CN118228584A - Acquisition method and device of mining strategy - Google Patents
Acquisition method and device of mining strategy Download PDFInfo
- Publication number
- CN118228584A CN118228584A CN202410336790.4A CN202410336790A CN118228584A CN 118228584 A CN118228584 A CN 118228584A CN 202410336790 A CN202410336790 A CN 202410336790A CN 118228584 A CN118228584 A CN 118228584A
- Authority
- CN
- China
- Prior art keywords
- mining
- strategy
- historical
- initial
- acquiring
- 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
- 238000005065 mining Methods 0.000 title claims abstract description 198
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000009412 basement excavation Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000004590 computer program Methods 0.000 claims description 24
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 3
- 230000005641 tunneling Effects 0.000 description 36
- 239000002689 soil Substances 0.000 description 21
- 238000010586 diagram Methods 0.000 description 19
- 238000004364 calculation method Methods 0.000 description 16
- 239000000428 dust Substances 0.000 description 14
- 238000005520 cutting process Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 13
- 239000011435 rock Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000011218 segmentation Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 238000005507 spraying Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000011835 investigation Methods 0.000 description 4
- 239000010410 layer Substances 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 239000003245 coal Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000011229 interlayer Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009933 burial Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Landscapes
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention discloses a method and a device for acquiring an excavating strategy, wherein the method comprises the following steps: acquiring three-dimensional image information of a working surface to be excavated; inputting three-dimensional image information into a mining strategy model, and outputting an initial mining strategy, wherein the mining strategy model is obtained by training a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy; acquiring excavation boundary conditions through environment information and equipment information; and optimizing the initial mining strategy based on the mining boundary conditions to obtain the target mining strategy. The invention can improve the accuracy and the generation efficiency of the mining strategy.
Description
Technical Field
The present invention relates to the field of image recognition technologies, and in particular, to a method and an apparatus for acquiring an mining policy.
Background
The direct tunneling equipment such as the cantilever tunneling machine originally applied to coal mining is comprehensive mechanical equipment integrating cutting, loading and transporting and automatic walking. Along with rapid progress of comprehensive coal mining mechanization of coal mine stope face, the requirement for roadway tunneling speed is also increasing. In order to meet the increasing demands on the roadway speed, the cantilever type heading machine is promoted and applied through positive development and gradual perfection. With the continuous development and updating of the equipment, the application range of the equipment is also enlarged. The application attempts of the method in the aspects of tunnel excavation in traffic, water engineering and the like provide more schemes for tunnel excavation construction in the fields.
For direct tunneling devices such as boom-type heading machines, breaker hammers for shovels, etc., the face generally refers to the location of the working face or face where the machine is tunneling and mining. In the tunneling and mining processes of equipment, the face always has a weakest position, and if the face is not selected and operated, slump risks and even engineering safety accidents can be caused. Meanwhile, the optimal tunneling angle exists on the tunnel face, and initial tunneling can be performed on the tunnel face more efficiently under the optimal tunneling angle, so that tunneling construction efficiency is greatly improved. It can be seen that the initial excavation position and angle of the face are selected to have a particularly pronounced effect on effective excavation during operation. However, the current initial tunneling strategy (i.e., the initial tunneling position and angle) of the face is determined subjectively by the driver based on working experience, with randomness and uncertainty. Under the condition, a driver cannot quickly and efficiently determine the optimal initial tunneling strategy, which is unfavorable for tunneling operation; if the driver inadvertently selects the wrong heading strategy, or unnecessary time and material costs would result.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a method and equipment for acquiring an excavating strategy, which are used for solving the technical problem that the efficiency of a strategy determination method for excavating and mining in the prior art is not high enough.
The embodiment of the invention provides a method for acquiring an excavating strategy, which comprises the following steps:
Acquiring three-dimensional image information of a working surface to be excavated;
Inputting three-dimensional image information into a mining strategy model, and outputting an initial mining strategy, wherein the mining strategy model is obtained by training a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy;
Acquiring excavation boundary conditions through environment information and equipment information;
And optimizing the initial mining strategy based on the mining boundary conditions to obtain the target mining strategy.
Optionally, in an embodiment of the present invention, optimizing the initial mining policy based on the mining boundary condition, obtaining the target mining policy includes: comparing the initial value in the initial mining strategy with the boundary value under the condition that the mining boundary condition comprises the boundary value, and adjusting the initial value in the initial mining strategy to be a target value under the condition that the boundary value is exceeded; and acquiring a target mining strategy based on the target value.
