CN113190934A - Optimization method and device of pick barrel drill and electronic equipment - Google Patents
Optimization method and device of pick barrel drill and electronic equipment Download PDFInfo
- Publication number
- CN113190934A CN113190934A CN202110649337.5A CN202110649337A CN113190934A CN 113190934 A CN113190934 A CN 113190934A CN 202110649337 A CN202110649337 A CN 202110649337A CN 113190934 A CN113190934 A CN 113190934A
- Authority
- CN
- China
- Prior art keywords
- cutting
- efficiency data
- cutting efficiency
- pick
- target
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 238000005520 cutting process Methods 0.000 claims abstract description 290
- 238000013499 data model Methods 0.000 claims abstract description 9
- 239000011435 rock Substances 0.000 claims description 72
- 230000015654 memory Effects 0.000 claims description 30
- 238000013528 artificial neural network Methods 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 25
- 238000005553 drilling Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 19
- 238000003062 neural network model Methods 0.000 claims description 16
- 239000000463 material Substances 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 13
- 239000000956 alloy Substances 0.000 claims description 12
- 229910045601 alloy Inorganic materials 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000003825 pressing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000004088 simulation Methods 0.000 description 22
- 230000036346 tooth eruption Effects 0.000 description 15
- 238000004364 calculation method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 9
- 238000010276 construction Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 238000003801 milling Methods 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 239000003292 glue Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000002679 ablation Methods 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- UONOETXJSWQNOL-UHFFFAOYSA-N tungsten carbide Chemical compound [W+]#[C-] UONOETXJSWQNOL-UHFFFAOYSA-N 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Earth Drilling (AREA)
Abstract
The invention provides a cutting tooth cylinder drill optimization method, a cutting tooth cylinder drill optimization device and electronic equipment. And finally, inputting a plurality of groups of target parameter combinations into the cutting efficiency data model to output to obtain corresponding target cutting efficiency data, and determining the optimal combination of the target parameter combinations according to the target cutting efficiency data.
Description
Technical Field
The invention relates to the technical field of construction of rotary drilling rigs, in particular to a method and a device for optimizing a cutting-tooth cylindrical drill and electronic equipment.
Background
In the current stage, no existing test and simulation method can directly obtain the optimal value for the arrangement of the cutting teeth in the rotary drilling cutting tooth cylinder drill, and the arrangement modes of the cutting teeth in all the construction sites are all determined by site construction because the rock layer hardness of all the construction sites is different, so that the cost is high, and the time consumption is long. The method for testing or simulating optimization of arrangement of cutting teeth in a rotary drilling cutting-tooth cylinder drill is difficult to develop because the efficiency of the rotary drilling rig is improved by reasonably arranging the cutting teeth, the joint optimization of the six factors of rock material, cutting tooth cutting angle, cutting tooth pressing depth (rotary drilling pressure), cutting tooth cutting speed (torque), cutting tooth size and transverse distance between two groups of cutting teeth needs to be considered, and due to the interaction effect between the factors, the single factor cannot represent the optimization scheme. Document CN111914372A discloses a crack propagation depth calculation method for single-tooth cutting, which does not consider the cutting tooth size and the transverse distance between two adjacent cutting teeth in the present study, and cannot realize the arrangement calculation of teeth. Moreover, the cutting efficiency of the cutting bit barrel drill is represented by the common performance of a plurality of results such as crack propagation and breakage of rock, work (related to oil consumption cost) done by a rotary drilling rig, specific cutting energy consumption, abrasion of cutting bits (tooth replacement time and money cost) and the like, the trend of each output is different, and each output result needs to be balanced to obtain an optimization scheme.
The existing test and simulation are aimed at single factor or single output result, and the optimization design of multiple input factors and multiple output results can not be carried out. In the existing single-cutting-pick rock cutting test, only the cutting of a corresponding rock sample can be obtained (the sample needs to be cut into huge blocks, the weight is at least 2 tons), the cutting angle analysis method is used for analyzing the influence of the cutting pick angle on the cutting, and the output only has the factors of the rock breaking and cutting work, the specific energy consumption and the like, and cannot output the rock crack expansion and the cutting pick loss.
Disclosure of Invention
In view of this, embodiments of the present invention provide a cutting pick barrel drill optimization method, device and electronic device, so as to solve the problems in the prior art.
In a first aspect, the present invention provides a method of optimizing a cutting pick barrel drill, comprising the steps of: acquiring various cutting parameters and corresponding various cutting efficiency data of a single-cutting-tooth cylindrical drill and a multi-cutting-tooth cylindrical drill; establishing a sample database, wherein the sample database comprises cutting parameter combinations and corresponding cutting efficiency data; building a neural network for training the sample data; collecting the sample database and inputting the sample database into the neural network for training to obtain a cutting efficiency model; inputting a plurality of groups of target parameter combinations into the cutting efficiency data model, outputting to obtain corresponding target cutting efficiency data, and correspondingly outputting various target cutting efficiency data by each group of target parameter combinations; and determining an optimal combination of the plurality of target parameter combinations from the target cutting efficiency data.
Further, the step of obtaining various cutting parameter combinations and corresponding cutting efficiency data of the single-cutting-tooth cylindrical drill and the multi-cutting-tooth cylindrical drill specifically comprises the following steps: building a cutting rock model of a single-cutting-tooth cylindrical drill and a multi-cutting-tooth cylindrical drill by a finite element analysis method; inputting a plurality of cutting parameters into the cutting rock model to obtain the cutting efficiency data.
Further, the pick barrel drill is a three-dimensional hexahedral mesh, and the rock model includes: a lagrangian mesh and a zero thickness cohesive mesh, a hybrid mesh of the zero thickness cohesive mesh interposed between the lagrangian meshes of adjacent three-dimensional tetrahedra.
Further, the plurality of cutting parameters includes: rock material, cutting angle of the cutting pick, pressing depth of the cutting pick, cutting speed of the cutting pick, size of the cutting pick and transverse distance between two adjacent cutting picks; the cutting efficiency data includes: the work done by the rotary drilling rig, the crushing volume of the rock, the specific cutting energy consumption, the loss of the alloy head part of the cutting pick, the loss of the tooth body part of the cutting pick and the crack propagation depth of the rock.
Further, in the step of acquiring the sample database and inputting the sample database into the neural network to train to obtain the cutting efficiency model, the method specifically comprises the following steps: constructing a sample set according to the sample database; randomly dividing the sample set into a training sample and a test sample; reading data in the training sample, and inputting the training sample into the neural network to execute training operation; adjusting the network parameter weight of the neural network in the training process to obtain a trained first neural network model; inputting the test sample into the first neural network model for verification operation to obtain a verification result; optimizing the first neural network model according to the verified result to obtain a cutting efficiency model.
Further, the step of inputting the test sample into the first neural network model for verification operation specifically includes the following steps: inputting X test samples to a first neural network model to obtain X first results; comparing the X first results with the cutting efficiency data of the X test samples, and counting the number Y of samples of which the absolute value of the difference between the first results and the cutting efficiency data is greater than a threshold value; and calculating a first verification result, wherein the calculated first verification result is the ratio of the number Y of the samples to the number X of the samples.
Further, the step of determining an optimal combination of the plurality of target parameter combinations according to the target cutting efficiency data specifically includes the steps of: respectively carrying out percentage conversion on the output multiple types of target cutting efficiency data; and carrying out weighted average according to preset weighted weight to obtain a weighted score, wherein the highest weighted score is the optimal combination.
In a second aspect, the present invention provides an optimisation device for a cutting pick barrel drill, comprising: the acquisition module is used for acquiring various cutting parameters and corresponding various cutting efficiency data of the single-cutting-tooth cylindrical drill and the multi-cutting-tooth cylindrical drill; the establishing module is used for establishing a sample database, and the sample database comprises cutting parameter combinations and corresponding cutting efficiency data; the building module is used for building a neural network for training the sample data; the acquisition module acquires the sample database and inputs the sample database into the neural network to train to obtain a cutting efficiency model; the input module inputs a plurality of groups of target parameter combinations into the cutting efficiency data model and outputs the target cutting efficiency data to obtain corresponding target cutting efficiency data, and each group of target parameter combinations correspondingly outputs various target cutting efficiency data; and a determination module that determines an optimal combination of the plurality of target parameter combinations according to the target cutting efficiency data.
In a third aspect, the present invention provides an electronic device comprising: the cutting bit barrel optimization method comprises a memory and a processor, wherein the memory and the processor are in communication connection with each other, computer instructions are stored in the memory, and the processor executes the computer instructions to execute the cutting bit barrel optimization method.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of optimizing a cutting pick barrel drill.
The technical scheme of the invention has the following advantages:
the invention provides an optimization method of a cutting tooth cylinder drill, which is characterized in that a neural network model is trained to obtain a cutting efficiency model by obtaining various cutting parameters of a single cutting tooth cylinder drill and a multi-cutting tooth cylinder drill and corresponding various cutting efficiency data. Inputting a plurality of groups of target parameter combinations into the cutting efficiency data model and outputting to obtain corresponding target cutting efficiency data, and determining the optimal combination of the plurality of target parameter combinations according to the target cutting efficiency data.
The combination of the multiple groups of target parameters simultaneously considers the mutual correlation effect among the multiple target parameters of the cutting bit barrel drilling of the rotary drilling rig, finally gives the optimized combination, and integrates the cutting efficiency data expressing different trends, different orders of magnitude and different units into one value. And moreover, a cutting efficiency trend graph and a table of specific input factors can be visually output, and the relationship between the cutting efficiency and the input factors can be visually represented.
The invention adopts a three-dimensional finite element method with cohesive force grids to simulate cutting pick cutting, and after the cohesive force grids are introduced, two failure modes of brittle fracture and plastic crushing of the rock can be shown respectively through the unit failure of the cohesive force grids and the common three-dimensional Lagrange grids stuck together by the cohesive force grids under the action of the action force. Because the rock cutting simulation has a large number of grids, a large number of contacts and a large calculation amount, the rock cutting simulation is not suitable for performing trial-and-error type simulation calculation with new input and a group of output recalculated. Therefore, in order to obtain an optimized result, a variable parameter database needs to be established first, and then model training processing is performed on the database result.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for optimizing a pick barrel drill provided in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a method for optimizing a pick barrel drill provided in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a single pick barrel drill cutting rock model provided in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of a multi-pick barrel drill cutting rock model provided in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram of a rotary drilling bit cutting barrel drill provided by the embodiment of the invention;
FIG. 6 is a flow chart of a method of optimizing a pick barrel drill provided in accordance with an embodiment of the present invention;
FIG. 7 is a user interface diagram of a software package provided in accordance with an embodiment of the present invention;
FIG. 8 is a flow chart of a method of optimizing a pick barrel drill provided in accordance with an embodiment of the present invention;
FIG. 9 is a graph of a single input factor provided in accordance with an embodiment of the present invention;
FIG. 10 is a graph of a plurality of input factors provided according to an embodiment of the present invention;
FIG. 11 is a block diagram of an apparatus for optimizing a pick barrel drill according to an embodiment of the present invention;
fig. 12 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1, the optimization method of a cutting pick cylindrical drill is a simulation method for optimizing the arrangement of the cutting pick cylindrical drill of a rotary drilling rig aiming at different geologies. Aiming at different geology, the parameter combination with the highest cutting efficiency can be obtained by one key, and the method is directly applied to a field construction site, so that time and cost are saved compared with a field construction site trial and error test. The optimization method comprises the following steps of S1-S6.
And S1, acquiring various cutting parameters of the single-cutting-pick cylindrical drill and the multi-cutting-pick cylindrical drill and various corresponding cutting efficiency data. As shown in fig. 2, the step of acquiring various cutting parameter combinations and corresponding cutting efficiency data of the single-cutting-pick cylindrical drill and the multi-cutting-pick cylindrical drill specifically includes the following steps S101 to S102.
S101, building a cutting rock model of a single-cutting-tooth cylindrical drill (shown in figure 3) and a multi-cutting-tooth cylindrical drill (shown in figure 4) through a finite element analysis method. The pick barrel drill is a three-dimensional hexahedral mesh (as shown in fig. 5), and the rock model includes: a lagrangian mesh and a zero thickness cohesive mesh, a hybrid mesh of the zero thickness cohesive mesh interposed between the lagrangian meshes of adjacent three-dimensional tetrahedra. For the mesh of the rock model, because the cohesive mesh is a mesh that behaves like a "glue" that is equivalent to zero thickness of the bonded normal cells. Once the 'glue' grid fails, the two adjacent common rock units are separated, and rock cracking is indicated. Whereas failure of a normal three-dimensional tetrahedral rock lattice under further barrel drilling cutting indicates fragmentation of the rock. Therefore, the rock cutting model can show two failure modes of brittle fracture and plastic crushing of the rock at the same time, and is suitable for showing the rock cutting efficiency of the rotary drilling bit.
S102, inputting various cutting parameters into the cutting rock model to obtain the cutting efficiency data.
The plurality of cutting parameters includes: rock material, cutting angle of the cutting pick, pressing depth of the cutting pick, cutting speed of the cutting pick, size of the cutting pick and transverse distance between two adjacent cutting picks; the cutting efficiency data includes: the work done by the rotary drilling rig, the crushing volume of the rock, the specific cutting energy consumption, the loss of the alloy head part of the cutting pick, the loss of the tooth body part of the cutting pick and the crack propagation depth of the rock. The rock material comprises rock compressive strength and rock types.
A method for calculating cutting efficiency data in a cutting rock model is provided as follows:
1. regarding the cutting work: the method obtained is the integral of the tangential force (using the reaction force experienced by the pick in the finite element results) over the path of the cutting length.
2. Cutting the volume of rock: counting a volume list of the units with the overall displacement value range of [0,1] of the rock units before and after cutting (if the displacement is in the interval, the rock which is not separated from the main body is judged, and if the displacement is outside the interval, the rock units scattered in the graph are obtained); the numbers of rock units before and after cutting are compared, and the sum of the volumes before cutting of the numbers of rock units which are scattered and cannot be corresponded is the cut rock volume.
3. Milling specific energy consumption: the value of the cutting work divided by the volume of the cut rock is given by the following formula:
4. Loss of pick alloy head section: because the rock part of the cutting simulation adopts the cohesive force unit, the whole simulation model is large, and the cutting pick part uses a rigid body model in the cutting simulation. The rigid body itself is undamaged, but the contact force experienced by all surface nodes of a rigid body pick at each time step can be derived from the cutting simulation. The contact force is extracted, a flexible body simulation model of the cutting pick is established independently, and the contact force is given as node force of each time step node of all surface nodes in the XYZ direction respectively. The alloy bit was given a standard WC (tungsten carbide) material and the unit of failure in the calculation was the loss of the pick alloy head. And outputting a volume list of effective units of the alloy drill bit before and after simulation, and comparing the unit numbers before and after simulation, wherein the sum of the volume before simulation of the unit numbers incapable of corresponding is the loss volume of the alloy drill bit.
5. Loss of pick body portion: the specific method is the same as the loss calculation mode of the alloy bit part of the cutting pick, and the tooth body part is endowed with standard 42CrMo steel material.
6. Obtaining the crack propagation depth of the rock, namely obtaining the pixel point ratio of the cohesion grids on the cutting path before cutting and after cutting, the area of the cohesion grids on the cutting path before cutting and the length of the cutting path; determining the area of the cohesion grid on the cutting path after cutting according to the pixel point ratio and the area of the cohesion grid on the cutting path before cutting; determining the crack propagation depth according to the area difference of the cohesive force grids on the cutting path before and after cutting and the length of the cutting path.
S2, establishing a sample database, wherein the sample database comprises cutting parameter combinations and corresponding cutting efficiency data. Because the single-tooth cutting rock simulation model is smaller than the multi-tooth cutting rock simulation model and has higher calculation speed, the cutting efficiency of other factors can be obtained by simulating the single-tooth cutting rock except that the multi-tooth cutting simulation is needed in consideration of the transverse spacing of the cutting teeth. The simulation of cutting the rock by the single cutting pick can analyze five factors of the rock material, the cutting angle of the cutting pick, the pressing depth of the cutting pick (the stress of the rotary drilling), the cutting speed (the torque) of the cutting pick and the size of the cutting pick. The multi-cutting-pick cutting simulation can analyze two factors of rock materials and the transverse distance between two groups of cutting picks. Aiming at the condition of the same rock material, the cutting of the single cutting pick is equivalent to the condition that the transverse distance between two groups of cutting picks in the multiple cutting picks is 50mm (the distance between two adjacent groups of cutting picks is the farthest, and the interference influence between the two groups of cutting picks is avoided), so that the cutting efficiency data results of the single cutting pick and the multiple cutting picks can be related in a database.
And S3, building a neural network for training the sample data. Artificial Neural Networks (ans), also referred to as Neural Networks (NNs) or Connection models (Connection models), are algorithmic mathematical models that Model animal Neural network behavior characteristics and perform distributed parallel information processing. The network achieves the aim of processing information by adjusting the mutual connection relationship among a large number of nodes in the network depending on the complexity of the system.
And S4, collecting the sample database and inputting the sample database into the neural network to train to obtain a cutting efficiency model.
As shown in fig. 6, the step of acquiring the sample database and inputting the sample database into the neural network to train to obtain the ablation efficiency model specifically includes the following steps S401 to S406.
S401, constructing a sample set according to the sample database.
S402, randomly dividing the sample set into training samples and testing samples.
And S403, reading data in the training sample, and inputting the training sample into the neural network to execute training operation.
S404, adjusting the network parameter weight of the neural network in the training process to obtain a trained first neural network model.
S405, inputting the test sample into the first neural network model for verification operation to obtain a verification result. Step S405 specifically includes the following steps: s4051, inputting X test samples to the first neural network model, and obtaining X first results; s4052, comparing the X first results with the cutting efficiency data of the X test samples, and counting the number Y of samples of which the absolute value of the difference between the first results and the cutting efficiency data is greater than a threshold value; s4053, calculating a first verification result, wherein the first verification result is the ratio of the number Y of the samples to the number X of the samples.
S406, optimizing the first neural network model according to the verified result to obtain a cutting efficiency model.
And S5, inputting a plurality of groups of target parameter combinations into the cutting efficiency data model, outputting to obtain corresponding target cutting efficiency data, and correspondingly outputting various target cutting efficiency data by each group of target parameter combinations.
The output result of the invention can obtain six results of the work done by the rotary drilling rig, the rock crushing volume, the specific cutting energy consumption, the loss of the alloy head part of the cutting pick, the loss of the tooth body part of the cutting pick and the crack propagation depth of the rock. The invention can also encapsulate the output result into visualization software (as shown in fig. 7), which visually corresponds to the visualization of the input target parameters and the output result. However, the trends of the six output results are not the same, for example, the rotary drilling rig is advantageous in that it performs less work and consumes less energy, but the rotary drilling rig is disadvantageous in that the volume of rock to be crushed is small and the crack of the rock is expanded shallowly. And the magnitude and unit of all output results are different, so that the following steps are required for uniform processing of quantization.
And S6, determining the optimal combination in the target parameter combinations according to the target cutting efficiency data.
As shown in fig. 8, the step of determining the optimal combination of the plurality of target parameter combinations based on the target cutting efficiency data specifically includes the following steps S601 to S602.
S601, performing percentage conversion on the output various cutting efficiency data respectively.
S602, carrying out weighted average according to preset weighted weight to obtain a weighted score, wherein the highest weighted score is the optimal combination.
In this embodiment, the six output results are first subjected to percentage conversion, respectively. Then, a proportional decision factor (i.e., a weighted weight) is introduced to calculate a weighted total score, and the six results are combined into a weighted score to represent the cutting efficiency (shown in fig. 7). For example, in an embodiment excavation scenario, increasing pressure on the barrel drill regardless of oil consumption and regardless of pick damage, then both rock volume and crack propagation depth can be weighted more heavily, while cutting work, specific power consumption, and damage volume of the pick alloy head and pick body can be weighted less heavily. Generally, considering that the time for replacing the teeth of the drum drill is long when the drum drill is lifted out of the ground (the cutting teeth are originally consumables, but the cost for purchasing the cutting teeth is increased when the cutting teeth are replaced too frequently, and importantly, the cutting teeth generate heat due to friction and the time for replacing the teeth and replacing the teeth under the high-temperature condition influences the overall efficiency), the cutting power, the specific power consumption and the damage volume of the alloy head and the tooth body of the cutting teeth need to be set with larger weights.
In this embodiment, step S5 further has a function of traversing data, which respectively traverses other target parameters except for the rock material, so as to obtain corresponding cutting efficiency data, and the reason why the rock material is excluded is that once the construction site is determined, the rock material value is fixed. Taking a single input factor in the target parameter combination as an example, fixing other five input factors, traversing data of the single input factor to be analyzed, drawing a cutting efficiency graph (fig. 9) of the single factor, wherein the horizontal axis is the input factor (Degree, cutting angle of a cutting tooth), the vertical axis is the cutting efficiency (Score), the peak cutting efficiency of the curve is the highest, and finding the input factor of the horizontal axis corresponding to the peak value shows that the cutting efficiency is high in the range around the value.
As shown in fig. 10, in this embodiment, four input factors in the target parameter combination may also be fixed, and a three-dimensional graph may be drawn by traversing two input factors (depth, cutting angle of cutting teeth; Distance of CT (mm), lateral Distance between two adjacent cutting teeth), so that the cutting efficiency at the valley of the curved surface is low, and the cutting efficiency at the peak of the curved surface is high, which may be used to study the optimal combination of the two input factors. When the graph is drawn, the output data result is presented in an excel (one key in fig. 7 can be exported), so that the subsequent accurate comparison can be facilitated. By adopting the method, the optimal cutting tooth arrangement method suitable for the corresponding construction site (rock material) can be assembled by combining every two cutting teeth for several times.
The invention provides an optimization method of a cutting tooth cylinder drill, which is characterized in that a neural network model is trained to obtain a cutting efficiency model by obtaining various cutting parameters of a single cutting tooth cylinder drill and a multi-cutting tooth cylinder drill and corresponding various cutting efficiency data. Inputting a plurality of groups of target parameter combinations into the cutting efficiency data model and outputting to obtain corresponding target cutting efficiency data, and determining the optimal combination of the plurality of target parameter combinations according to the target cutting efficiency data.
The combination of the multiple groups of target parameters simultaneously considers the mutual correlation effect among the multiple target parameters of the cutting bit barrel drilling of the rotary drilling rig, finally gives the optimized combination, and integrates the cutting efficiency data expressing different trends, different orders of magnitude and different units into one value. And moreover, a cutting efficiency trend graph and a table of specific input factors can be visually output, and the relationship between the cutting efficiency and the input factors can be visually represented.
The invention adopts a three-dimensional finite element method with cohesive force grids to simulate cutting pick cutting, and after the cohesive force grids are introduced, two failure modes of brittle fracture and plastic crushing of the rock can be shown respectively through the unit failure of the cohesive force grids and the common three-dimensional Lagrange grids stuck together by the cohesive force grids under the action of the action force. Because the rock cutting simulation has a large number of grids, a large number of contacts and a large calculation amount, the rock cutting simulation is not suitable for performing trial-and-error type simulation calculation with new input and a group of output recalculated. Therefore, in order to obtain an optimized result, a variable parameter database needs to be established first, and then model training processing is performed on the database result.
Example 2
As shown in fig. 11, the present invention also provides an optimization device for a cutting pick barrel drill, comprising: the device comprises an acquisition module 11, a building module 12, a building module 13, a collection module 14, an input module 15 and a determination module 16.
The obtaining module 11 is used for obtaining various cutting parameters of the single-cutting-tooth cylindrical drill and the multi-cutting-tooth cylindrical drill and various corresponding cutting efficiency data.
The establishing module 12 is configured to establish a sample database, where the sample database includes cutting parameter combinations and the corresponding cutting efficiency data.
The building module 13 is used for building a neural network for training the sample data.
The acquisition module 14 is configured to acquire the sample database and input the sample database into the neural network to train to obtain a cutting efficiency model.
The input module 15 is configured to input a plurality of sets of target parameter combinations into the cutting efficiency data model, output the target cutting efficiency data to obtain corresponding target cutting efficiency data, and output a plurality of target cutting efficiency data corresponding to each set of target parameter combinations.
The determination module 16 is configured to determine an optimal combination of the plurality of combinations of target parameters according to the target cutting efficiency data.
In this embodiment, there is also provided an optimized device for a cutting pick barrel drill, which is used for implementing the above embodiments and preferred embodiments, and which has already been described and will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
The cutting pick barrel optimization apparatus in this embodiment is in the form of a functional unit, where the unit is an ASIC circuit, a processor and memory executing one or more software or fixed programs, and/or other devices that can provide the above-described functionality.
Further functional descriptions of the modules are the same as those of the corresponding embodiments, and are not repeated herein.
An embodiment of the present invention further provides an electronic device, which has the authentication apparatus for accessing the network shown in fig. 11.
Referring to fig. 12, fig. 12 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, where the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit), at least one communication interface 53, memory 54, at least one communication bus 52. Wherein a communication bus 52 is used to enable the connection communication between these components. The communication interface 53 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 53 may also include a standard wired interface and a standard wireless interface. The Memory 54 may be a high-speed RAM Memory (volatile Random Access Memory) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 54 may alternatively be at least one memory device located remotely from the processor 51. Wherein the processor 51 may be in connection with the apparatus described in fig. 11, the memory 54 stores an application program, and the processor 51 calls the program code stored in the memory 54 for performing any of the above-mentioned method steps.
The communication bus 52 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 52 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 12, but this is not intended to represent only one bus or type of bus.
The memory 54 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated: HDD) or a solid-state drive (english: SSD); the memory 54 may also comprise a combination of the above types of memories.
The processor 51 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor 51 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 54 is also used to store program instructions. The processor 51 may invoke program instructions to implement the cutting pick barrel optimization method as shown in the present invention.
The embodiment of the invention also provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the cutting pick barrel drill optimization method in any method embodiment. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A cutting pick barrel drill optimization method is characterized by comprising the following steps:
acquiring various cutting parameters and corresponding various cutting efficiency data of a single-cutting-tooth cylindrical drill and a multi-cutting-tooth cylindrical drill;
establishing a sample database, wherein the sample database comprises cutting parameter combinations and corresponding cutting efficiency data;
building a neural network for training the sample data;
collecting the sample database and inputting the sample database into the neural network for training to obtain a cutting efficiency model;
inputting a plurality of groups of target parameter combinations into the cutting efficiency data model, outputting to obtain corresponding target cutting efficiency data, and correspondingly outputting various target cutting efficiency data by each group of target parameter combinations; and
determining an optimal combination of the plurality of target parameter combinations from the target cutting efficiency data.
2. The method for optimizing a cutting pick barrel drill according to claim 1, wherein the step of obtaining a plurality of cutting parameter combinations and corresponding cutting efficiency data of the single cutting pick barrel drill and the multiple cutting pick barrel drill specifically comprises the steps of:
building a cutting rock model of a single-cutting-tooth cylindrical drill and a multi-cutting-tooth cylindrical drill by a finite element analysis method; and
inputting a plurality of cutting parameters into the cutting rock model to obtain the cutting efficiency data.
3. The cutting pick barrel drill optimization method of claim 2, wherein the cutting pick barrel drill is a three-dimensional hexahedral mesh, the rock model comprising: a lagrangian mesh and a zero thickness cohesive mesh, a hybrid mesh of the zero thickness cohesive mesh interposed between the lagrangian meshes of adjacent three-dimensional tetrahedra.
4. The method of optimizing a cutting pick barrel drill according to claim 1, wherein the plurality of cutting parameters includes: rock material, cutting angle of the cutting pick, pressing depth of the cutting pick, cutting speed of the cutting pick, size of the cutting pick and transverse distance between two adjacent cutting picks;
the cutting efficiency data includes: the work done by the rotary drilling rig, the crushing volume of the rock, the specific cutting energy consumption, the loss of the alloy head part of the cutting pick, the loss of the tooth body part of the cutting pick and the crack propagation depth of the rock.
5. The cutting pick barrel drill optimization method according to claim 1, wherein in the step of collecting the sample database and inputting the sample database into the neural network to train and obtain the cutting efficiency model, the method specifically comprises the following steps:
constructing a sample set according to the sample database;
randomly dividing the sample set into a training sample and a test sample;
reading data in the training sample, and inputting the training sample into the neural network to execute training operation;
adjusting the network parameter weight of the neural network in the training process to obtain a trained first neural network model;
inputting the test sample into the first neural network model for verification operation to obtain a verification result;
optimizing the first neural network model according to the verified result to obtain a cutting efficiency model.
6. The cutting pick barrel drill optimization method according to claim 5, wherein the step of inputting the test sample into the first neural network model for validation includes the following steps:
inputting X test samples to a first neural network model to obtain X first results;
comparing the X first results with the cutting efficiency data of the X test samples, and counting the number Y of samples of which the absolute value of the difference between the first results and the cutting efficiency data is greater than a threshold value;
and calculating a first verification result, wherein the calculated first verification result is the ratio of the number Y of the samples to the number X of the samples.
7. The method of claim 1, wherein the step of determining the optimum combination of the plurality of combinations of target parameters from the target cutting efficiency data includes the steps of:
respectively carrying out percentage conversion on the output multiple types of target cutting efficiency data;
and carrying out weighted average according to preset weighted weight to obtain a weighted score, wherein the highest weighted score is the optimal combination.
8. An optimization device for a cutting pick barrel drill, comprising:
the acquisition module is used for acquiring various cutting parameters and corresponding various cutting efficiency data of the single-cutting-tooth cylindrical drill and the multi-cutting-tooth cylindrical drill;
the establishing module is used for establishing a sample database, and the sample database comprises cutting parameter combinations and corresponding cutting efficiency data;
the building module is used for building a neural network for training the sample data;
the acquisition module acquires the sample database and inputs the sample database into the neural network to train to obtain a cutting efficiency model;
the input module inputs a plurality of groups of target parameter combinations into the cutting efficiency data model and outputs the target cutting efficiency data to obtain corresponding target cutting efficiency data, and each group of target parameter combinations correspondingly outputs various target cutting efficiency data; and
a determination module that determines an optimal combination of the plurality of target parameter combinations according to the target cutting efficiency data.
9. An electronic device, comprising:
a memory and a processor communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of optimizing a cutting pick barrel drill of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a computer to perform the method of optimization of a cutting pick barrel drill of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110649337.5A CN113190934B (en) | 2021-06-10 | 2021-06-10 | Optimization method and device for cutting pick barrel drill and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110649337.5A CN113190934B (en) | 2021-06-10 | 2021-06-10 | Optimization method and device for cutting pick barrel drill and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113190934A true CN113190934A (en) | 2021-07-30 |
| CN113190934B CN113190934B (en) | 2024-07-30 |
Family
ID=76976514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110649337.5A Active CN113190934B (en) | 2021-06-10 | 2021-06-10 | Optimization method and device for cutting pick barrel drill and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190934B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116673A (en) * | 2013-02-04 | 2013-05-22 | 陈慧群 | Predictive method of milling machining surface form |
| US20190012414A1 (en) * | 2017-07-04 | 2019-01-10 | Rockfield Software Limited | Modeling Sand Production |
| CN111369982A (en) * | 2020-03-13 | 2020-07-03 | 北京远鉴信息技术有限公司 | Training method of audio classification model, audio classification method, device and equipment |
| CN111914372A (en) * | 2020-08-17 | 2020-11-10 | 北京三一智造科技有限公司 | Crack propagation depth calculation method and device and electronic equipment |
| CN112419271A (en) * | 2020-10-27 | 2021-02-26 | 深圳市深光粟科技有限公司 | Image segmentation method and device and computer readable storage medium |
| CN112459765A (en) * | 2020-12-08 | 2021-03-09 | 北京三一智造科技有限公司 | System and method for collecting load data of rotary drilling tool |
-
2021
- 2021-06-10 CN CN202110649337.5A patent/CN113190934B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116673A (en) * | 2013-02-04 | 2013-05-22 | 陈慧群 | Predictive method of milling machining surface form |
| US20190012414A1 (en) * | 2017-07-04 | 2019-01-10 | Rockfield Software Limited | Modeling Sand Production |
| CN111369982A (en) * | 2020-03-13 | 2020-07-03 | 北京远鉴信息技术有限公司 | Training method of audio classification model, audio classification method, device and equipment |
| CN111914372A (en) * | 2020-08-17 | 2020-11-10 | 北京三一智造科技有限公司 | Crack propagation depth calculation method and device and electronic equipment |
| CN112419271A (en) * | 2020-10-27 | 2021-02-26 | 深圳市深光粟科技有限公司 | Image segmentation method and device and computer readable storage medium |
| CN112459765A (en) * | 2020-12-08 | 2021-03-09 | 北京三一智造科技有限公司 | System and method for collecting load data of rotary drilling tool |
Non-Patent Citations (4)
| Title |
|---|
| WEI MA等: "The finite element analysis–based simulation and artificial neural network–based prediction for milling processes of aluminum alloy 7050", PROC IMECHE PART B: J ENGINEERING MANUFACTURE, vol. 235, no. 1, 1 July 2020 (2020-07-01), pages 265 * |
| 张雯娟: "模具数控加工切削用量智能化研究", 中国优秀硕士学位论文全文数据库, no. 5, 15 May 2007 (2007-05-15), pages 21 - 43 * |
| 赵斌等: "基于零件摩擦学性能的磨削参数优化", 浙江大学学报（工学版）, vol. 52, no. 1, 31 January 2018 (2018-01-31), pages 16 - 23 * |
| 阮强;左卫东;邱红臣;: "旋挖钻机筒式钻头强度分析及优化设计", 煤矿机械, vol. 34, no. 01, 15 January 2013 (2013-01-15), pages 39 - 41 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113190934B (en) | 2024-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Koopialipoor et al. | Predicting tunnel boring machine performance through a new model based on the group method of data handling | |
| Wang et al. | Modeling of brittle rock failure considering inter-and intra-grain contact failures | |
| CN106778010B (en) | TBM cutter life prediction method based on data-driven support vector regression machine | |
| Kita et al. | Rapid post-earthquake damage localization and quantification in masonry structures through multidimensional non-linear seismic IDA | |
| CN111860952B (en) | Method for rapidly optimizing key mining parameters of outburst coal seam | |
| Liu et al. | Numerical studies on bit-rock fragmentation mechanisms | |
| Azocar | Investigating the mesh dependency and upscaling of 3D grain-based models for the simulation of brittle fracture processes in low-porosity crystalline rock | |
| CN111091310B (en) | Excavation equipment health monitoring system and method | |
| Tian et al. | The effect of ICA and PSO on ANN results in approximating elasticity modulus of rock material | |
| CN114372319A (en) | Rock cuttability evaluation method based on mining-following parameters and/or drilling parameters, rock breaking equipment and rock breaking system | |
| CN106997334A (en) | One kind is based on time-weighted mine pressure data handling system and method | |
| Rajabi et al. | Studying the deformation and stability of rock mass surrounding the power station caverns using NA and GEP models | |
| CN113190934A (en) | Optimization method and device of pick barrel drill and electronic equipment | |
| CN115705454A (en) | Crack propagation simulation fracturing design optimization method based on phase field method | |
| CN116226982B (en) | Cohesive soil-rock tunnel excavation coupling numerical method | |
| Zhao et al. | A Study on the Dynamic Transmission Law of Spiral Drum Cutting Coal Rock Based on ANSYS/LS‐DYNA Simulation | |
| CN114862071B (en) | Method, device and equipment for predicting reaming torque of horizontal directional drilling and storage medium | |
| Zhou et al. | Rock chip properties of TBM penetration in jointed rock masses based on an improved DICE2D simulation | |
| CN116432494A (en) | Nonlinear strength reduction method and device for slope stability evaluation | |
| CN116611262A (en) | Correction method for grading tunnel surrounding rock and related equipment | |
| Yang et al. | Computation and analysis of high rocky slope safety in a water conservancy project | |
| US20220156429A1 (en) | Cutter and Drill Bit Design by Virtual Testing with Digitized Rocks | |
| CN115659744A (en) | Geological parameter real-time sensing method based on geological and equipment coupling simulation | |
| Zhang et al. | A study on pick cutting properties with full-scale rotary cutting experiments and numerical simulations | |
| CN111914372B (en) | Crack propagation depth calculation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |