CN117189251A - Prediction method for shield interface of coal mine tunnel - Google Patents
Prediction method for shield interface of coal mine tunnel Download PDFInfo
- Publication number
- CN117189251A CN117189251A CN202311085497.7A CN202311085497A CN117189251A CN 117189251 A CN117189251 A CN 117189251A CN 202311085497 A CN202311085497 A CN 202311085497A CN 117189251 A CN117189251 A CN 117189251A
- Authority
- CN
- China
- Prior art keywords
- interface
- shield
- acoustic
- rock
- prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 82
- 239000003245 coal Substances 0.000 title claims abstract description 48
- 239000011435 rock Substances 0.000 claims abstract description 104
- 230000005641 tunneling Effects 0.000 claims abstract description 58
- 230000008569 process Effects 0.000 claims abstract description 48
- 238000009826 distribution Methods 0.000 claims description 62
- 239000002893 slag Substances 0.000 claims description 38
- 238000001228 spectrum Methods 0.000 claims description 38
- 238000005070 sampling Methods 0.000 claims description 10
- 238000006467 substitution reaction Methods 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract 1
- 238000010521 absorption reaction Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000004873 anchoring Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application relates to the field of tunneling, and discloses a prediction method of a coal mine tunnel shield interface, which comprises the following steps: the method comprises the steps of obtaining preset background noise according to working parameters of a shield machine and historical shield acoustic data, removing background of an interface acoustic signal based on a characteristic signal of the background noise, obtaining the interface acoustic signal, inputting a prediction network based on the interface acoustic signal and a parameter stage of the shield machine, obtaining information of a prediction interface, obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine, and determining the type of the interface based on the difference between the vibration information and actual measurement vibration information, wherein the historical shield acoustic data is obtained based on tunneling data of a rock tunnel. The application solves the problem that the tunneling process cannot be monitored because the surrounding rock attribute under the mine is complex by acquiring the relevance of the acoustic signal and the interface data.
Description
Technical Field
The application relates to the field of tunnel tunneling, in particular to a prediction method for a shield interface of a coal mine tunnel.
Background
At present, coal mine roadway tunneling modes mainly comprise a comprehensive tunneling method, a drilling and blasting method and a continuous miner method (only suitable for coal roadway tunneling). The tunneling methods are easy to solve the problems of unbalanced tunneling, anchoring and transportation in actual construction.
Aiming at the situation, some coal mines adopt shield tunneling systems, so that the tunneling efficiency of the coal mine rock roadway is greatly improved. The equipment mainly used in the shield tunneling system is a shield machine and is mainly used for tunneling tunnels. The modern shield machine has higher technological content, integrates a plurality of technologies such as light, machine, electricity, liquid, sensors and the like, can realize the functions of cutting and conveying rock and soil bodies, supporting forming roadways and the like, and has higher overall reliability and safety. In the conventional tunneling process, the information of the interface can be obtained through approaches such as a pixel, mechanical vibration, ultrasonic waves, images, a radar and the like, but the method is difficult to apply to a shield tunneling machine.
Disclosure of Invention
The application aims to overcome one or more of the prior technical problems and provide a prediction method for a shield interface of a coal mine tunnel.
In order to achieve the above purpose, the method for predicting the shield interface of the coal mine tunnel provided by the application comprises the following steps:
acquiring preset back noise according to working parameters of the shield machine and historical shield acoustic data;
removing the back of the interface acoustic signal based on the characteristic signal of the background noise to obtain the interface acoustic signal;
inputting a prediction network based on the interface acoustic signals and the parameter stage of the shield machine to obtain information of a prediction interface;
obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine;
determining the type of the interface based on the difference between the vibration information and the measured vibration information;
the historical shield acoustic data is acquired based on tunneling data of the rock tunnel.
According to one aspect of the application, the vibration distribution difference of the interface is obtained according to the difference of the vibration information and the actually measured vibration information in frequency and energy, and the rock type corresponding to the frequency spectrum distribution is determined based on the vibration distribution difference and the information of the predicted interface;
the composition of the predicted interface is adjusted based on the type of rock.
According to one aspect of the application, rock slag in a chute at the cutter head position is obtained, the formation time of the rock slag is estimated according to the speed of a conveyor belt, and the working parameters of the shield machine are obtained according to the travel time of the rock slag;
obtaining color distribution, size distribution and edge distribution of slag in an image according to a sampling image of the rock slag;
clustering slag based on color distribution, size distribution or edge distribution of the slag, and classifying shield acoustic data based on clustering results;
classifying the classification result by using a KNN model to obtain association relations of acoustic signals under working parameters of different shield machines;
and obtaining a classification result with the maximum approximation degree as rock classification according to the working parameters of the shield tunneling machine and the characteristics of the acquired acoustic signals.