Optionally, in an embodiment of the present invention, obtaining the mining strategy model includes: acquiring a plurality of historical three-dimensional image information; lithology information respectively corresponding to the plurality of historical three-dimensional image information is obtained; acquiring a history mining strategy corresponding to each of the lithology information; acquiring a plurality of historical target mining strategies based on the plurality of historical mining strategies; obtaining a plurality of groups of samples through a plurality of history mining strategies and a plurality of history three-dimensional images; and performing deep learning training through a plurality of groups of samples to obtain an excavation strategy model.
Optionally, in an embodiment of the present invention, based on the plurality of history mining policies, acquiring a plurality of history target mining policies further includes: based on evaluation information input by an external terminal, obtaining scores respectively corresponding to a plurality of historical mining strategies; and adjusting the corresponding historical mining strategies based on the scores to obtain a plurality of historical target mining strategies.
The embodiment of the invention provides an acquisition device of an excavating strategy, which comprises the following steps:
the first acquisition module is used for acquiring three-dimensional image information of the working surface to be excavated;
The input/output module is used for inputting the three-dimensional image information into the mining strategy model and outputting an initial mining strategy, wherein the mining strategy model is obtained by training a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy;
The second acquisition module is used for acquiring mining boundary conditions through the environment information and the equipment information;
and the optimization module is used for optimizing the initial mining strategy based on the mining boundary condition and acquiring the target mining strategy.
Optionally, in an embodiment of the present invention, the first obtaining module includes: the comparison unit is used for comparing the initial value in the initial mining strategy with the boundary value under the condition that the mining boundary condition comprises the boundary value, and adjusting the initial value in the initial mining strategy to be the target value under the condition that the boundary value is exceeded; the first acquisition unit acquires a target mining strategy based on the target value.
Optionally, in an embodiment of the present invention, obtaining the mining strategy model includes: a second acquisition unit configured to acquire a plurality of pieces of history three-dimensional image information; a third acquisition unit for acquiring lithology information corresponding to the plurality of historical three-dimensional image information respectively; a fourth obtaining unit, configured to obtain a history mining policy corresponding to each of the plurality of lithology information; a fifth acquisition unit configured to acquire a plurality of history target mining policies based on the plurality of history mining policies; a sixth obtaining unit, configured to obtain a plurality of groups of samples through a plurality of history mining policies and a plurality of history three-dimensional images; and the seventh acquisition unit is used for performing deep learning training through a plurality of groups of samples to acquire an excavation strategy model.
Optionally, in an embodiment of the present invention, the fifth obtaining unit further includes: the first acquisition subunit is used for acquiring scores corresponding to the plurality of history mining strategies respectively based on the evaluation information input by the external terminal; and the adjustment subunit is used for adjusting the corresponding historical mining strategies based on the scores to acquire a plurality of historical target mining strategies.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the acquisition method of the mining strategy when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the acquisition method of the mining strategy is realized when the computer program is executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the acquisition method of the mining strategy is realized when the computer program is executed by a processor.
The method and the device for acquiring the mining strategy provided by the embodiment of the invention acquire the three-dimensional image information of the working surface to be mined; inputting three-dimensional image information into a mining strategy model, and outputting an initial mining strategy, wherein the mining strategy model is obtained by training a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy; acquiring excavation boundary conditions through environment information and equipment information; and optimizing the initial mining strategy based on the mining boundary conditions to obtain the target mining strategy, so that the efficiency and accuracy of determining the mining strategy are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flowchart of a method for acquiring mining policies in an embodiment of the present invention;
FIG. 2 is a schematic diagram of mining strategy visualization in an embodiment of the present invention;
FIG. 3 is a schematic diagram of face image semantic segmentation in an embodiment of the present invention;
FIG. 4 is a schematic diagram of semantic segmentation of a face image according to an embodiment of the present invention;
FIG. 5 (a) is a schematic illustration of a cross-section of an exemplary face in an embodiment of the present invention;
FIG. 5 (b) is a schematic diagram of an example face joint map and lithology analysis according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a dust suppression module according to an embodiment of the invention;
FIG. 7 is a flowchart of a method for acquiring a preferred mining strategy in an embodiment of the present invention;
FIG. 8 is a schematic diagram of an acquisition device of an mining strategy in an embodiment of the present invention;
Fig. 9 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Fig. 1 is a flowchart of a method for acquiring an mining policy in an embodiment of the present invention, and as shown in fig. 1, an embodiment of the present invention provides a method for acquiring an mining policy, including:
step S101, acquiring three-dimensional image information of a working surface to be excavated;
In the above steps, firstly, a three-dimensional image of a face to be excavated (excavation working face) is obtained, and it should be noted that, the method for obtaining the three-dimensional image includes three-dimensional reconstruction, and the ToF technology is that light is reflected when encountering an object by emitting a continuous light source, and then captured by a receiving device. And forming a surface by using tens of thousands of beams, wherein the return time of each beam is different, so that the 'height' of the surface is calculated, and a three-dimensional structure model is drawn according to the information. The dust in the excavation process is very intense, so that the scanning of the TOF camera is seriously disturbed. In the invention, the physical method is adopted to reduce dust and remove dust and is combined with the reconstruction algorithm to optimize, so that the three-dimensional reconstruction model has better reduction degree. The physical dust fall and dust removal is mainly realized through the work of a dust fall and dust removal module, and the dust emission of a tunnel in the excavation process is reduced through intelligent controllable spraying. And the algorithm optimization is mainly carried out by updating the algorithm in the fitting process, eliminating data points interfered by dust, and reducing the data sample size influenced by the dust, so that a better three-dimensional reconstruction result is obtained.
