CN114104666A - Coal and gangue identification method and coal mine conveying system - Google Patents
Coal and gangue identification method and coal mine conveying system Download PDFInfo
- Publication number
- CN114104666A CN114104666A CN202111393330.8A CN202111393330A CN114104666A CN 114104666 A CN114104666 A CN 114104666A CN 202111393330 A CN202111393330 A CN 202111393330A CN 114104666 A CN114104666 A CN 114104666A
- Authority
- CN
- China
- Prior art keywords
- coal
- gangue
- signal
- rear conveyor
- model
- 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.)
- Pending
Links
- 239000003245 coal Substances 0.000 title claims abstract description 253
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000012549 training Methods 0.000 claims abstract description 47
- 230000001133 acceleration Effects 0.000 claims abstract description 33
- 238000010183 spectrum analysis Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000013135 deep learning Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000001228 spectrum Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 3
- 239000010878 waste rock Substances 0.000 claims description 3
- 230000009471 action Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 238000003672 processing method Methods 0.000 description 6
- 230000005236 sound signal Effects 0.000 description 5
- 239000000872 buffer Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011496 digital image analysis Methods 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/02—Devices for feeding articles or materials to conveyors
- B65G47/16—Devices for feeding articles or materials to conveyors for feeding materials in bulk
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2201/00—Indexing codes relating to handling devices, e.g. conveyors, characterised by the type of product or load being conveyed or handled
- B65G2201/04—Bulk
- B65G2201/045—Sand, soil and mineral ore
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
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)
- Mechanical Engineering (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a coal and gangue identification method and a coal mine conveying system, wherein the coal and gangue identification method comprises the following steps: collecting impact signals generated by coal falling onto a rear conveyor through a vibration acceleration sensor arranged on a rear conveyor body; carrying out spectrum analysis according to the impact signal to obtain characteristic frequency, constructing a characteristic threshold value through digital signal processing according to the characteristic frequency, and/or training a recognition model through a deep learning method; and analyzing the impact signal to be detected through the characteristic threshold and/or the identification model, and identifying and determining the coal or gangue on the rear conveyor body according to the analysis result. Therefore, on the basis, in order to meet the requirements of different fully mechanized caving working faces, the coal or gangue falling on the rear conveyor can be judged in real time, the coal caving action can be controlled according to the output result of the model, and the production efficiency of the coal mine is improved.
Description
Technical Field
The invention relates to the field of mineral exploitation, in particular to a coal and gangue identification method and a coal mine conveying system.
Background
With the rapid development of modern automation control technology, the automation technology of fully mechanized top coal caving working face gradually advances to the unmanned mining age. At present, the automation of fully mechanized mining in the front of the working face is already preliminarily realized. However, due to the technical level and the toggle of theoretical research, the intelligent coal caving of the current top coal caving working face is still in a starting stage, the degree of coal and gangue caving is judged mainly through ear hearing and visual inspection of operators, and the coal caving is stopped by adopting the principle of 'closing a window when the gangue is seen'. However, the situation of over-discharge and under-discharge of the top coal inevitably occurs through manual operation, and personal injury of operators is also possibly caused. The automatic coal caving device has great significance in improving coal mining efficiency, guaranteeing personal safety of personnel and realizing automatic coal caving of a top coal caving working face. As a key technology for automatic coal caving of a top coal caving working face, coal and gangue identification methods are mainly divided into a gamma ray method, a radar detection method, a cutting force response analysis method, an image identification method and the like, but due to the fact that the underground working face is poor in environment and low in visibility, the coal and gangue identification method is low in identification rate and low in deployability. Therefore, designing a reliable automatic identification method of the coal gangue becomes a key problem in the automatic coal caving technology of the top coal caving face.
In order to solve the problem of low precision of coal and gangue manual identification caused by severe environments such as multiple dusts, humidity and darkness on a working face, the technology provides a coal and gangue identification method in a top coal caving process based on multi-sensing information fusion. Firstly, audio signals and vibration signals collected on a tail beam of a top coal caving hydraulic support are respectively collected, then Empirical Mode Decomposition (EMD) is used for feature extraction, a support vector machine and a BP neural network are trained to carry out coal and gangue identification on the audio signals and the vibration signals, and finally decision and fusion are carried out on identification results according to a D-S evidence theory, so that the accuracy and the reliability of coal and gangue identification are greatly improved. However, the technology selects to install a vibration sensor on the tail beam of the hydraulic support for the caving coal to collect vibration signals generated when coal and gangue fall on the tail beam. However, in the actual working condition of top coal caving, coal is always stacked on the upper part of the tail beam, and the coal and gangue cannot directly fall on the tail beam in the falling process, so that the vibration sensor arranged on the tail beam of the hydraulic support is difficult to collect effective coal and gangue signals. Secondly, when the technology uses a support vector machine and a BP neural network model to identify the coal and gangue, effective characteristics of an audio signal and a vibration signal need to be extracted additionally, and the coal and gangue identification rate is possibly too low due to the characteristics with weak discrimination capability. Finally, a support vector machine and a BP neural network model used by the technology belong to a typical supervised learning model, and a large amount of manpower is consumed to label the coal and gangue signals during model training, so that the training cost is high.
In order to solve the problems that the coal discharge rate is low in the existing coal mining process, and a large amount of dust generated when scattered coal gangue is discharged causes harm to human bodies, the technology designs a coal gangue identification and automatic coal discharge control system. Firstly, a voiceprint sensor and an image sensor are installed at a coal caving port of a coal caving device, audio signals and video signals are collected, then a DSP (digital signal processor) is used for matching the audio signals with a preset sound frequency spectrum and carrying out digital image analysis on the video signals, and finally a control instruction is sent out according to a processed result, so that the electro-hydraulic control device realizes the control of caving coal. However, the background noise of the working face is extremely complex, so that the process of collecting high-quality coal gangue acoustic signals is difficult, and the signal analysis is not easy to realize. At the coal discharge port, a large amount of dust is generated in the falling process of coal and gangue, and the similarity between the coal and the gangue at the upper part is large, so that the resolution of a video signal is not high.