According to one aspect of the application, an acoustic characteristic frequency range is determined from an energy spectrum distribution of an acquired acoustic signal;
constructing an acoustic working condition dictionary based on the acoustic characteristic frequency range, wherein keys of the acoustic working condition dictionary are working parameters of the shield machine, and values of the acoustic working condition dictionary are acoustic characteristic frequencies;
and constructing a rock characteristic dictionary of the classification result and the rock characteristic, wherein the keys of the rock characteristic dictionary are acoustic working condition dictionaries, and the values of the rock characteristic dictionary are rock characteristics.
According to one aspect of the application, the proportion of each type of rock is obtained according to the information of the prediction interface, acoustic signals are fitted based on the proportion of each type of rock and the working parameters, and when fitting is performed, adjacent data are used for linear fitting to missing data to obtain a substitution value;
the vibration information is acquired based on a vibration characteristic network, and the input of the vibration characteristic network comprises information of interface characteristics and working parameters of the shield machine.
According to one aspect of the application, noise before a shield is used as an environment background to remove environmental noise in the collected acoustic signals, and sound collected at a working part of the shield is used as the background to remove noise of a working part in the collected acoustic signals, so that an interface acoustic signal is obtained; in the process of removing the back, noise is removed by adopting a characteristic spectrum mode.
According to one aspect of the application, the noise of the environment noise and the noise of the pushing part of the shield tunneling machine cutterhead are respectively obtained, the characteristic peak is determined, the least square method is used for fitting the energy of each frequency interval, the overall contribution degree of the environment noise and the pushing part to the acoustic signal is set to be 1, and the noise which can be identified according to the characteristic frequency is removed from the collected acoustic signal through optimizing and is used as an interface acoustic signal.
According to one aspect of the application, the predictive network is based on a deep neural network, the input of which comprises the interface acoustic signal and the operating parameters, and the output of which further comprises the spectral distribution of the interface acoustic signal.
In order to achieve the above purpose, the present application provides a prediction system for a shield interface of a coal mine tunnel, comprising:
the back bottom noise acquisition module: acquiring preset back noise according to working parameters of the shield machine and historical shield acoustic data;
interface acoustic signal acquisition module: removing the back of the interface acoustic signal based on the characteristic signal of the background noise to obtain the interface acoustic signal;
the prediction interface information acquisition module: inputting a prediction network based on the interface acoustic signals and the parameter stage of the shield machine to obtain information of a prediction interface;
vibration information acquisition module: obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine;
an interface type determining module: determining the type of the interface based on the difference between the vibration information and the measured vibration information;
the historical shield acoustic data is acquired based on tunneling data of the rock tunnel.
Based on the above, the application has the beneficial effects that: the application solves the problem that the tunneling process cannot be monitored because the surrounding rock attribute under the mine is complex by acquiring the relevance of the acoustic signal and the interface data.
Drawings
FIG. 1 is a flow chart of a method for predicting a shield interface of a coal mine tunnel;
FIG. 2 is a flow chart of a prediction system for a shield interface of a coal mine tunnel of the present application.
Detailed Description
The present disclosure will now be discussed with reference to exemplary embodiments, it being understood that the embodiments discussed are merely for the purpose of enabling those of ordinary skill in the art to better understand and thus practice the present disclosure and do not imply any limitation to the scope of the present disclosure.
As used herein, the term "comprising" and variants thereof are to be interpreted as meaning "including but not limited to" open-ended terms. The terms "based on" and "based at least in part on" are to be construed as "at least one embodiment.
Fig. 1 is a flowchart of a method for predicting a coal mine tunnel shield interface according to an embodiment of the present application, and as shown in fig. 1, the method for predicting a coal mine tunnel shield interface includes:
in order to achieve the above purpose, the method for predicting the shield interface of the coal mine tunnel provided by the application comprises the following steps:
acquiring preset back noise according to working parameters of the shield machine and historical shield acoustic data;
removing the back of the interface acoustic signal based on the characteristic signal of the background noise to obtain the interface acoustic signal;
inputting a prediction network based on the interface acoustic signals and the parameter stage of the shield machine to obtain information of a prediction interface;
obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine;
determining the type of the interface based on the difference between the vibration information and the measured vibration information;
the historical shield acoustic data is acquired based on tunneling data of the rock tunnel.
According to one embodiment of the application, the vibration distribution difference of the interface is obtained according to the difference of the vibration information and the actually measured vibration information in frequency and energy, and the rock type corresponding to the frequency spectrum distribution is determined based on the vibration distribution difference and the information of the predicted interface;
the composition of the predicted interface is adjusted based on the type of rock.
According to one embodiment of the application, rock slag in a chute at the cutter head position is obtained, the formation time of the rock slag is estimated according to the speed of a conveyor belt, and the working parameters of the shield machine are obtained according to the travel time of the rock slag;
obtaining color distribution, size distribution and edge distribution of slag in an image according to a sampling image of the rock slag;
clustering slag based on color distribution, size distribution or edge distribution of the slag, and classifying shield acoustic data based on clustering results;
classifying the classification result by using a KNN model to obtain association relations of acoustic signals under working parameters of different shield machines;
and obtaining a classification result with the maximum approximation degree as rock classification according to the working parameters of the shield tunneling machine and the characteristics of the acquired acoustic signals.
According to one embodiment of the application, the characteristic frequency range of the acoustics is determined according to the energy spectrum distribution of the collected acoustic signals;
constructing an acoustic working condition dictionary based on the acoustic characteristic frequency range, wherein keys of the acoustic working condition dictionary are working parameters of the shield machine, and values of the acoustic working condition dictionary are acoustic characteristic frequencies;
and constructing a rock characteristic dictionary of the classification result and the rock characteristic, wherein the keys of the rock characteristic dictionary are acoustic working condition dictionaries, and the values of the rock characteristic dictionary are rock characteristics.
According to one embodiment of the application, the proportion of each type of rock is obtained according to the information of the prediction interface, the acoustic signals are fitted based on the proportion of each type of rock and the working parameters, and when the acoustic signals are fitted, adjacent data are used for linear fitting to missing data to obtain a substitution value;
the vibration information is acquired based on a vibration characteristic network, and the input of the vibration characteristic network comprises information of interface characteristics and working parameters of the shield machine.
According to one embodiment of the application, noise before the shield is used as an environment background to remove the environment noise in the collected acoustic signals, and sound collected at a working part of the shield is used as the background to remove the noise of a working part in the collected acoustic signals, so that an interface acoustic signal is obtained; in the process of removing the back, noise is removed by adopting a characteristic spectrum mode.
According to one embodiment of the application, the noise of the environment noise and the noise of the pushing part of the shield tunneling machine cutterhead are respectively obtained, the characteristic peak is determined, the energy of each frequency interval is fitted by using a least square method, the overall contribution degree of the environment noise and the pushing part to the acoustic signal is set to be 1, and the noise which can be identified according to the characteristic frequency is removed from the collected acoustic signal through optimizing to serve as an interface acoustic signal.
According to one embodiment of the application, the prediction network is based on a deep neural network, the input of which comprises the interface acoustic signal and the operating parameters, and the output of which further comprises the spectral distribution of the interface acoustic signal.
According to one embodiment of the application, the nature of the interface is important to the operation of the coal mine tunnelling process. Therefore, the identification of the coal rock slime type is always a difficult problem to be solved by researchers at home and abroad. However, unlike ordinary hard rock tunneling, surrounding rock under the mine has complex properties, numerous operating parameters affecting the tunneling characteristics of the TBM, and the problem that the tunneling process cannot be monitored in the tunneling process exists. In the tunneling process of a TBM on a coal mine tunnel, common TBM usable parameters comprise a pushing speed, an operation parameter, collected data, a digging diameter, a cutter type, cutter driving power, cutter rotating speed, pushing force and a pushing stroke, and the form of a tunneling surface is difficult to restore through the parameters. The applicant has found that during the driving process, acoustic signals collected by sensors provided on the TBM and the interface have a certain correlation during the driving of the cutterhead and during the driving process of one cycle, and that the properties of the interface and the morphology of the cutterhead during the driving process also have a certain correlation, so that valuable information can be obtained by processing the relevant data. However, if data are collected each time to construct a model in the process of forming the roadway, the complexity of work is increased to a certain extent, and the intelligent degree is not improved enough; the inventor realizes the reuse of data by tracking a series of sound signals collected in the history shield process.
According to one embodiment of the application, acoustic signals can be acquired at some parts of the shield machine, such as acoustic signals acquired at cutterhead, shield and support sites in some embodiments of the application; in the process of acquiring acoustic signals, in order to obtain the tunneling process, the cutter head and the interface contact feed back the energy absorption of the interface in a vibration or sound wave mode, and the property of the interface can be restored to a certain extent through analysis of the energy absorption.
According to one embodiment of the application, the acoustic signal is filtered, and the acoustic distribution characteristics in the tunneling process are obtained; here filtering is performed to obtain the intensity of the sound field in a certain frequency range, and it should be noted that part of the acoustic sensor should be recalculated when it is collected due to the change of distance during the gold mining process. In addition, the sampling points should be set fully considering the representativeness of sampling, because the underground noise is larger in the TBM tunneling process, the sound distribution of part of the sampling points may not be related to the tunneling process,
according to one embodiment of the application, attitude distribution prediction in the tunneling process is obtained according to acoustic distribution characteristics in the tunneling process and the pushing distance of the cutterhead; the interface and the sound have relevance, and when the tunnel is shielded under the same working condition, the corresponding lift data of the tunnel should be similar.
According to one embodiment of the application, further, the inventor finds that, when backtracking data, the characteristics of the rock tunnel and the coal mine are different, but reflected on the rock slag and the frequency spectrum, the characteristics of the rock tunnel and the coal mine tunnel are related, namely, the frequency spectrum characteristics of the energy are inconsistent, but the frequency spectrum of the energy and the rock slag have independent relevance. Based on some approximate signals in the rock mass as basic noise sources, the interface acoustic signals can be further obtained, and the signals are different from actual values, but the prediction of the shield interface can be realized based on the signals. That is, in the spectrum range, the spectrum range of a simple roadway is inconsistent with the spectrum range of coal, but the spectrum ranges of a plurality of types of roadways can cover the coal roadway.
According to one embodiment of the application, the interface of the shield and at least one rock type are distributed by vibration and substitution is achieved. And because the coal and the rock are not consistent in practice, more accurate coal substitution distribution can be further obtained by adjusting the components of the coal and the rock.
According to the embodiment of the application, during the confirmation of the distribution of the rock slag, special attention is paid to tracking the crushing behavior of the rock under the corresponding parameters of the shield tunneling machine, namely tracking the size distribution and the edge distribution, further clustering the color distribution of the slag in combination with the acoustic characteristics, classifying the clustering result, and obtaining the association relation between the acoustic signals and the actual interface under different working conditions.
According to one embodiment of the application, correlations between some common coal-rock characteristics and acoustic spectra in the shield process are obtained, which are used to decompose the obtained acoustic signals to obtain corresponding interface compositions. Further, the characteristic energy peak is obtained by comparing different rock characteristic frequency spectrums. In most cases, the maximum peak and the characteristic peak of the energy spectrum are coincident; in some cases, the characteristic peaks of the energy spectrum are weaker than the maximum peaks.
According to one embodiment of the application, since it is impossible to acquire all the characteristics of the rock tunnel, or to acquire the correlation between the acoustic characteristics and the rock under different working conditions in a simulated manner, in most cases, the characteristics spectrum of the rock slag, the acoustic characteristics spectrum, or the intensity of the vibration signal, are basically smooth transition, and after acquiring the signal peaks of the characteristics, the acquisition of intermediate values can be performed by fitting to enrich the data sources. In this process, no constraints of the physical model are generally involved, i.e. ghost points occur, far from the actual operating parameters or the numerical intervals acquired by the sensors.
According to one embodiment of the application, since the noise sources of the shield machine during shield are multiple, and the noise sources collected by the front pick-up and the rear pick-up are not identical, the acoustic signals collected by the rear pick-up can be used as references. In a typical case, characteristic signals different from the front pickup can be obtained, the characteristic signals reflect noise based on other parts of the shield machine, and interface acoustic signals after interference removal can be obtained by calculating distances among a plurality of pickup and assuming that other noise sources do not exist in the middle.
According to one embodiment of the present application, the number of microphones that need to be set is reduced, and the accuracy of fitting is improved. However, those skilled in the art will appreciate that the sound at the interface cannot acquire the acoustic signals that are theoretically and practically consistent in the above manner, and some situations are ideal, the whole machine can generate noise in the working of the shield tunneling machine, and through training of the model, the model can recognize and learn how the noise at the positions affects the output interface acoustic signals.
According to one embodiment of the application, the data set may be removed in the event of a start-up or apparent abnormality prior to training.
Moreover, in order to achieve the above object, the present application also provides a prediction system for a coal mine tunnel shield interface, and fig. 2 is a flowchart of a prediction system for a coal mine tunnel shield interface in the present application, as shown in fig. 2, the prediction system for a coal mine tunnel shield interface in the present application includes:
the back bottom noise acquisition module: acquiring preset back noise according to working parameters of the shield machine and historical shield acoustic data;
interface acoustic signal acquisition module: removing the back of the interface acoustic signal based on the characteristic signal of the background noise to obtain the interface acoustic signal;
the prediction interface information acquisition module: inputting a prediction network based on the interface acoustic signals and the parameter stage of the shield machine to obtain information of a prediction interface;
vibration information acquisition module: obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine;
an interface type determining module: determining the type of the interface based on the difference between the vibration information and the measured vibration information;
the historical shield acoustic data is acquired based on tunneling data of the rock tunnel.
According to one embodiment of the application, the vibration distribution difference of the interface is obtained according to the difference of the vibration information and the actually measured vibration information in frequency and energy, and the rock type corresponding to the frequency spectrum distribution is determined based on the vibration distribution difference and the information of the predicted interface;
the composition of the predicted interface is adjusted based on the type of rock.
According to one embodiment of the application, rock slag in a chute at the cutter head position is obtained, the formation time of the rock slag is estimated according to the speed of a conveyor belt, and the working parameters of the shield machine are obtained according to the travel time of the rock slag;
obtaining color distribution, size distribution and edge distribution of slag in an image according to a sampling image of the rock slag;
clustering slag based on color distribution, size distribution or edge distribution of the slag, and classifying shield acoustic data based on clustering results;
classifying the classification result by using a KNN model to obtain association relations of acoustic signals under working parameters of different shield machines;
and obtaining a classification result with the maximum approximation degree as rock classification according to the working parameters of the shield tunneling machine and the characteristics of the acquired acoustic signals.
According to one embodiment of the application, the characteristic frequency range of the acoustics is determined according to the energy spectrum distribution of the collected acoustic signals;
constructing an acoustic working condition dictionary based on the acoustic characteristic frequency range, wherein keys of the acoustic working condition dictionary are working parameters of the shield machine, and values of the acoustic working condition dictionary are acoustic characteristic frequencies;
and constructing a rock characteristic dictionary of the classification result and the rock characteristic, wherein the keys of the rock characteristic dictionary are acoustic working condition dictionaries, and the values of the rock characteristic dictionary are rock characteristics.
According to one embodiment of the application, the proportion of each type of rock is obtained according to the information of the prediction interface, the acoustic signals are fitted based on the proportion of each type of rock and the working parameters, and when the acoustic signals are fitted, adjacent data are used for linear fitting to missing data to obtain a substitution value;
the vibration information is acquired based on a vibration characteristic network, and the input of the vibration characteristic network comprises information of interface characteristics and working parameters of the shield machine.
According to one embodiment of the application, noise before the shield is used as an environment background to remove the environment noise in the collected acoustic signals, and sound collected at a working part of the shield is used as the background to remove the noise of a working part in the collected acoustic signals, so that an interface acoustic signal is obtained; in the process of removing the back, noise is removed by adopting a characteristic spectrum mode.
According to one embodiment of the application, the noise of the environment noise and the noise of the pushing part of the shield tunneling machine cutterhead are respectively obtained, the characteristic peak is determined, the energy of each frequency interval is fitted by using a least square method, the overall contribution degree of the environment noise and the pushing part to the acoustic signal is set to be 1, and the noise which can be identified according to the characteristic frequency is removed from the collected acoustic signal through optimizing to serve as an interface acoustic signal.
According to one embodiment of the application, the prediction network is based on a deep neural network, the input of which comprises the interface acoustic signal and the operating parameters, and the output of which further comprises the spectral distribution of the interface acoustic signal.
According to one embodiment of the application, the nature of the interface is important to the operation of the coal mine tunnelling process. Therefore, the identification of the coal rock slime type is always a difficult problem to be solved by researchers at home and abroad. However, unlike ordinary hard rock tunneling, surrounding rock under the mine has complex properties, numerous operating parameters affecting the tunneling characteristics of the TBM, and the problem that the tunneling process cannot be monitored in the tunneling process exists. In the tunneling process of a TBM on a coal mine tunnel, common TBM usable parameters comprise a pushing speed, an operation parameter, collected data, a digging diameter, a cutter type, cutter driving power, cutter rotating speed, pushing force and a pushing stroke, and the form of a tunneling surface is difficult to restore through the parameters. The applicant has found that during the driving process, acoustic signals collected by sensors provided on the TBM and the interface have a certain correlation during the driving of the cutterhead and during the driving process of one cycle, and that the properties of the interface and the morphology of the cutterhead during the driving process also have a certain correlation, so that valuable information can be obtained by processing the relevant data. However, if data are collected each time to construct a model in the process of forming the roadway, the complexity of work is increased to a certain extent, and the intelligent degree is not improved enough; the inventor realizes the reuse of data by tracking a series of sound signals collected in the history shield process.
According to one embodiment of the application, acoustic signals can be acquired at some parts of the shield machine, such as acoustic signals acquired at cutterhead, shield and support sites in some embodiments of the application; in the process of acquiring acoustic signals, in order to obtain the tunneling process, the cutter head and the interface contact feed back the energy absorption of the interface in a vibration or sound wave mode, and the property of the interface can be restored to a certain extent through analysis of the energy absorption.
According to one embodiment of the application, the acoustic signal is filtered, and the acoustic distribution characteristics in the tunneling process are obtained; here filtering is performed to obtain the intensity of the sound field in a certain frequency range, and it should be noted that part of the acoustic sensor should be recalculated when it is collected due to the change of distance during the gold mining process. In addition, the sampling points should be set fully considering the representativeness of sampling, because the underground noise is larger in the TBM tunneling process, the sound distribution of part of the sampling points may not be related to the tunneling process,
according to one embodiment of the application, attitude distribution prediction in the tunneling process is obtained according to acoustic distribution characteristics in the tunneling process and the pushing distance of the cutterhead; the interface and the sound have relevance, and when the tunnel is shielded under the same working condition, the corresponding lift data of the tunnel should be similar.
According to one embodiment of the application, further, the inventor finds that, when backtracking data, the characteristics of the rock tunnel and the coal mine are different, but reflected on the rock slag and the frequency spectrum, the characteristics of the rock tunnel and the coal mine tunnel are related, namely, the frequency spectrum characteristics of the energy are inconsistent, but the frequency spectrum of the energy and the rock slag have independent relevance. Based on some approximate signals in the rock mass as basic noise sources, the interface acoustic signals can be further obtained, and the signals are different from actual values, but the prediction of the shield interface can be realized based on the signals. That is, in the spectrum range, the spectrum range of a simple roadway is inconsistent with the spectrum range of coal, but the spectrum ranges of a plurality of types of roadways can cover the coal roadway.
According to one embodiment of the application, the interface of the shield and at least one rock type are distributed by vibration and substitution is achieved. And because the coal and the rock are not consistent in practice, more accurate coal substitution distribution can be further obtained by adjusting the components of the coal and the rock.
According to the embodiment of the application, during the confirmation of the distribution of the rock slag, special attention is paid to tracking the crushing behavior of the rock under the corresponding parameters of the shield tunneling machine, namely tracking the size distribution and the edge distribution, further clustering the color distribution of the slag in combination with the acoustic characteristics, classifying the clustering result, and obtaining the association relation between the acoustic signals and the actual interface under different working conditions.
According to one embodiment of the application, correlations between some common coal-rock characteristics and acoustic spectra in the shield process are obtained, which are used to decompose the obtained acoustic signals to obtain corresponding interface compositions. Further, the characteristic energy peak is obtained by comparing different rock characteristic frequency spectrums. In most cases, the maximum peak and the characteristic peak of the energy spectrum are coincident; in some cases, the characteristic peaks of the energy spectrum are weaker than the maximum peaks.
According to one embodiment of the application, since it is impossible to acquire all the characteristics of the rock tunnel, or to acquire the correlation between the acoustic characteristics and the rock under different working conditions in a simulated manner, in most cases, the characteristics spectrum of the rock slag, the acoustic characteristics spectrum, or the intensity of the vibration signal, are basically smooth transition, and after acquiring the signal peaks of the characteristics, the acquisition of intermediate values can be performed by fitting to enrich the data sources. In this process, no constraints of the physical model are generally involved, i.e. ghost points occur, far from the actual operating parameters or the numerical intervals acquired by the sensors.
According to one embodiment of the application, since the noise sources of the shield machine during shield are multiple, and the noise sources collected by the front pick-up and the rear pick-up are not identical, the acoustic signals collected by the rear pick-up can be used as references. In a typical case, characteristic signals different from the front pickup can be obtained, the characteristic signals reflect noise based on other parts of the shield machine, and interface acoustic signals after interference removal can be obtained by calculating distances among a plurality of pickup and assuming that other noise sources do not exist in the middle.
According to one embodiment of the present application, the number of microphones that need to be set is reduced, and the accuracy of fitting is improved. However, those skilled in the art will appreciate that the sound at the interface cannot acquire the acoustic signals that are theoretically and practically consistent in the above manner, and some situations are ideal, the whole machine can generate noise in the working of the shield tunneling machine, and through training of the model, the model can recognize and learn how the noise at the positions affects the output interface acoustic signals.
According to one embodiment of the application, the data set may be removed in the event of a start-up or apparent abnormality prior to training.
Based on the above, the method has the beneficial effects that the problem that the tunneling process cannot be monitored because the surrounding rock attribute under the mine is complex is solved by acquiring the correlation between the acoustic signal and the interface data.
Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and device described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment of the application.
In addition, each functional module in the embodiment of the present application may be integrated in one processing module, or each module may exist alone physically, or two or more modules may be integrated in one module.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method for energy saving signal transmission/reception of the various embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
It should be understood that, the sequence numbers of the steps in the summary and the embodiments of the present application do not necessarily mean the order of execution, and the execution order of the processes should be determined by the functions and the internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.
Claims (9)
1. The prediction method of the shield interface of the coal mine tunnel is characterized by comprising the following steps of:
acquiring preset back noise according to working parameters of the shield machine and historical shield acoustic data;
removing the back of the interface acoustic signal based on the characteristic signal of the background noise to obtain the interface acoustic signal;
inputting a prediction network based on the interface acoustic signals and the parameter stage of the shield machine to obtain information of a prediction interface;
obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine;
determining the type of the interface based on the difference between the vibration information and the measured vibration information;
the historical shield acoustic data is acquired based on tunneling data of the rock tunnel.
2. The method for predicting a shield interface of a coal mine tunnel according to claim 1, wherein the vibration distribution difference of the interface is obtained according to the difference of the vibration information and the actually measured vibration information in frequency and energy, and the rock type corresponding to the frequency spectrum distribution is determined based on the vibration distribution difference and the information of the predicted interface;
the composition of the predicted interface is adjusted based on the type of rock.
3. The prediction method of the shield interface of the coal mine tunnel according to claim 2, wherein rock slag in a chute at the cutter head position is obtained, the formation time of the rock slag is estimated according to the speed of a conveyor belt, and the working parameters of the shield machine are obtained according to the travel time of the rock slag;
obtaining color distribution, size distribution and edge distribution of slag in an image according to a sampling image of the rock slag;
clustering slag based on color distribution, size distribution or edge distribution of the slag, and classifying shield acoustic data based on clustering results;
classifying the classification result by using a KNN model to obtain association relations of acoustic signals under working parameters of different shield machines;
and obtaining a classification result with the maximum approximation degree as rock classification according to the working parameters of the shield tunneling machine and the characteristics of the acquired acoustic signals.
4. A method of predicting a coal mine tunnel shield interface as claimed in claim 3 wherein the characteristic frequency range of the acoustics is determined from the energy spectrum distribution of the acquired acoustic signals;
constructing an acoustic working condition dictionary based on the acoustic characteristic frequency range, wherein keys of the acoustic working condition dictionary are working parameters of the shield machine, and values of the acoustic working condition dictionary are acoustic characteristic frequencies;
and constructing a rock characteristic dictionary of the classification result and the rock characteristic, wherein the keys of the rock characteristic dictionary are acoustic working condition dictionaries, and the values of the rock characteristic dictionary are rock characteristics.
5. The prediction method of a coal mine tunnel shield interface according to claim 4, wherein the proportion of each type of rock is obtained according to the information of the prediction interface, acoustic signals are fitted based on the proportion of each type of rock and working parameters, and when fitting is performed, adjacent data are used for linear fitting to missing data to obtain a substitution value;
the vibration information is acquired based on a vibration characteristic network, and the input of the vibration characteristic network comprises information of interface characteristics and working parameters of the shield machine.
6. The prediction method of the coal mine tunnel shield interface according to claim 5, wherein noise before shield is used as an environment background to remove the environment noise in the collected acoustic signals, and sound collected at a working part of the shield machine is used as the background to remove the noise of a working part in the collected acoustic signals, so that the interface acoustic signals are obtained; in the process of removing the back, noise is removed by adopting a characteristic spectrum mode.
7. The prediction method of the coal mine tunnel shield interface according to claim 6, wherein the environmental noise and the noise of the shield machine cutterhead propelling part are respectively obtained, the characteristic peaks are determined, the least square method is used for fitting the energy of each frequency interval, the overall contribution degree of the environmental noise and the propelling part to the acoustic signal is set to be 1, and noise which can be identified according to the characteristic frequency is removed from the collected acoustic signal through optimizing to serve as the interface acoustic signal.
8. The method for predicting a shield interface of a coal mine tunnel of claim 7, wherein the prediction network is based on a deep neural network, the input of which comprises an interface acoustic signal and an operating parameter, and the output of which further comprises a spectral distribution of the interface acoustic signal.
9. The prediction system of the shield interface of the coal mine tunnel is characterized by comprising the following components:
the back bottom noise acquisition module: acquiring preset back noise according to working parameters of the shield machine and historical shield acoustic data;
interface acoustic signal acquisition module: removing the back of the interface acoustic signal based on the characteristic signal of the background noise to obtain the interface acoustic signal;
the prediction interface information acquisition module: inputting a prediction network based on the interface acoustic signals and the parameter stage of the shield machine to obtain information of a prediction interface;
vibration information acquisition module: obtaining predicted vibration information based on the information of the prediction interface and the working parameters of the shield machine;
an interface type determining module: determining the type of the interface based on the difference between the vibration information and the measured vibration information;
the historical shield acoustic data is acquired based on tunneling data of the rock tunnel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311085497.7A CN117189251A (en) | 2023-08-25 | 2023-08-25 | Prediction method for shield interface of coal mine tunnel |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311085497.7A CN117189251A (en) | 2023-08-25 | 2023-08-25 | Prediction method for shield interface of coal mine tunnel |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117189251A true CN117189251A (en) | 2023-12-08 |
Family
ID=88999094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311085497.7A Pending CN117189251A (en) | 2023-08-25 | 2023-08-25 | Prediction method for shield interface of coal mine tunnel |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117189251A (en) |
-
2023
- 2023-08-25 CN CN202311085497.7A patent/CN117189251A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11834943B2 (en) | Systems, apparatuses, and methods for determining rock-coal transition with a drilling machine | |
CN211291565U (en) | Tunnel construction dynamic monitoring and early warning system | |
CN113685188B (en) | TBM tunneling optimization method based on physical characteristics of rock slag | |
CN1904644A (en) | Network tunnel real time continuous leading preinforming method and device | |
CN103603669A (en) | Unfavorable geology forecasting device for shield tunnel and tunnel construction method | |
AU2011264084A1 (en) | Method and apparatus for increasing the yield in a deposit | |
CN111080015A (en) | Shield equipment and real-time service life prediction system and prediction method thereof | |
Dickmann et al. | Towards the integration of smart techniques for tunnel seismic applications | |
Shen et al. | Estimating locations of soil–rock interfaces based on vibration data during shield tunnelling | |
CN111337447B (en) | Coal and gangue bionic identification system and method | |
CN117189251A (en) | Prediction method for shield interface of coal mine tunnel | |
Ding et al. | A Bayesian optimized variational mode decomposition-based denoising method for measurement while drilling signal of down-the-hole drilling | |
Wang et al. | Experimental evaluation of rock disintegration detection in drilling by a new acoustic sensor method | |
CN110847907A (en) | Coal rock identification method based on touch sense | |
Babaei Khorzoughi | Use of measurement while drilling techniques for improved rock mass characterization in open-pit mines | |
CN115239108B (en) | Weak broken surrounding rock sensing method based on TBM real-time broken rock data | |
CN113703038B (en) | Automatic microseismic signal acquisition and identification method and system | |
CN115950947A (en) | Real-time geological parameter prediction method of TBM tunnel based on vibration signal | |
CN216198098U (en) | Device and system for acquiring geological information | |
LaBelle | Lithological classification by drilling | |
CN117189146A (en) | TBM tunneling process-based geological information acquisition method | |
CN110850471B (en) | Method for converting SH wave detection washband based on shock wave excitation seismic source | |
CN203769782U (en) | Unfavorable geology forecast device for shield tunnel | |
CN114104666B (en) | Coal gangue identification method and coal mine conveying system | |
JPH09317372A (en) | Method for searching rock mass |
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 |