Step S102, three-dimensional image information is input into a mining strategy model, and an initial mining strategy is output, wherein the mining strategy model is obtained through training of a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy;
In the above step, the obtained three-dimensional image is input into a trained mining strategy model, and an initial mining strategy is output, and it should be noted that the mining strategy includes a plurality of specific mining information items, including at least: visual information such as the optimal excavation position, the optimal excavation cutting angle, the optimal tunneling advancing speed, the optimal swing arm speed and the like.
Step S103, acquiring excavation boundary conditions through environment information and equipment information;
In the above step, the mining boundary condition is acquired through the current environment information and the device information, where the environment information at least includes: the characteristics of the rock and soil, the maximum main stress, the minimum main stress and the mechanical strength of the rock and soil body, and the equipment information comprises: the method comprises the following steps of excavating equipment, namely excavating tunnel radius D of excavating equipment, bit radius D of excavating equipment, cutting angle theta, heading machine advancing speed v, swinging speed w, engine power P, bit rotation period T and the like.
Step S104, optimizing the initial mining strategy based on the mining boundary conditions, and obtaining the target mining strategy.
In the step, auditing a plurality of pieces of information in the initial mining information strategy based on mining boundary conditions, judging whether the information in the initial mining information strategy does not accord with the current environment and equipment conditions, and if the information does not accord with the current environment and equipment conditions, optimizing the initial mining strategy to obtain the target mining strategy.
Fig. 2 is a schematic diagram of visualization of an excavation strategy in an embodiment of the present invention, where, as shown in fig. 2, the content of the optimal initial tunneling strategy mainly includes visual information such as an optimal excavation position, an optimal excavation cutting angle, an optimal tunneling advancing speed, an optimal swing arm speed, etc. marked by a graphic method, and information (as shown in fig. 2) for assisting an operator to judge, such as an joint image, lithology information, current mechanical equipment status (engine power, hydraulic system hydraulic pressure, etc.). The optimal initial tunneling strategy is directly presented to an operator in a visual mode through a display screen, and a real-time tunneling strategy scheme can be provided for the operator quickly and accurately.
As one embodiment of the present invention, optimizing an initial mining strategy based on a mining boundary condition, obtaining a target mining strategy includes: comparing the initial value in the initial mining strategy with the boundary value under the condition that the mining boundary condition comprises the boundary value, and adjusting the initial value in the initial mining strategy to be a target value under the condition that the boundary value is exceeded; and acquiring a target mining strategy based on the target value.
In the above alternative embodiment, when the mining boundary condition includes a boundary value, the boundary data is compared with an initial value in the mining policy, and if the boundary value is exceeded, the initial value in the initial mining policy is adjusted, and the adjusted value is used as the target mining policy. For example, if the optimal tunneling forward speed output by the mining strategy model is greater than the upper tunneling forward speed limit of the mining equipment, obviously unreasonable data appears, and the data is changed into the upper tunneling forward speed limit of the equipment.