Disclosure of Invention
The invention aims to provide a coal and gangue identification method and a coal mine conveying system, which take vibration signals generated when coal and gangue fall on a rear conveyor as research objects, surround the characteristics and the requirements of a coal and gangue identification technology and take the improvement of coal and gangue identification accuracy as a core target.
In order to achieve the purpose, the coal gangue identification method provided by the invention comprises the following steps: collecting impact signals generated by coal falling onto a rear conveyor through a vibration acceleration sensor arranged on a rear conveyor body; carrying out spectrum analysis according to the impact signal to obtain characteristic frequency, constructing a characteristic threshold value through digital signal processing according to the characteristic frequency, and/or training a recognition model through a deep learning method; and analyzing the impact signal to be detected through the characteristic threshold and/or the identification model, and identifying and determining the coal or gangue on the rear conveyor body according to the analysis result.
In the coal gangue identification method, preferably, the obtaining of the characteristic frequency by performing spectrum analysis according to the impact signal further includes: carrying out spectrum analysis on an impact signal generated by coal to obtain a first impact frequency; carrying out frequency spectrum analysis on an impact signal generated by the waste rock on the rear conveyor to obtain a second impact frequency; and obtaining the characteristic frequency according to the comparison result between the first impact frequency and the second impact frequency.
In the above coal gangue identification method, preferably, the constructing a characteristic threshold value by digital signal processing according to the characteristic frequency includes: performing band-pass filtering on the characteristic frequency to obtain a characteristic frequency spectrum, performing inverse spectrum analysis on the characteristic frequency spectrum, and calculating an effective value of the characteristic frequency spectrum after inverse transformation; and constructing a characteristic threshold according to the effective value.
In the above coal gangue identification method, preferably, the training of the identification model by the deep learning method includes: the identification model is a hypersphere model described by depth support vector data; wherein the hypersphere model comprises: marking the impact signal as sample data; training a hypersphere model described by deep support vector data by using a deep learning method through the sample data to obtain a distance threshold of the hypersphere model; and identifying coal or gangue on the rear conveyor body according to the distance threshold.
In the above coal gangue identification method, preferably, the loss function of the hypersphere model during training includes:
in the above formula, xiN is the number of training samples, c is the hypersphere centre, lambda is the penalty parameter, phi (·; w) is the mapping function of Deep SVDD feature extractor, w ═{W1,…WLAnd is the network parameter of the feature extractor.
In the coal and gangue identification method, preferably, the constructing of the characteristic threshold value by digital signal processing according to the characteristic frequency and the training of the identification model by a deep learning method include: carrying out spectrum analysis on an impact signal generated by coal to obtain a characteristic spectrum; and carrying out band-pass filtering on the characteristic frequency spectrum according to the signal characteristics of the coal signal, and then training a deep self-coding model to obtain a recognition model.
In the coal gangue identification method, preferably, the loss function of the identification model during training includes:
in the above formula, m is the number of training samples, W and b are the weight and bias of DAE model, H (ω)(r)In order to input the data, the data is,
is the result of the reconstruction.
In the coal and gangue identification method, preferably, identifying and determining coal or gangue on the rear conveyor body according to the analysis result further includes: generating a control signal when the identification result is gangue; and stopping transmitting the coal gangue ores to the rear conveyor body according to the control signal.
The invention also provides a coal mine conveying system suitable for the coal and gangue identification method, and the system comprises a caving area, a coal discharge port, an output controller, a rear conveyor body, a vibration acceleration sensor and a processing module; the caving region is a region where the coal gangue ores are to be discharged; the output controller is used for opening or closing the coal discharge port according to the received control instruction; the coal discharge port is used for sliding the coal gangue ores accumulated in the caving area to the rear conveyor body; the vibration acceleration sensor is arranged on the rear conveyor body and used for collecting impact signals generated by coal gangue ores falling onto the rear conveyor; the processing module is used for identifying that the ore on the rear conveyor body is coal gangue ore according to the impact information, and when the ore on the rear conveyor body is coal gangue ore, a control instruction is generated to control the output controller to close the coal discharge port.
In the coal mine conveying system, preferably, the vibration acceleration sensor is a single-shaft piezoelectric acceleration sensor, and the single-shaft piezoelectric acceleration sensor is mounted on the rear conveyor body in a manner of a strong magnetic suction seat.
In the coal mine conveying system, preferably, the vibration acceleration sensor further comprises a power consumption unit, and the power consumption unit is used for controlling the vibration acceleration sensor to correspondingly start or close the acquisition of the impact signal when the output controller starts or closes the coal discharge port.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method.
The invention has the beneficial technical effects that: by installing the vibration acceleration sensor on the rear conveyor body, the collected vibration signals can directly reflect the specific state of the coal gangue on the top coal caving working face. On the basis, in order to meet the requirements of different fully mechanized caving working faces, the coal or gangue falling on the rear conveyor can be judged in real time, the coal caving action can be controlled according to the output result of the model, and the production efficiency of the coal mine is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a schematic flow chart of a coal gangue identification method according to an embodiment of the present invention;
fig. 2A is a schematic diagram illustrating a characteristic frequency obtaining process according to an embodiment of the present invention;
fig. 2B is a schematic diagram illustrating a process of constructing a feature threshold according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for constructing a hypersphere model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a process of constructing a recognition model according to an embodiment of the present invention;
fig. 5 is a schematic application flow diagram of a coal gangue identification method according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a coal mine transportation system according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, unless otherwise specified, the embodiments and features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Additionally, the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions and, although a logical order is illustrated in the flow charts, in some cases, the steps illustrated or described may be performed in an order different than here.
Referring to fig. 1, the method for identifying coal and gangue provided by the present invention specifically includes:
s101, acquiring impact signals generated by coal falling onto a rear conveyor through a vibration acceleration sensor arranged on a rear conveyor body;
s102, carrying out spectrum analysis according to the impact signal to obtain characteristic frequency, constructing a characteristic threshold value through digital signal processing according to the characteristic frequency, and/or training a recognition model through a deep learning method;
s103, analyzing the impact signal to be detected through the characteristic threshold and/or the identification model, and identifying and determining coal or gangue on the rear conveyor body according to an analysis result.
Specifically, in the actual work, vibration acceleration sensor still contains the signal collector, installs vibration acceleration sensor on back conveyer organism before the use in order to withdraw when the picture peg at the coal caving in-process, and coal and waste rock are on directly falling the back conveyer, and the state that the coal gangue whereabouts can directly be reflected to the coal gangue vibration signal of gathering this moment. And then, the installed vibration acceleration sensor is connected with a signal input end of a signal collector, and the signal collector can transmit the collected coal and gangue vibration signals to an upper computer for storage and analysis through network cable transmission. The hydraulic support for controlling the coal gangue to be discharged is convenient to follow, automatic coal discharging is achieved, wherein the coal gangue vibration signal collected for the first time can be obtained by manually controlling starting and stopping of the coal discharging action, the specific implementation mode is described in detail in the following embodiment, and detailed description is omitted here.
Referring to fig. 2A, in an embodiment of the present invention, obtaining the characteristic frequency according to the impulse signal by performing the spectrum analysis further includes:
s201, carrying out spectrum analysis on an impact signal generated by coal to obtain a first impact frequency;
s202, carrying out frequency spectrum analysis on an impact signal generated by the gangue on a rear conveyor to obtain a second impact frequency;
s203, the characteristic frequency is obtained according to the comparison result between the first impact frequency and the second impact frequency.
Further, referring to fig. 2B, the constructing the feature threshold according to the feature frequency by digital signal processing includes:
s204, performing band-pass filtering on the characteristic frequency to obtain a characteristic frequency spectrum, performing inverse spectrum analysis on the characteristic frequency spectrum, and calculating an effective value of the shock signal after inverse transformation;
s205, constructing a characteristic threshold according to the effective value.
Specifically, the coal and gangue vibration signals can be resampled and marked in actual work, for example, one-dimensional coal and gangue vibration signals stored by an upper computer are marked as a sample every 0.1s, then the coal and gangue vibration signals stored by the upper computer are marked according to manual field recording, the coal discharge signal is marked as 0, and the gangue discharge signal is marked as 1; then, performing coal and gangue identification by using a digital signal processing method; in the process of collecting the coal gangue signals, starting and stopping can occur in the coal caving process, and in the process, all data can be collected by the signal collector, so that signals with the amplitude value of 0 can exist in the data stored by the upper computer; however, only the impact signal has analytical significance, so that the impact signal of the coal gangue signal needs to be extracted first, and then the extracted impact signal needs to be subjected to spectrum analysis. Under the actual working condition, characteristic frequencies different from coal signals exist in the gangue signals, and the range of the characteristic frequencies is screened out and subjected to band-pass filtering; the filtered spectrum is then subjected to an inverse spectral analysis and an effective value of the inverse transformed signal is determined. Through the operation, a certain discrimination degree exists between the effective values of the coal signal and the gangue signal. Therefore, in the online coal and gangue identification stage, only one threshold value m needs to be set, if the effective value of the signal is greater than m, the sample is a coal signal, and otherwise, the sample is a gangue signal; once the coal and gangue state mark is changed from coal to gangue, the hydraulic support controller sends a 'stop coal discharge' control instruction to finish the coal discharge; therefore, the used digital signal processing method is more intuitive physically, and the coal signal and the gangue signal can be distinguished directly through the oscillogram of the signals. Of course, those skilled in the art may also use other time-frequency domain analysis and filtering operations to complete the above feature threshold construction and coal and gangue identification, which is not further limited by the present invention.
In an embodiment of the present invention, training the recognition model by the deep learning method includes:
the identification model is a hypersphere model described by depth support vector data; referring to fig. 3, the hypersphere model includes:
s301, marking the impact signal as sample data;
s302, training a hypersphere model described by deep support vector data by using a deep learning method through the sample data to obtain a distance threshold of the hypersphere model;
s303, identifying the coal or gangue on the rear conveyor body according to the distance threshold value.
In the above embodiment, the loss function of the hypersphere model during training includes:
in the above formula, xiN is the number of training samples, c is the hypersphere centre, lambda is the penalty parameter, phi (·; W) is the mapping function of Deep SVDD feature extractor, W ═ W { (W)1,…WLAnd is the network parameter of the feature extractor.
Specifically, when the Deep learning method is used for identifying the coal and gangue, a coal caving sample marked as 0 is selected as a training set to train a Deep support vector data description (Deep SVDD) hypersphere model, and the model obtains a decision rule by searching for the minimum hypersphere in a feature space which can contain coal signals. Through training, the Deep SVDD hypersphere can enclose all coal signals in the hypersphere, and exclude gangue signals outside the hypersphere. Therefore, a distance threshold value of 0 is set, the distance between the sample and the hypersphere is smaller than the threshold value, the output label of the model is 0, the corresponding sample is a coal discharge sample, when the distance is larger than the threshold value, the output label of the model is 1, and the corresponding sample is a gangue discharge sample. The target loss during Deep SVDD model training can be as follows:
in the above formula, xiN is the number of training samples, c is the hypersphere centre, lambda is the penalty parameter, phi (·; W) is the mapping function of Deep SVDD feature extractor, W ═ W { (W)1,…WLAnd is the network parameter of the feature extractor.
Therefore, after the training, the Deep SVDD model can accurately distinguish whether the sample is coal or gangue, and then the structure of the model and the corresponding network parameters are stored. In the on-line identification stage, the state mark corresponding to the signal sample can be obtained only by directly inputting the real-time vibration signal acquired by the signal acquisition device into the trained Deep SVDD model. And once the coal and gangue state output by the model is marked as gangue, the hydraulic support controller sends a 'stopping coal discharge' control instruction to finish the coal discharge. Therefore, only the original coal and gangue vibration signals are input into the model in actual use, the obtained model output is the coal and gangue state mark, extra operations such as feature extraction and feature selection are not needed, and the easiness in deployment is high. In addition, the Deep SVDD model belongs to a singular value detection model, namely, only one type of data is needed for training data, so that the data labeling cost can be reduced to a certain extent; other single-classification anomaly detection models can be adopted by those skilled in the art in practical use, such as a traditional SVDD model based on a kernel method, and the like, and the invention is not limited thereto.
Referring to fig. 4, in an embodiment of the present invention, the constructing the feature threshold value by digital signal processing according to the feature frequency and training the recognition model by a deep learning method includes:
s401, carrying out spectrum analysis on the impact signal generated by the coal to obtain a characteristic spectrum;
s402, performing band-pass filtering on the characteristic frequency spectrum according to the signal characteristics of the coal signal, and then training a deep self-coding model to obtain a recognition model.
In the above embodiment, the loss function of the recognition model during training includes:
in the above formula, m is the number of training samples, W and b are the weight and bias of DAE model, H (ω)(r)In order to input the data, the data is,
is the result of the reconstruction.
In consideration of the respective advantages of the real-time state recognition of the coal and gangue signals by the digital signal processing method and the real-time state recognition of the original data of the coal and gangue signals by the deep learning model, the deep learning model is further fused in the embodiment, namely the deep learning model is constructed on the basis of preprocessing the original coal and gangue vibration signals by the digital signal processing method, and the accuracy of the coal and gangue recognition is further improved. Specifically, in actual work, the flow of the embodiment is as follows:
firstly, extracting an impact signal of a coal gangue signal, carrying out spectrum analysis, carrying out band-pass filtering on a spectrum according to the signal characteristics of the coal gangue signal, and then training a deep self-encoding model (DAE) by using the spectrum of the coal signal subjected to band-pass filtering. The idea of DAE model training is to use the input data itself as a monitor to guide the neural network to learn a mapping relationship, thereby obtaining a reconstructed output. Therefore, the DAE model trained according to the coal discharge signal can basically reconstruct and restore the coal signal, but cannot reconstruct and restore the gangue signal, so that the reconstruction error of the gangue signal is large. The target loss during training of the DAE model is as follows:
wherein m is the number of training samples, W and b are the weight and bias of DAE model, H (omega)(r)In order to input the data, the data is,
is the result of the reconstruction.
In the stage of on-line coal and gangue identification, only the real-time vibration signal acquired by the signal acquisition device is directly input into the trained DAE model and a threshold value n is set, if the reconstruction error of the signal is less than n, the sample is a coal signal, otherwise, the sample is a gangue signal. And once the coal and gangue state mark is changed from coal to gangue, the hydraulic support controller sends a 'stop coal discharge' control instruction to finish the coal discharge. Of course, in practical work, other variants of the DAE model, such as denoising autoencoder, shrinkage autoencoder, sparse autoencoder, and variation autoencoder, can achieve the above effects, and those skilled in the art can select the setting according to practical needs, and the invention is not limited herein.
Therefore, the method and the device can combine the advantages of the digital signal processing method and the deep learning method, and the accuracy of coal and gangue identification is higher. Meanwhile, the DAE belongs to an unsupervised learning model, only coal signals are needed to be used as training data, training labels are not needed, and a large amount of data labeling work can be avoided.
In an embodiment of the present invention, identifying and determining coal or gangue on the rear transporter body according to the analysis result further includes: generating a control signal when the identification result is gangue; stopping transmitting the coal gangue ore to the rear conveyor body according to the control signal; therefore, the purposes of automatic identification and control are achieved. In order to more clearly understand the specific implementation flow of the coal gangue identification method provided by the present invention, the following refers to fig. 5 to collectively describe the above embodiments:
firstly, mounting a vibration acceleration sensor and a signal collecting device on a rear conveyor, wherein the signal collecting device is used for collecting vibration signals collected by the vibration acceleration sensor; at the moment, the coal and gangue transmission is manually started, the upper computer stores the coal and gangue vibration signals collected by the signal collecting device, then the coal and gangue vibration signals are resampled and marked, and the one-dimensional coal and gangue vibration signals stored by the upper computer can be recorded as a sample every 0.1 s; and then marking the coal and gangue vibration signals stored by the upper computer according to manual field records, wherein the coal discharge signal is marked as 0, and the gangue discharge signal is marked as 1.
Then, an identification link is carried out, and the invention mainly provides 3 modes, which are as follows:
the first mode is as follows: and (4) performing coal gangue identification by using a digital signal processing method. In the process of collecting coal gangue signals, the coal caving process can have two conditions of starting and stopping, and in the process, all data can be collected by the signal collector, so that signals with the amplitude value of 0 can exist in the data stored by the upper computer. However, only the impact signal has analytical significance, so that the impact signal of the coal and gangue signal needs to be extracted firstly; the extracted impulse signal is then subjected to a spectral analysis. Under the actual working condition, characteristic frequencies different from coal signals exist in the gangue signals, and the range of the characteristic frequencies is screened out and subjected to band-pass filtering; the filtered spectrum is then subjected to an inverse spectral analysis and an effective value of the inverse transformed signal is determined. Through the operation, a certain discrimination degree exists between the effective values of the coal signal and the gangue signal. Therefore, in the online coal and gangue identification stage, only one threshold value m needs to be set, if the effective value of the signal is greater than m, the sample is a coal signal, and otherwise, the sample is a gangue signal. And once the coal and gangue state mark is changed from coal to gangue, the hydraulic support controller sends a 'stop coal discharge' control instruction to finish the coal discharge.
And a second mode: and performing coal and gangue identification by using a deep learning method. The sample of the coal caving labeled 0 is selected as a training set to train a Deep support vector data description (Deep SVDD) hypersphere model, which finds the minimum hypersphere in the feature space that can contain the coal signal, to obtain the decision rule. Through training, the Deep SVDD hypersphere can enclose all coal signals in the hypersphere, and exclude gangue signals outside the hypersphere. Therefore, a distance threshold value of 0 is set, the distance between the sample and the hypersphere is smaller than the threshold value, the output label of the model is 0, the corresponding sample is a coal discharge sample, when the distance is larger than the threshold value, the output label of the model is 1, and the corresponding sample is a gangue discharge sample. After training, the Deep SVDD model can accurately distinguish whether the sample is coal or gangue, and then the structure of the model and the corresponding network parameters are stored. In the on-line identification stage, the state mark corresponding to the signal sample can be obtained only by directly inputting the real-time vibration signal acquired by the signal acquisition device into the trained Deep SVDD model. And once the coal and gangue state output by the model is marked as gangue, the hydraulic support controller sends a 'stopping coal discharge' control instruction to finish the coal discharge.
And a third mode: firstly, extracting an impact signal of a coal gangue signal, carrying out spectrum analysis, carrying out band-pass filtering on a spectrum according to the signal characteristics of the coal gangue signal, and then training a deep self-encoding model (DAE) by using the spectrum of the coal signal subjected to band-pass filtering. The idea of DAE model training is to use the input data itself as a monitor to guide the neural network to learn a mapping relationship, thereby obtaining a reconstructed output. Therefore, the DAE model trained according to the coal discharge signal can basically reconstruct and restore the coal signal, but cannot reconstruct and restore the gangue signal, so that the reconstruction error of the gangue signal is large. In the stage of on-line coal and gangue identification, only the real-time vibration signal acquired by the signal acquisition device is directly input into the trained DAE model and a threshold value n is set, if the reconstruction error of the signal is less than n, the sample is a coal signal, otherwise, the sample is a gangue signal. And once the coal and gangue state mark is changed from coal to gangue, the hydraulic support controller sends a 'stop coal discharge' control instruction to finish the coal discharge.
In practical operation, the selection of the above mode can be set according to actual needs, and those skilled in the art can select the setting according to actual needs, and the present invention is not limited herein.
Referring to fig. 6, the invention further provides a coal mine transportation system suitable for the coal and gangue identification method, where the system includes a caving area, a coal discharge port, an output controller, a rear conveyor body, a vibration acceleration sensor, and a processing module; the caving region is a region where the coal gangue ores are to be discharged; the output controller is used for opening or closing the coal discharge port according to the received control instruction; the coal discharge port is used for sliding the coal gangue ores stored in the first storage module to the rear conveyor body; the vibration acceleration sensor is arranged on the rear conveyor body and used for collecting impact signals generated by coal gangue ores falling onto the rear conveyor; the processing module is used for identifying that the ore on the rear conveyor body is coal gangue ore according to the impact information, and when the ore on the rear conveyor body is coal gangue ore, a control instruction is generated to control the output controller to close the coal discharge port.
In the above embodiment, the vibration acceleration sensor is a single-axis piezoelectric acceleration sensor, and the single-axis piezoelectric acceleration sensor is mounted on the rear transporter body in a manner of a strong magnetic suction seat. Further, the vibration acceleration sensor can further comprise a power consumption unit, and the power consumption unit is used for controlling the vibration acceleration sensor to correspondingly start or close impact signal acquisition when the output controller starts or closes the coal discharge port. In actual work, the reason for installing the vibration acceleration sensor on the rear conveyor body is that coal is always stacked on the upper part of the tail beam in the actual working condition of top coal caving, and the coal and gangue cannot directly fall on the tail beam but directly fall on the rear conveyor in the falling process, so that the vibration acceleration sensor is installed on the rear conveyor body, and the coal and gangue signals collected by the vibration sensor can most directly reflect the falling state of the coal and gangue. The power consumption unit can be an existing enabling switch, the enabling switch can control starting and stopping of vibration signal acquisition, and the module enters a low power consumption mode in a stopping stage of vibration signal acquisition; the enable switch can be implemented by the prior art, and the invention is not described in detail herein.
The invention has the beneficial technical effects that: by installing the vibration acceleration sensor on the rear conveyor body, the collected vibration signals can directly reflect the specific state of the coal gangue on the top coal caving working face. On the basis, in order to meet the requirements of different fully mechanized caving working faces, the coal or gangue falling on the rear conveyor can be judged in real time, the coal caving action can be controlled according to the output result of the model, and the production efficiency of the coal mine is improved.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method.
As shown in fig. 7, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in fig. 7; furthermore, the electronic device 600 may also comprise components not shown in fig. 7, which may be referred to in the prior art.
As shown in fig. 7, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (13)
1. A coal and gangue identification method is characterized by comprising the following steps:
collecting impact signals generated by coal falling onto a rear conveyor through a vibration acceleration sensor arranged on a rear conveyor body;
carrying out spectrum analysis according to the impact signal to obtain characteristic frequency, constructing a characteristic threshold value through digital signal processing according to the characteristic frequency, and/or training a recognition model through a deep learning method;
and analyzing the impact signal to be detected through the characteristic threshold and/or the identification model, and identifying and determining the coal or gangue on the rear conveyor body according to the analysis result.
2. The method of claim 1, wherein the obtaining the characteristic frequency by performing the spectral analysis on the impulse signal further comprises:
carrying out spectrum analysis on an impact signal generated by coal to obtain a first impact frequency;
carrying out frequency spectrum analysis on an impact signal generated by the waste rock on the rear conveyor to obtain a second impact frequency;
and obtaining the characteristic frequency according to the comparison result between the first impact frequency and the second impact frequency.
3. The method of claim 2, wherein the constructing the characteristic threshold value through digital signal processing according to the characteristic frequency comprises:
performing band-pass filtering on the characteristic frequency to obtain a characteristic frequency spectrum, performing inverse spectrum analysis on the characteristic frequency spectrum, and calculating an effective value of the characteristic frequency spectrum after inverse transformation;
and constructing a characteristic threshold according to the effective value.
4. The coal gangue identification method of claim 1, wherein training the identification model by the deep learning method comprises:
the identification model is a hypersphere model described by depth support vector data;
wherein the hypersphere model comprises: marking the impact signal as sample data; training a hypersphere model described by deep support vector data by using a deep learning method through the sample data to obtain a distance threshold of the hypersphere model; and identifying coal or gangue on the rear conveyor body according to the distance threshold.
5. The coal gangue identification method of claim 4, wherein the loss function of the hypersphere model during training comprises:
in the above formula, xiN is the number of training samples, c is the hypersphere centre, lambda is the penalty parameter, phi (·; W) is the mapping function of Deep SVDD feature extractor, W ═ W { (W)1，...WLAnd is the network parameter of the feature extractor.
6. The coal gangue identification method of claim 1, wherein the constructing of the feature threshold value through digital signal processing and the training of the identification model through a deep learning method according to the feature frequency comprises:
carrying out spectrum analysis on an impact signal generated by coal to obtain a characteristic spectrum;
and carrying out band-pass filtering on the characteristic frequency spectrum according to the signal characteristics of the coal signal, and then training a deep self-coding model to obtain a recognition model.
7. The coal gangue identification method of claim 6, wherein the loss function of the identification model during training comprises:
in the above formula, m is the number of training samples, W and b are the weight and bias of DAF model, H (ω)(r)In order to input the data, the data is,
is the result of the reconstruction.
8. The method of claim 1, wherein identifying and determining coal or gangue on the rear conveyor body according to the analysis result further comprises:
generating a control signal when the identification result is gangue;
and stopping transmitting the coal gangue ores to the rear conveyor body according to the control signal.
9. A coal mine transportation system suitable for the coal gangue identification method of any one of claims 1 to 8, wherein the system comprises a caving area, a coal discharge port, an output controller, a rear conveyor body, a vibration acceleration sensor and a processing module;
the caving region is a region where the coal gangue ores are to be discharged;
the output controller is used for opening or closing the coal discharge port according to the received control instruction;
the coal discharge port is used for sliding the coal gangue ores accumulated in the caving area to the rear conveyor body;
the vibration acceleration sensor is arranged on the rear conveyor body and used for collecting impact signals generated by coal gangue ores falling onto the rear conveyor;
the processing module is used for identifying that the ore on the rear conveyor body is coal gangue ore according to the impact signal, and when the ore on the rear conveyor body is coal gangue ore, a control instruction is generated to control the output controller to close the coal discharge port.
10. A coal mine conveyor system as in claim 9 wherein the vibration acceleration sensor is a single axis piezoelectric acceleration sensor mounted on the rear conveyor body by means of a strong magnetic suction mount.
11. The coal mine conveying system of claim 9, wherein the vibration acceleration sensor further comprises a power consumption unit, and the power consumption unit is used for controlling the vibration acceleration sensor to correspondingly turn on or off impact signal acquisition when the output controller turns on or off the coal discharge port.
12. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 8 when executing the computer program.
13. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 8 by a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111393330.8A CN114104666A (en) | 2021-11-23 | 2021-11-23 | Coal and gangue identification method and coal mine conveying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111393330.8A CN114104666A (en) | 2021-11-23 | 2021-11-23 | Coal and gangue identification method and coal mine conveying system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114104666A true CN114104666A (en) | 2022-03-01 |
Family
ID=80439832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111393330.8A Pending CN114104666A (en) | 2021-11-23 | 2021-11-23 | Coal and gangue identification method and coal mine conveying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114104666A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115795369A (en) * | 2023-02-09 | 2023-03-14 | 西安华创马科智能控制系统有限公司 | Coal-rock interface identification method and device |
Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06274633A (en) * | 1993-03-22 | 1994-09-30 | Nippon Telegr & Teleph Corp <Ntt> | Device and method for generating feature detector |
| WO2007016936A1 (en) * | 2005-07-29 | 2007-02-15 | Telecom Italia, S.P.A. | Automatic biometric identification based on face recognition and support vector machines |
| CN101634842A (en) * | 2009-03-05 | 2010-01-27 | 中国矿业大学(北京) | Control system for identifying coal and gangue and automatic coal discharge |
| CN101798927A (en) * | 2010-04-01 | 2010-08-11 | 中国矿业大学 | Near infrared spectral recognizing coal gangue and gangue content control method |
| CN102467654A (en) * | 2010-11-03 | 2012-05-23 | 西安电子科技大学 | Structural modal parameter identification method |
| CN103466284A (en) * | 2013-09-16 | 2013-12-25 | 中国神华能源股份有限公司 | Belt conveyor centralized control method and system |
| CN103558029A (en) * | 2013-10-22 | 2014-02-05 | 重庆建设摩托车股份有限公司 | Abnormal engine sound fault on-line diagnostic system and diagnostic method |
| CN104112143A (en) * | 2014-07-23 | 2014-10-22 | 大连民族学院 | Weighted hyper-sphere support vector machine algorithm based image classification method |
| CN106156950A (en) * | 2016-07-06 | 2016-11-23 | 燕山大学 | A kind of active distribution network economical operation evaluation methodology based on Hypersphere Support Vector Machine |
| CN205743956U (en) * | 2016-07-07 | 2016-11-30 | 中国矿业大学(北京) | A kind of fully mechanized coal face puts coal automated system |
| CN106362957A (en) * | 2016-09-14 | 2017-02-01 | 西安科技大学 | Coal-gangue separation system and separation method |
| CN107676095A (en) * | 2017-11-01 | 2018-02-09 | 天地科技股份有限公司 | High seam top coal caving device and method |
| CN107824477A (en) * | 2017-11-01 | 2018-03-23 | 天地科技股份有限公司 | Top-coal caving face bastard coal automatic sorting method on the spot |
| EP3346419A1 (en) * | 2016-08-30 | 2018-07-11 | Soochow University | Feature extraction and classification method based on support vector data description and system thereof |
| CN110135468A (en) * | 2019-04-24 | 2019-08-16 | 中国矿业大学(北京) | A kind of recognition methods of gangue |
| WO2019174534A1 (en) * | 2018-03-14 | 2019-09-19 | 山东科技大学 | Coal gangue interface recognition test system for top coal caving |
| CN110706720A (en) * | 2019-08-16 | 2020-01-17 | 广东省智能制造研究所 | Acoustic anomaly detection method for end-to-end unsupervised deep support network |
| CN111266304A (en) * | 2019-12-02 | 2020-06-12 | 唐山因泰智能科技发展有限公司 | Coal briquette identification, detection and sorting system |
| CN111337447A (en) * | 2020-03-20 | 2020-06-26 | 中国矿业大学 | Coal and gangue bionic identification system and method |
| WO2020220416A1 (en) * | 2019-04-28 | 2020-11-05 | 山东科技大学 | Deep learning-based micro-seismic signal classification and identification method |
| CN112328590A (en) * | 2020-12-01 | 2021-02-05 | 西安交通大学 | Deep cleaning method for operation data of thermal equipment |
| CN112465063A (en) * | 2020-12-11 | 2021-03-09 | 中国矿业大学 | Coal gangue identification method in top coal caving process based on multi-sensor information fusion |
| CN112668519A (en) * | 2020-12-31 | 2021-04-16 | 声耕智能科技(西安)研究院有限公司 | Abnormal face recognition living body detection method and system based on MCCAE network and Deep SVDD network |
| CN112893159A (en) * | 2021-01-14 | 2021-06-04 | 陕西陕煤曹家滩矿业有限公司 | Coal gangue sorting method based on image recognition |
| CN113269725A (en) * | 2021-04-28 | 2021-08-17 | 安徽理工大学 | Coal gangue rapid detection method based on imaging technology and deep learning |
| CN113283391A (en) * | 2021-06-28 | 2021-08-20 | 西安科技大学 | Method for identifying coal and gangue under complex working conditions in fully mechanized caving mining caving process |
| CN113505356A (en) * | 2021-07-13 | 2021-10-15 | 清华大学 | Single-class classifier, identification method, medium and computing device for identifying user identity |
-
2021
- 2021-11-23 CN CN202111393330.8A patent/CN114104666A/en active Pending
Patent Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06274633A (en) * | 1993-03-22 | 1994-09-30 | Nippon Telegr & Teleph Corp <Ntt> | Device and method for generating feature detector |
| WO2007016936A1 (en) * | 2005-07-29 | 2007-02-15 | Telecom Italia, S.P.A. | Automatic biometric identification based on face recognition and support vector machines |
| CN101634842A (en) * | 2009-03-05 | 2010-01-27 | 中国矿业大学(北京) | Control system for identifying coal and gangue and automatic coal discharge |
| CN101798927A (en) * | 2010-04-01 | 2010-08-11 | 中国矿业大学 | Near infrared spectral recognizing coal gangue and gangue content control method |
| CN102467654A (en) * | 2010-11-03 | 2012-05-23 | 西安电子科技大学 | Structural modal parameter identification method |
| CN103466284A (en) * | 2013-09-16 | 2013-12-25 | 中国神华能源股份有限公司 | Belt conveyor centralized control method and system |
| CN103558029A (en) * | 2013-10-22 | 2014-02-05 | 重庆建设摩托车股份有限公司 | Abnormal engine sound fault on-line diagnostic system and diagnostic method |
| CN104112143A (en) * | 2014-07-23 | 2014-10-22 | 大连民族学院 | Weighted hyper-sphere support vector machine algorithm based image classification method |
| CN106156950A (en) * | 2016-07-06 | 2016-11-23 | 燕山大学 | A kind of active distribution network economical operation evaluation methodology based on Hypersphere Support Vector Machine |
| CN205743956U (en) * | 2016-07-07 | 2016-11-30 | 中国矿业大学(北京) | A kind of fully mechanized coal face puts coal automated system |
| EP3346419A1 (en) * | 2016-08-30 | 2018-07-11 | Soochow University | Feature extraction and classification method based on support vector data description and system thereof |
| CN106362957A (en) * | 2016-09-14 | 2017-02-01 | 西安科技大学 | Coal-gangue separation system and separation method |
| CN107824477A (en) * | 2017-11-01 | 2018-03-23 | 天地科技股份有限公司 | Top-coal caving face bastard coal automatic sorting method on the spot |
| CN107676095A (en) * | 2017-11-01 | 2018-02-09 | 天地科技股份有限公司 | High seam top coal caving device and method |
| WO2019174534A1 (en) * | 2018-03-14 | 2019-09-19 | 山东科技大学 | Coal gangue interface recognition test system for top coal caving |
| CN110135468A (en) * | 2019-04-24 | 2019-08-16 | 中国矿业大学(北京) | A kind of recognition methods of gangue |
| WO2020220416A1 (en) * | 2019-04-28 | 2020-11-05 | 山东科技大学 | Deep learning-based micro-seismic signal classification and identification method |
| CN110706720A (en) * | 2019-08-16 | 2020-01-17 | 广东省智能制造研究所 | Acoustic anomaly detection method for end-to-end unsupervised deep support network |
| CN111266304A (en) * | 2019-12-02 | 2020-06-12 | 唐山因泰智能科技发展有限公司 | Coal briquette identification, detection and sorting system |
| CN111337447A (en) * | 2020-03-20 | 2020-06-26 | 中国矿业大学 | Coal and gangue bionic identification system and method |
| CN112328590A (en) * | 2020-12-01 | 2021-02-05 | 西安交通大学 | Deep cleaning method for operation data of thermal equipment |
| CN112465063A (en) * | 2020-12-11 | 2021-03-09 | 中国矿业大学 | Coal gangue identification method in top coal caving process based on multi-sensor information fusion |
| CN112668519A (en) * | 2020-12-31 | 2021-04-16 | 声耕智能科技(西安)研究院有限公司 | Abnormal face recognition living body detection method and system based on MCCAE network and Deep SVDD network |
| CN112893159A (en) * | 2021-01-14 | 2021-06-04 | 陕西陕煤曹家滩矿业有限公司 | Coal gangue sorting method based on image recognition |
| CN113269725A (en) * | 2021-04-28 | 2021-08-17 | 安徽理工大学 | Coal gangue rapid detection method based on imaging technology and deep learning |
| CN113283391A (en) * | 2021-06-28 | 2021-08-20 | 西安科技大学 | Method for identifying coal and gangue under complex working conditions in fully mechanized caving mining caving process |
| CN113505356A (en) * | 2021-07-13 | 2021-10-15 | 清华大学 | Single-class classifier, identification method, medium and computing device for identifying user identity |
Non-Patent Citations (4)
| Title |
|---|
| 张铭钧等: "《水下机器人故障诊断理论与技术》", vol. 1, 31 January 2017, 哈尔滨大学出版社, pages: 119 - 120 * |
| 王国法: "《放顶煤液压支架与综采放顶煤技术》", vol. 1, 31 July 2010, 煤炭工业出版社, pages: 306 * |
| 郜压松等: "《基于深度学习的煤矸石识别技术与实现》", 《煤炭科学技术》, vol. 49, no. 12, pages 202 - 108 * |
| 雷世威等: "《基于改进YOLOv3的煤矸识别方法研究》", 《矿业安全与环保》, vol. 48, no. 03, 30 June 2021 (2021-06-30), pages 50 - 55 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115795369A (en) * | 2023-02-09 | 2023-03-14 | 西安华创马科智能控制系统有限公司 | Coal-rock interface identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108335694B (en) | Far-field environment noise processing method, device, equipment and storage medium | |
| CN101110067B (en) | Intelligent analytical method and system for blasting operation | |
| US20210148214A1 (en) | Systems, apparatuses, and methods for determining rock-coal transition with a drilling machine | |
| Sherafat et al. | Automated activity recognition of construction equipment using a data fusion approach | |
| CN105723458A (en) | Dynamic threshold methods, systems, computer readable media, and program code for filtering noise and restoring attenuated high-frequency components of acoustic signals | |
| CN106328130A (en) | Robot voice addressed rotation system and method | |
| CN114104666A (en) | Coal and gangue identification method and coal mine conveying system | |
| JP5867153B2 (en) | Traveling lane detection device, traveling lane detection method, and program | |
| CN108401427A (en) | A kind of vehicle-surroundings environmental analysis method, apparatus and mobile unit | |
| CN104380143A (en) | Systems and methods for processing geophysical data | |
| CN101551467A (en) | Automatic first break picking method based on edge detection | |
| CN102879813A (en) | Method and device for automatically picking up time of arrival of micro earthquake signal | |
| CN115795369B (en) | Coal-rock interface identification method and device | |
| CN106643541A (en) | Method and device for management and analysis of real-time monitoring data of bridge | |
| CN114692273A (en) | TBM (tunnel boring machine) -oriented construction tunnel geological dictionary establishing method and system | |
| CN111653271B (en) | Sample data acquisition and model training method and device and computer equipment | |
| CN113539262B (en) | Sound enhancement and recording method and system for voice control of electric door | |
| CN111382631B (en) | Identification method, identification device, terminal, server and storage medium | |
| CN113705334A (en) | Method and device for supervising engineering muck truck, vehicle-mounted terminal and vehicle | |
| Deowan et al. | A warning and detection system for elephant intrusions utilizing signal processing and iot | |
| JP6059932B2 (en) | Travel speed management vehicle-mounted device | |
| CN114254685A (en) | Training method and device of sound detection model and detection method of sound event | |
| CN205721843U (en) | A kind of automatic recognition system of vehicle VIN code | |
| CN112363225B (en) | Transverse wave micro-logging interpretation method and device | |
| CN117189251A (en) | Prediction method for shield interface of coal mine tunnel |
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 |