the characteristic parameters of the raw coal to be detected.
In this embodiment, the characteristic parameters include, but are not limited to, volume parameters, material parameters, quality parameters, and thickness parameters.
In the embodiment, the position and the X-ray intensity of the X-ray imaging module are adjusted according to the characteristic parameters of the raw coal to be detected, so that the screening precision of the coal gangue primary screening module is further improved, and the coal gangue-impurity can be largely judged at the coal gangue primary screening module.
Optionally, the gangue check module 102 includes a multi-modality imaging module and a multi-modality image analysis module; wherein,,
the multi-mode imaging module comprises at least two of a visible light imaging module, an infrared imaging module and a depth imaging module and is used for generating a multi-mode image corresponding to the target deviating from the set threshold according to the target information;
the multi-mode image analysis module is used for inputting the multi-mode image into a multi-mode gangue detection model to obtain a multi-mode detection result, and fusing the multi-mode detection result to obtain second positioning information.
In one embodiment, the multimodal processing information may be fused using a weight matrix.
Specifically, in the gangue check module 102, a multi-mode image is firstly generated by using a multi-mode imaging module for a target deviating from a set threshold value obtained after passing through the gangue preliminary screening module 101, then the generated multi-mode image is input into a multi-mode gangue detection model of a multi-mode image analysis module to obtain a multi-mode detection result, after the multi-mode detection result is fused, the gangue-impurity can be accurately distinguished, and then the locating information of the distinguished gangue and impurity is sent to the motion planning module 103 to sort out the gangue and impurity.
In the embodiment, the multi-mode imaging module and the multi-mode image analysis module are mutually matched, raw coal which is failed to be detected by the coal gangue primary screening module can be screened again, the sorting precision of the coal gangue is improved, and meanwhile, positioning information of the gangue and impurities can be timely generated and sent to the motion planning module, so that the gangue and the impurities which are judged by the coal gangue check module can be quickly sorted out.
Optionally, the multi-mode gangue detection model is obtained by training according to a multi-mode image sample and an actual detection result corresponding to the multi-mode image sample.
The actual detection result refers to actual positioning information of gangue and impurities in the multi-mode image sample.
In one embodiment, the multi-modal gangue detection model may use a ShuffleNet and SGAN converged network.
In another embodiment, the multi-modal gangue detection model may use a Knowledge Distillation and ShuffleNet fusion network.
The multi-mode gangue detection model can detect and classify multi-mode images, output multi-mode information and acquire gangue check results by fusing the multi-mode information.
The embodiment of the application does not limit the structure of the multi-mode gangue detection model and the training method.
In the embodiment, the multi-mode images are detected and classified by utilizing the multi-mode gangue detection model, so that coal-gangue-impurity can be rapidly and efficiently distinguished, and the screening speed of the gangue sorting system is improved.
Optionally, the system further comprises a conveying system for conveying the raw coal to be detected through a belt;
the number and the angle of the imaging modules contained in the multi-mode imaging module are determined according to the width of the belt, the transmission speed of the belt and the characteristic parameters of the raw coal to be detected.
It can be understood that parameters such as quality, thickness, volume, material and the like of the raw coal to be detected, and belt transmission speed and width have certain influence on acquisition of multi-mode images, so that accuracy of screening results is influenced.
In the embodiment, the imaging module is reasonably arranged and adjusted according to the parameters such as the width of the belt, the belt transmission speed, the quality of the coal gangue and the like, so that the accuracy of screening results is improved, and the intelligent detection equipment can be better realized to replace manual gangue selection.
Optionally, in the case that the multi-mode imaging module includes an infrared imaging module, the system further includes heating modules disposed at both sides of the belt for heating raw coal corresponding to the target information.
It should be understood that when an infrared imaging module, such as an infrared camera, is used to acquire images, a corresponding heating device is required to rapidly heat the raw coal to be detected.
In one embodiment, the heating means may be radiant heating.
Optionally, the performing the planning of the cooperative motion of the multiple mechanical arms according to the first positioning information and the second positioning information, so as to control the multiple mechanical arms to sort out the gangue and the impurity through the cooperative motion, including:
constructing a multi-mechanical arm collaborative motion planning optimization model according to the first positioning information and the second positioning information;
solving the multi-mechanical arm cooperative motion planning optimization model by using a deep reinforcement learning algorithm to obtain a multi-mechanical arm cooperative motion planning result;
and sending a control instruction to each mechanical arm in the multiple mechanical arms according to the cooperative motion planning result of the multiple mechanical arms, wherein the control instruction is used for indicating the action of each mechanical arm to sort gangue and impurities.
In the above embodiment, the motion planning module establishes the optimal mathematical model of the mechanical arm dynamic target grabbing problem by receiving the positioning information of the coal gangue primary screening module and the coal gangue check module, and introduces a deep reinforcement learning algorithm, so that the strain of the multi-mechanical arm to a changeable environment, the rapidity of autonomous path planning and intelligent decision and the high efficiency of the multi-mechanical arm collaborative task can be improved.
Fig. 2 is a second schematic structural diagram of the gangue sorting system based on multi-mode imaging analysis according to the present application, as shown in fig. 2, including:
the system comprises an X-ray imaging module 1, an X-ray image analysis module 2, a visible light module 3, an infrared imaging module 4, a depth imaging module 5, a multi-mode image analysis module 6, a motion planning module 7 and a multi-mechanical arm 8;
specifically, firstly, an X-ray imaging module 1 is used for emitting rays to raw coal to be detected and generating an X-ray image, then an X-ray image analysis module 2 is used for carrying out image data processing on the generated X-ray image, whether the raw coal to be detected is coal, gangue and impurities or targets deviating from a set threshold value is judged, positioning information of the gangue and the impurities is used as first positioning information to be sent to a motion planning module 7, and target information deviating from the set threshold value is sent to a gangue check module; then, a visible light module 3, an infrared imaging module 4 and a depth imaging module 5 in the gangue check module collect images of targets deviating from a set threshold value, the collected images are respectively sent to a multi-mode image analysis module 6, the multi-mode image analysis module 6 inputs multi-mode images into a multi-mode gangue detection model to obtain multi-mode detection results, the multi-mode detection results are fused, coal, gangue and impurities are further distinguished, and positioning information of the gangue and the impurities is used as second positioning information to be sent to a motion planning module 7; and then the motion planning module 7 sends control instructions to each mechanical arm in the multi-mechanical arms 8 according to the first positioning information and the second positioning information, so as to sort gangue and impurities corresponding to the positioning information.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (7)
1. A coal refuse sorting system based on multi-modal imaging analysis, comprising: the system comprises a coal gangue primary screening module, a coal gangue check module and a motion planning module; wherein,,
the coal gangue preliminary screening module is used for carrying out preliminary screening on the coal gangue to be detected to obtain first positioning information and target information, sending the first positioning information to the motion planning module and sending the target information to the coal gangue check module; the first positioning information is gangue and impurity positioning information determined by the gangue screening module, and the target information is positioning information of a target deviating from a set threshold determined by the gangue screening module;
the coal gangue check module is used for acquiring a multi-mode image according to the target information, inputting the multi-mode image into a multi-mode coal gangue detection model to check the coal gangue, obtaining second positioning information, and sending the second positioning information to the motion planning module; the second positioning information is gangue and impurity positioning information determined by the gangue check module;
the motion planning module is used for carrying out multi-mechanical arm cooperative motion planning according to the first positioning information and the second positioning information so as to control the multi-mechanical arm to sort out gangue and impurities through cooperative motion;
the multi-mechanical arm collaborative motion planning is performed according to the first positioning information and the second positioning information, so as to control the multi-mechanical arm to sort out gangue and impurities through collaborative motion, and the method comprises the following steps:
constructing a multi-mechanical arm collaborative motion planning optimization model according to the first positioning information and the second positioning information;
solving the multi-mechanical arm cooperative motion planning optimization model by using a deep reinforcement learning algorithm to obtain a multi-mechanical arm cooperative motion planning result;
and sending a control instruction to each mechanical arm in the multiple mechanical arms according to the cooperative motion planning result of the multiple mechanical arms, wherein the control instruction is used for indicating the action of each mechanical arm to sort gangue and impurities.
2. The multi-modality imaging analysis based gangue sorting system of claim 1, wherein the gangue prescreening module comprises an X-ray imaging module and an X-ray image analysis module; wherein,,
the X-ray imaging module is used for emitting X-rays to the raw coal to be detected and generating an X-ray image of the raw coal to be detected;
the X-ray image analysis module is used for judging the coal-gangue-impurity of the X-ray image of the raw coal to be detected based on a preset coal-gangue-impurity judgment threshold value, and the first positioning information and the target information are obtained.
3. The coal gangue sorting system based on multi-modal imaging analysis according to claim 2, wherein the relative positions of the X-ray imaging module and the raw coal to be detected and the X-ray emission intensity of the X-ray imaging module are adjusted according to the characteristic parameters of the raw coal to be detected.
4. The multi-modality imaging analysis based gangue sorting system of claim 1, wherein the gangue check module comprises a multi-modality imaging module and a multi-modality image analysis module; wherein,,
the multi-mode imaging module comprises at least two of a visible light imaging module, an infrared imaging module and a depth imaging module and is used for generating a multi-mode image corresponding to the target deviating from the set threshold according to the target information;
the multi-mode image analysis module is used for inputting the multi-mode image into a multi-mode gangue detection model to obtain a multi-mode detection result, and fusing the multi-mode detection result to obtain second positioning information.
5. The coal gangue sorting system based on multi-modal imaging analysis according to claim 4, wherein the multi-modal coal gangue detection model is trained based on multi-modal image samples and actual detection results corresponding to the multi-modal image samples.
6. The coal refuse sorting system based on multi-modality imaging analysis according to claim 4, further comprising a conveyor system for conveying the raw coal to be detected by a belt;
the number and the angle of the imaging modules contained in the multi-mode imaging module are determined according to the width of the belt, the transmission speed of the belt and the characteristic parameters of the raw coal to be detected.
7. The coal refuse sorting system based on multi-modality imaging analysis according to claim 6, characterized in that in case the multi-modality imaging module comprises an infrared imaging module, the system further comprises heating modules arranged at both sides of the belt for heating raw coal corresponding to the target information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531791.7A CN114515705B (en) | 2021-12-14 | 2021-12-14 | Gangue sorting system based on multi-mode imaging analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531791.7A CN114515705B (en) | 2021-12-14 | 2021-12-14 | Gangue sorting system based on multi-mode imaging analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114515705A CN114515705A (en) | 2022-05-20 |
| CN114515705B true CN114515705B (en) | 2023-10-17 |
Family
ID=81596744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111531791.7A Active CN114515705B (en) | 2021-12-14 | 2021-12-14 | Gangue sorting system based on multi-mode imaging analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114515705B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114985305B (en) * | 2022-05-27 | 2024-04-26 | 安徽国祯生态科技有限公司 | Straw quality detection and classification system and method |
| CN115862009B (en) * | 2023-02-24 | 2023-05-12 | 山东卫康生物医药科技有限公司 | Data processing method and system for precisely culturing ginseng stem cells |
| CN116159773A (en) * | 2023-02-28 | 2023-05-26 | 安徽理工大学 | Coal gangue separation method based on series connection of visible light and X-rays and device thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110052421A (en) * | 2019-04-29 | 2019-07-26 | 山东华特磁电科技股份有限公司 | A kind of coal mine method for separating based on X-ray sensing |
| CN111266172A (en) * | 2020-01-22 | 2020-06-12 | 山西鸿太旭飞能源科技有限公司 | Coal gangue underground treatment method |
| CN111993418A (en) * | 2020-08-06 | 2020-11-27 | 西安科技大学 | Multi-target multi-mechanical-arm collaborative sorting system and sorting strategy for coal and gangue sorting robot |
| CN112845039A (en) * | 2020-12-21 | 2021-05-28 | 中国矿业大学 | Efficient coal gangue sorting method based on microwave radiation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102416386B (en) * | 2011-10-27 | 2013-09-18 | 山东博润工业技术股份有限公司 | Process and system for sorting coal by discharging coal gangue through dry method |
-
2021
- 2021-12-14 CN CN202111531791.7A patent/CN114515705B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110052421A (en) * | 2019-04-29 | 2019-07-26 | 山东华特磁电科技股份有限公司 | A kind of coal mine method for separating based on X-ray sensing |
| CN111266172A (en) * | 2020-01-22 | 2020-06-12 | 山西鸿太旭飞能源科技有限公司 | Coal gangue underground treatment method |
| CN111993418A (en) * | 2020-08-06 | 2020-11-27 | 西安科技大学 | Multi-target multi-mechanical-arm collaborative sorting system and sorting strategy for coal and gangue sorting robot |
| CN112845039A (en) * | 2020-12-21 | 2021-05-28 | 中国矿业大学 | Efficient coal gangue sorting method based on microwave radiation |
Non-Patent Citations (3)
| Title |
|---|
| 唐子惠.医学人工智能导论.上海科学技术出版社,2020,第445页. * |
| 唐苏亚.IECQ QC080000有害物质过程管理体系的建立与实施.广东经济出版社,2011,第198-199页. * |
| 张乃禄.安全检测技术 第3版.西安电子科技大学出版社,2018,第305-306页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114515705A (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114515705B (en) | Gangue sorting system based on multi-mode imaging analysis | |
| CN112083017A (en) | Intelligent detection device, method and medium for internal defects of welding seam | |
| CN109948506A (en) | A kind of multi-angle garbage classification cloud platform based on deep learning | |
| CN106897737B (en) | A kind of high-spectrum remote sensing terrain classification method based on the learning machine that transfinites | |
| CN107944504B (en) | Board recognition and machine learning method and device for board recognition and electronic equipment | |
| CN110135468A (en) | A kind of recognition methods of gangue | |
| CN108918539A (en) | A kind of apparent Defect inspection device and method of tunnel structure | |
| CN1151464C (en) | Method of reading characters and method of reading postal addresses | |
| CN109919243A (en) | A kind of scrap iron and steel type automatic identifying method and device based on CNN | |
| CN206139527U (en) | Panoramic vision potato is selected separately and defect detecting device | |
| CN107818302A (en) | Non-rigid multiple dimensioned object detecting method based on convolutional neural networks | |
| CN101105459A (en) | Empty bottle mouth defect inspection method and device | |
| CN103934211A (en) | Stereoscopic vision-based three-dimensional product size sorting system | |
| CN113421230B (en) | Visual detection method for defects of vehicle-mounted liquid crystal display light guide plate based on target detection network | |
| Soilán et al. | Semantic segmentation of point clouds with pointnet and kpconv architectures applied to railway tunnels | |
| CN103785622A (en) | Machine-vision-based part sorting device and method | |
| CN110633738B (en) | Rapid classification method for industrial part images | |
| CN106598622A (en) | Smart vision inspection platform | |
| CN109693140A (en) | A kind of intelligent flexible production line and its working method | |
| Gill et al. | Garbage Classification Utilizing Effective Convolutional Neural Network | |
| CN114378002A (en) | Hericium erinaceus grading system and grading method based on machine vision | |
| CN206139529U (en) | Transparent roller bearing mechanism | |
| CN109410203A (en) | A kind of picture picture quality detection method based on machine learning | |
| CN110728119B (en) | Poster generation method and device | |
| CN112418362B (en) | Target detection training sample screening method |
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 |