The front soil body of the face is an ideal elastoplastic material meeting Mohr-Coulomb yield criterion, and according to the rock-soil static balance condition and yield condition criterion and in combination with the soil arch effect, a slip deformation equation of the front soil body of the face can be constructed: Wherein: sigma v is the vertical soil pressure in the arch region calculated by adopting the large principal stress arch theory; z is the distance between the calculated position and the top of the slip plane development area; gamma is the weight of the rock-soil body; c is the cohesive force of the rock-soil mass; /(I) Is the internal friction angle of the rock-soil body; the coefficient, gamma, utilizes the superposition principle to obtain the average weight calculation formula of n layers of different rock-soil bodies, wherein the average weight calculation formula is as follows: /(I)Similarly, the average cohesion c of the rock-soil mass is as follows: /(I)Average internal friction angle phi of the rock-soil mass: /(I)
Compared with the traditional method for assuming that the soil body above the tunnel face is of a single rock body type, the method can fully consider the characteristics of the soil body of each rock stratum, so that the calculation result is more accurate and reliable.
On the other hand, the boundary conditions of the mechanical equipment conditions are mainly used for combining the mechanical equipment conditions, such as the excavation tunnel radius D of the excavation equipment, the drill bit radius D of the excavation equipment, the cutting angle theta, the advancing speed v of the heading machine, the swinging speed w, the engine power P, the drill bit rotation period T and the like. And deducing the cutting pressure sigma τ of the face in the excavation process from the information, and further calculating the cutting speed of the three-dimensional model. The cutting pressure sigma τ is calculated as follows: Wherein: alpha i is the influence coefficient of the conditions of each mechanical device on the cutting pressure, and is determined through experiments.
Compared with the traditional method for determining the cutting pressure during face excavation, the method fully considers the influence of mechanical equipment. Meanwhile, the real-time calculation can be carried out according to the cutting pressure of mechanical equipment under different conditions and under different working conditions of the same equipment, so that the finite element simulation result is more accurate and reliable.
As one embodiment of the present invention, obtaining an mining strategy model includes: acquiring a plurality of historical three-dimensional image information; lithology information respectively corresponding to the plurality of historical three-dimensional image information is obtained; acquiring a history mining strategy corresponding to each of the lithology information; acquiring a plurality of historical target mining strategies based on the plurality of historical mining strategies; obtaining a plurality of groups of samples through a plurality of history mining strategies and a plurality of history three-dimensional images; and performing deep learning training through a plurality of groups of samples to obtain an excavation strategy model.
In the above optional embodiment, the method for acquiring corresponding lithology information by using the historical three-dimensional image information includes: fig. 3 is a schematic diagram of semantic segmentation of a face image according to an embodiment of the present invention, as shown in fig. 3, using a corresponding device to obtain image (video) data of the face, using a deep learning model to perform semantic segmentation on the image, and visualizing information after performing semantic segmentation on the image, as shown in fig. 4 (fig. 4 is a schematic diagram of the semantic segmentation of the face image according to an embodiment of the present invention).
After the three-dimensional structure model of the working surface is obtained, various kinds of information are added to the three-dimensional model by combining the information of each layer of the working surface. For example, different kinds of rock and soil in the model are endowed with the characteristics (bearing capacity, friction angle and the like) of the different kinds of rock and soil; interpreting and assigning joint information of the model, such as positioning, shape fitting, geometric information (shape, spacing, breaking distance, etc.) of each structural surface; giving the information of the weak surface of the model, constructing the fracture and interlayer information of the rock-soil body, randomly simulating a discontinuous surface network of the rock-soil body by using a proper method, and drawing a three-dimensional joint calculation network of the model. By the means, the three-dimensional structure model with the calculation elements can be obtained, and the digital twin model which can carry out rapid finite element calculation and is convenient for expert evaluation is formed.
After lithology information of each three-dimensional image is obtained, outputting a history mining strategy corresponding to each three-dimensional image, scoring each history mining strategy by using an expert scoring mode, adjusting the strategy when scoring is poor, forming a group of training samples by the history three-dimensional images and the history mining strategy after adjustment, and performing machine learning training on a plurality of groups of training samples to obtain a mining strategy model.
The artificial intelligent model is trained by using the face image and the corresponding optimal initial tunneling strategy data set. The input end of the model is a face image in the tunneling process, and the output end is the optimal initial tunneling strategy of the face. Compared with the traditional mode, the artificial intelligence can provide the optimal initial tunneling strategy of the tunnel face according to the tunnel face image information acquired in real time on site, and has higher instantaneity. And the training data set source of the artificial intelligent model is investigated through expert evaluation, so that the method has higher feasibility.
As one embodiment of the present invention, based on the plurality of history mining policies, obtaining a plurality of history target mining policies further includes: based on evaluation information input by an external terminal, obtaining scores respectively corresponding to a plurality of historical mining strategies; and adjusting the corresponding historical mining strategies based on the scores to obtain a plurality of historical target mining strategies.
In the above-mentioned alternative embodiment, the scores of the experts on the historical mining policies (i.e., the evaluation information input by the external terminal) are obtained, the historical mining policies are adjusted based on the scores, the historical target mining policies are obtained, and the model training is performed by using the historical target mining policies.
The expert evaluation investigation method is used for checking the excavability of the weak position and the optimal excavation angle and judging whether the finite element calculation result is reasonable or not. And (3) weighting each scoring item, wherein the total weight is 10, and the score of each item is 1-10. And evaluating the rationality of the three-dimensional model, the rationality of the joints and the accuracy of lithology identification through expert investigation. Meanwhile, because the calculation of the finite element cannot fully consider various factors (such as groundwater condition, tunnel face supporting condition and the like) in the digging process, an expert is required to judge the optimal digging position and angle feasibility calculated by the finite element and provide a modification suggestion. And determining the optimal initial excavation position and excavation angle according to expert evaluation investigation conditions and suggestions, and establishing a deep learning data set by combining the face image.
In the following, a cantilever type heading machine is used for construction in a hydraulic tunnel excavation project. The average depth of the excavated burial is 120m. The on-site face cross-sectional image is shown in fig. 5 (a) below, and after the image semantic segmentation function is adopted, joint information and lithology information are identified from the face cross-sectional image (shown in fig. 5 (b) below). The information in table 1 can thus be obtained.
TABLE 1 face lithology
According to the lithology characteristics of the rock, the rock mass strength of the face is calculated:
σ1＝σ3+σcim
Wherein: σ 1 is the maximum principal stress; sigma 3 is the minimum principal stress, and the size is judged to be the minimum principal stress according to the image recognition combined with the equivalent Mohr-Coulomb criterion (The severity γ can be derived from lithology, about 23kN/m 3); σ ci is the uniaxial compressive strength of the rock and soil, and the average size of the lithology rock is 0.9Mpa; m is an influence coefficient reflected according to the three-dimensional joint characteristics, and the size is 1.5.
σ1＝σ3+σcim＝1.213+1.5×0.9＝2.563Mpa
If the traditional calculation method is adopted, the joints are counted first, and score evaluation is carried out by combining JCond89,89, and the result is shown in the following table 2:
TABLE 2 Joint-JCond 89 score table
RQD values were then determined based on the face joint density and the results are shown in Table 3 below:
TABLE 3 Joint RQD score Table
GSI value is calculated according to the formula:
calculating a maximum principal stress value according to the formula:
The calculation can be as follows: σ 3＝1.213Mpa,a＝0.5382,s＝0.000454,mb＝0.731,σ1 = 2.5476Mpa
Therefore, the rock-soil body mechanical parameters calculated by the novel method have smaller difference from the results calculated by the traditional method, but the calculation process is greatly simplified, so that the semantic segmentation is more effectively used for providing data support for the digital twin model and the finite element calculation, and the workload is greatly reduced.
On the other hand, the invention is illustrated by the angle of the device, and the method provided by the embodiment of the invention further comprises the following modules.
1. And a dust removal module: the module has the main function of achieving the effect of dust fall through the perceptively self-adaptive spraying device, thereby creating a working environment for the image acquisition device. The module mainly comprises an infrared sensor (sensing dust conditions), a water supply and storage device, a spraying device (adjusting a spraying mode, improving the spraying effect to save water), and a microcomputer controller (controlling the spraying amount and the spraying mode). The working schematic diagram 6 is as follows:
2. An illumination module: the module has the main function of providing a visual environment for the image acquisition device through a proper constant light source. Meanwhile, a stable light source is created for the image acquisition device so as to prevent the acquired image information from being interfered by brightness. The module mainly comprises a constant light source, a power supply cable and a control switch.
3. And an image acquisition module: the main function of the module is to collect the image data of the face and provide the image data for the semantic segmentation system to extract and mine the structural information of the face. Under the application condition, the main function is to collect the image data of the face and transmit the data back to the computer for judgment. The module mainly comprises a camera, an image feedback device, an image storage device, a power supply device and a controller.
Tof laser reconstruction module: the module has the main function of constructing a three-dimensional reconstruction model of the excavated tunnel in real time by scanning the excavated face. The module is mainly composed of a ToF laser scanner and a data processing computer.
5. The heading machine gesture sensing module is used for: the module is mainly used for obtaining the attitude information of the heading machine and transmitting the attitude information back to the computer for calculation and judgment.
6. Working state sensing module of the tunneling machine: the main function of the module is to obtain the working state information of the heading machine, such as cutting rate, cutting power, cylinder pressure, engine power and the like. And the obtained information is transmitted back to the computer to help the judgment of the tunneling strategy.
7. The optimal initial tunneling scheme display device module: the module has the main functions of displaying the obtained optimal initial excavation position and excavation angle of the face to operators in real time and providing various information for the operators for comprehensive judgment. The device mainly comprises a computer loaded with an artificial intelligent model, an image display and a laser indicator. The computer is mainly used for image processing of the face and running the artificial intelligent model, and is required to have certain computing and data processing capacity. The image display mainly provides the operator with a visualized optimal initial tunneling strategy and various auxiliary judgment information (such as the image shown in fig. 2). The laser indicator has the main function of directly marking the optimal excavation position on the actual face, so that operators can more intuitively excavate the face.
Fig. 7 is a flowchart of a method for acquiring a preferred excavation strategy in the embodiment of the present invention, as shown in fig. 7, in the embodiment provided by the present invention, through real-time three-dimensional reconstruction, acquiring a three-dimensional structure of a tunnel face, acquiring a tunnel face image (video), performing semantic segmentation on the image, acquiring a tunnel face structure face state, a joint form, a weak layer and lithology information of a rock formed by the weak layer, coupling the three-dimensional structure and the image, establishing a twin model of the tunnel face, adopting finite element simulation analysis and combining an expert investigation method, acquiring an optimal initial excavation strategy of the tunnel face, repeating the steps, establishing the tunnel face and a data set corresponding to the optimal initial excavation strategy, and training an artificial intelligent model, so that the artificial intelligent model can give an optimal initial excavation strategy according to the tunnel face working condition actually acquired.
The method provided by the embodiment of the invention has the following main beneficial effects:
1. Compared with the method that only the attitude information and the working state of the heading machine are concerned, and the operator judges the excavation strategy by himself, the technical scheme of the invention provides the optimal initial excavation strategy which is suitable for the state of the heading machine and is provided more reasonably and accurately by comprehensively considering the characteristics of the face and the working condition of the heading machine.
2. The excavation strategy is obtained more quickly and in real time. According to the artificial intelligence trained by a large amount of data, the optimal excavation strategy can be rapidly deduced according to the face image shot in real time. Compared with the existing scheme, the technical scheme of the invention is correspondingly more timely and more comprehensive in judgment, and saves a great amount of working time of construction first-line personnel.
3. The evaluation method based on the digital twin model deeply utilizes various monitoring data of the tunneling construction site, improves the utilization rate of the data, adopts an automatic collecting and processing module, reduces the application cost and widens the application scene of the method.
4. Compared with the traditional mining tunnel face joint information rapid digital identification and stability analysis method, the method has real-time performance. The stability of the face is judged by utilizing various instruments and equipment mainly before and after excavation by the traditional scheme, so that subsequent excavation is guided. The tool used by the scheme is simple and convenient, has high instantaneity, and can provide a required initial excavation scheme for site operators in real time.
The method comprises the following steps of establishing an intelligent real-time evaluation method for the weak part of the tunnel face of the cantilever type heading machine and setting main devices of the intelligent real-time evaluation method; technically forming a digital twin model based on three-dimensional reconstruction and image semantic recognition coupling, and forming a set of method by combining finite element calculation and an artificial intelligent model; the method is characterized in that the information of the structural face, the weak interlayer, the occurrence of joints and the like on the face in the tunneling process is considered in calculation, and constraint conditions such as the tunneling hole diameter, the size of a cantilever tunneling machine, the actual environmental working condition and the like are combined in application. Through the above, the state of the face is estimated in real time, and the proposal is put forward for tunneling, so that the tunneling speed of the tunnel is improved, and the failure rate and the safety risk rate of construction equipment are reduced.
Fig. 8 is a schematic diagram of an acquisition device of an mining strategy according to an embodiment of the present invention, and as shown in fig. 8, an embodiment of the present invention provides an acquisition device of a mining strategy, including:
a first obtaining module 81, configured to obtain three-dimensional image information of a working surface to be excavated;
The input/output module 82 is configured to input the three-dimensional image information into a mining strategy model, and output an initial mining strategy, where the mining strategy model is obtained by training a plurality of groups of samples, and each group of samples includes: historical three-dimensional image information and a corresponding historical mining strategy;
A second obtaining module 83, configured to obtain an excavation boundary condition through the environmental information and the device information;
the optimizing module 84 is configured to optimize the initial mining policy based on the mining boundary condition, and obtain the target mining policy.
As an embodiment of the present invention, the first acquisition module includes: the comparison unit is used for comparing the initial value in the initial mining strategy with the boundary value under the condition that the mining boundary condition comprises the boundary value, and adjusting the initial value in the initial mining strategy to be the target value under the condition that the boundary value is exceeded; the first acquisition unit acquires a target mining strategy based on the target value.
As one embodiment of the present invention, obtaining an mining strategy model includes: a second acquisition unit configured to acquire a plurality of pieces of history three-dimensional image information; a third acquisition unit for acquiring lithology information corresponding to the plurality of historical three-dimensional image information respectively; a fourth obtaining unit, configured to obtain a history mining policy corresponding to each of the plurality of lithology information; a fifth acquisition unit configured to acquire a plurality of history target mining policies based on the plurality of history mining policies; a sixth obtaining unit, configured to obtain a plurality of groups of samples through a plurality of history mining policies and a plurality of history three-dimensional images; and the seventh acquisition unit is used for performing deep learning training through a plurality of groups of samples to acquire an excavation strategy model.
As an embodiment of the present invention, the fifth acquisition unit further includes: the first acquisition subunit is used for acquiring scores corresponding to the plurality of history mining strategies respectively based on the evaluation information input by the external terminal; and the adjustment subunit is used for adjusting the corresponding historical mining strategies based on the scores to acquire a plurality of historical target mining strategies.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the acquisition method of the mining strategy when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the acquisition method of the mining strategy is realized when the computer program is executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the acquisition method of the mining strategy is realized when the computer program is executed by a processor.
Fig. 9 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, where, as shown in fig. 9, the electronic device includes: a processor (processor) 901, a memory (memory) 902, and a bus 903.
The processor 901 and the memory 902 perform communication with each other via the bus 903.
The processor 901 is configured to invoke the program instructions in the memory 902 to perform the methods provided by the method embodiments described above.
It will be appreciated by those skilled in the art that 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The method for acquiring the mining strategy is characterized by comprising the following steps:
Acquiring three-dimensional image information of a working surface to be excavated;
Inputting the three-dimensional image information into a mining strategy model, and outputting an initial mining strategy, wherein the mining strategy model is obtained through training of a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy;
Acquiring excavation boundary conditions through environment information and equipment information;
and optimizing the initial mining strategy based on the mining boundary conditions to obtain a target mining strategy.
2. The method of claim 1, wherein optimizing an initial mining strategy based on the mining boundary conditions, obtaining a target mining strategy, comprises:
Comparing the initial value in the initial mining strategy with the boundary value when the mining boundary condition comprises the boundary value, and adjusting the initial value in the initial mining strategy to be a target value when the initial value exceeds the boundary value;
and acquiring the target mining strategy based on the target value.
3. The method of claim 1, wherein obtaining the mining strategy model comprises:
Acquiring a plurality of historical three-dimensional image information;
Acquiring lithology information respectively corresponding to the plurality of historical three-dimensional image information;
acquiring a history mining strategy corresponding to each of the lithology information;
acquiring a plurality of historical target mining strategies based on the historical mining strategies;
Acquiring the plurality of groups of samples through a plurality of history mining strategies and the plurality of history three-dimensional images;
and performing deep learning training through the plurality of groups of samples to obtain the mining strategy model.
4. The method of claim 1, wherein obtaining the plurality of historical target mining policies based on a plurality of historical mining policies, further comprising:
Based on evaluation information input by an external terminal, obtaining scores respectively corresponding to a plurality of historical mining strategies;
and adjusting the corresponding historical mining strategies based on the scores to obtain a plurality of historical target mining strategies.
5. An acquisition device of an excavation strategy is characterized by comprising:
the first acquisition module is used for acquiring three-dimensional image information of the working surface to be excavated;
The input/output module is used for inputting the three-dimensional image information into a mining strategy model and outputting an initial mining strategy, wherein the mining strategy model is obtained through training a plurality of groups of samples, and each group of samples comprises: historical three-dimensional image information and a corresponding historical mining strategy;
The second acquisition module is used for acquiring mining boundary conditions through the environment information and the equipment information;
and the optimization module is used for optimizing the initial mining strategy based on the mining boundary condition and obtaining a target mining strategy.
6. The apparatus of claim 5, wherein the first acquisition module comprises:
The comparison unit is used for comparing the initial numerical value in the initial mining strategy with the boundary numerical value when the mining boundary condition comprises the boundary numerical value, and adjusting the initial numerical value in the initial mining strategy to be a target numerical value when the initial numerical value exceeds the boundary numerical value;
The first acquisition unit acquires the target mining strategy based on the target value.
7. The apparatus of claim 5, wherein obtaining the mining strategy model comprises:
A second acquisition unit configured to acquire a plurality of pieces of history three-dimensional image information;
A third acquisition unit for acquiring lithology information corresponding to the plurality of historical three-dimensional image information respectively;
A fourth obtaining unit, configured to obtain a history mining policy corresponding to each of the plurality of lithology information;
A fifth acquisition unit configured to acquire a plurality of history target mining policies based on the plurality of history mining policies;
a sixth obtaining unit, configured to obtain the plurality of groups of samples through a plurality of history mining policies and the plurality of history three-dimensional images;
and a seventh obtaining unit, configured to perform deep learning training through the multiple groups of samples, and obtain the mining strategy model.
8. The apparatus of claim 7, wherein the fifth acquisition unit further comprises:
the first acquisition subunit is used for acquiring scores corresponding to the plurality of history mining strategies respectively based on the evaluation information input by the external terminal;
and the adjustment subunit is used for adjusting the corresponding historical mining strategies based on the scores to acquire a plurality of historical target mining strategies.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 4 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410336790.4A CN118228584A (en) | 2024-03-22 | 2024-03-22 | Acquisition method and device of mining strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410336790.4A CN118228584A (en) | 2024-03-22 | 2024-03-22 | Acquisition method and device of mining strategy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118228584A true CN118228584A (en) | 2024-06-21 |
Family
ID=91513287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410336790.4A Pending CN118228584A (en) | 2024-03-22 | 2024-03-22 | Acquisition method and device of mining strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118228584A (en) |
-
2024
- 2024-03-22 CN CN202410336790.4A patent/CN118228584A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Deshmukh et al. | Roadheader–A comprehensive review | |
| Li et al. | Application and outlook of information and intelligence technology for safe and efficient TBM construction | |
| AU2013396723B2 (en) | Arrangement for controlling percussive drilling process | |
| WO2019042483A2 (en) | Tbm boring rock state real-time sensing system and method | |
| CN115773127A (en) | Intelligent decision-making method, system, equipment and medium for slurry balance shield | |
| CN113431581B (en) | Non-blasting mechanical intelligent mining method for deep hard rock ore body | |
| CN113505911B (en) | Cutter life prediction system based on automatic cruise and prediction method thereof | |
| KR102045263B1 (en) | Apparatus for predicting excavator failure and operating method thereof | |
| Liu et al. | Research progress and prospects of intelligent technology in underground mining of hard rock mines | |
| JP2000034890A (en) | Tbm facing, and method and device for evaluating peripheral geology at real time | |
| CN117556687A (en) | Tunnel blasting parameter determination method, system, electronic equipment and medium | |
| CN118228584A (en) | Acquisition method and device of mining strategy | |
| CN110806859A (en) | Modular drilling data monitoring and design system based on machine learning | |
| JP7492482B2 (en) | Shield tunneling machine tunneling prediction model | |
| JP7510768B2 (en) | Process discrimination system and process discrimination method | |
| JP6936845B2 (en) | Ground prediction system | |
| CN112652012A (en) | Intelligent control method, device and equipment for excavator, storage medium and excavator | |
| JP2022143625A (en) | Shield excavator construction management method | |
| CN110469334B (en) | Blasting system for blasting subway shield boulders and protruding rocks | |
| CN117287179B (en) | Remote control system and method for precision drilling and production equipment | |
| JP7412171B2 (en) | Teacher data generation device and teacher data generation method | |
| KR102193830B1 (en) | Apparatus and method for predicting front geological features based on indicatingtendency to change according to measuring data for a blind end in a tunnel | |
| US20220237534A1 (en) | Data processing system for construction machine | |
| Bye et al. | Geotechnical applications in open pit mining | |
| JP2022143626A (en) | General purpose learned model for initial excavation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |