CN116992770A - Wall protection control blasting method based on GOA-DBN neural network - Google Patents
Wall protection control blasting method based on GOA-DBN neural network Download PDFInfo
- Publication number
- CN116992770A CN116992770A CN202310985541.3A CN202310985541A CN116992770A CN 116992770 A CN116992770 A CN 116992770A CN 202310985541 A CN202310985541 A CN 202310985541A CN 116992770 A CN116992770 A CN 116992770A
- Authority
- CN
- China
- Prior art keywords
- goa
- blasting
- dbn
- detonation
- energy
- 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
- 238000005422 blasting Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 16
- 239000003814 drug Substances 0.000 claims abstract description 26
- 230000000694 effects Effects 0.000 claims abstract description 22
- 239000011358 absorbing material Substances 0.000 claims abstract description 18
- 238000005474 detonation Methods 0.000 claims description 41
- 230000000903 blocking effect Effects 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 18
- 229940079593 drug Drugs 0.000 claims description 16
- 230000002093 peripheral effect Effects 0.000 claims description 15
- 230000001186 cumulative effect Effects 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 10
- 239000002360 explosive Substances 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000004880 explosion Methods 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 6
- 230000005641 tunneling Effects 0.000 claims description 6
- 238000005553 drilling Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims 2
- 239000011435 rock Substances 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Abstract
The invention provides a wall protection control blasting method based on a GOA-DBN neural network, which is more accurate in blasting effect prediction, so that tunnel blasting parameters are reversely optimized, a multi-medium energy-collecting wall protection medicine bag can adjust energy collecting and wall protection angles, and the wall protection control blasting method and the multi-medium energy-collecting wall protection medicine bag act together, so that vibration impact on surrounding rocks of a contour is reduced, stability of the surrounding rocks of the contour is protected as much as possible, self-stabilizing capacity of the wall protection medicine bag is enhanced, meanwhile, the time for a field worker to paste energy absorbing materials can be reduced due to adjustable wall protection angles, the wall protection medicine bag is directly prefabricated and formed, the angle is directly adjusted to be filled into a blast hole, and charging time is saved.
Description
Technical Field
The invention relates to the technical field of tunnel blasting construction, in particular to a wall protection control blasting method based on a GOA-DBN neural network.
Background
With the gradual implementation of the western large development strategy, the gravity center of highway and railway engineering construction gradually turns to the western mountain area, and the tunnel passes through the soft rock geological area when the tunnel is subjected to a plurality of soft rock tunnel engineering, so that great difficulty is brought to tunnel construction. The soft rock is the most common bad geology in tunnel construction, is also an important factor influencing the stability of surrounding rock of the tunnel, is in a stable state under the normal condition, and can be destroyed when being influenced by external forces such as blasting, excavation and the like, so that engineering accidents such as collapse, roof fall and the like occur.
Among the numerous construction methods of tunnels (shield, TBM, open cut, semi-open cut, etc.), the drill-burst method occupies the most important position in the tunnel construction process due to lower cost and higher tunneling efficiency. The blasting is controlled by facing the protection wall which needs to protect the outline surrounding rock, and the directional vibration control is needed in the blasting process. The explosion energy is fully utilized, the crushing block degree is improved, and the explosion vibration is reduced to the maximum extent.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a wall protection control blasting method of a multi-medium energy-gathering wall protection cartridge based on a GOA-DBN neural network. Aims to solve the problem of reducing the damage to the periphery during drilling and blasting construction.
The technical scheme adopted by the invention is as follows:
a wall protection control blasting method based on GOA-DBN neural network comprises the following steps:
step S1: designing blasting parameters;
step S2: establishing a GOA-DBN blasting effect prediction model;
step S3: predicting the vibration speed of the blasting parameters in the step S1 by adopting the GOA-DBN blasting effect prediction model in the step S2;
step S4: checking a vibration speed prediction result;
step S5: taking the explosion parameters which are qualified in inspection as construction explosion parameters;
step S6: measuring a lofting hole, and drilling and filling the hole to be blocked;
step S7: blasting and checking blasting effect.
In the technical scheme, the GOA-DBN blasting effect prediction model establishment process is as follows:
step S201: establishing a blasting effect database
Selecting the drug loading quantity of the cutting eye, tunneling the drug loading quantity of the eye, assisting the drug loading quantity of the eye and the drug loading quantity of the peripheral eye; taking the eye drug loading amount of the bottom plate as an input variable and the vibration speed as an output variable to construct a data set;
step S202: initializing DBN model parameters and GOA algorithm parameters;
step S203: optimizing the hidden layer number and the learning rate of the DBN model by using a GOA algorithm, and outputting particles with proper fitness as initial parameters of the DBN model;
step S204: and inputting the blasting effect data set into the DBN model for training, and outputting the GOA-DBN blasting effect prediction model.
In the above technical solution, further, the elimination of the correlation of a plurality of main influencing factors among factors is performed on the data set constructed in step S201, and the specific steps are as follows:
a. the data preprocessing is carried out by adopting a 'mapmin max' normalization formula, and the formula is as follows:
wherein: y is max Is the maximum value of the normalized data; y is min The minimum value of the data after normalization processing; x is x max Is the maximum value of the data before normalization processing; x is x min The minimum value of the data before normalization processing;
the range of the processed data is [ -1,1], and the formula (1) can be simplified as follows:
b. constructing an observation data matrix, providing an overall U with n samples (U 1 ,U 2 ,U 3 ,…U n ) Each sample has m dimensions, m>n. I.e. the observation data matrix can be represented by formula (3):
c. the correlation coefficient matrix is constructed and can be represented by the following formulas (4) and (5):
wherein: u (u) ki 、u kj Representing u, t in the observation data matrix ij Representing the correlation coefficient, calculating the correlation coefficient between two different elements, i, j E [1, n ]]And j=i, t ij ＝1；
d. Calculating eigenvalue and eigenvector of correlation coefficient matrix T
From the characteristic equation: i T-lambda I P The eigenvalue λ can be calculated by =0 1 ≥λ 2 ≥…≥λ n Not less than 0 and feature vector e 1 ,e 2 ,…e n The method comprises the steps of carrying out a first treatment on the surface of the IP represents an n-order identity matrix;
e. the principal component expression can be represented by formula (6):
wherein: l is less than or equal to n;
f. the calculated contribution rate and the cumulative contribution rate can be represented by the formulas (7), (8):
lambda in the above i Indicating the characteristic value of the i-th principal component,representing the total eigenvalue cumulative sum,/->Representing the cumulative sum of the characteristic values of the s principal components; if the cumulative value of the contribution rates of the first P variables is greater than 85%, the first P principal components are considered to be capable of representing all variable information, and the first P principal components are taken as a data set for analysis.
In the above technical solution, further, the checking process of step S4 includes comparing the predicted result of the vibration speed in step S3 with the limited vibration speed, if v > v max Redesign until the vibration speed prediction results meet the requirements, i.e. v.ltoreq.v max And outputting the blasting parameter of the predicted result as the tunnel blasting parameter.
In the above technical scheme, further, the traditional Chinese medicine package in step S6 adopts a multi-medium energy-gathering wall-protecting medicine package, which comprises
The detonation blocking pipe is of a cylinder structure;
the medium fixing tube is wrapped on the outer side of the detonation obstructing tube and is of a half-arc structure, and two ends of the half-arc structure are clamped with the detonation obstructing tube;
the energy absorbing material is embedded on the cambered surface of the medium fixing pipe;
the explosive is filled in the cylinder body of the detonation blocking pipe, and the end part of the explosive is limited by the energy gathering cover.
In the above technical scheme, further, the two ends of the medium fixing tube are connected with the detonation blocking tube through the limiters, and air is used between the inner wall of the medium fixing tube and the outer wall of the detonation blocking tube.
In the above technical scheme, further, a plurality of equally spaced detonation blocking tube limiting grooves are formed in the outer peripheral wall of the detonation blocking tube, symmetrical medium fixing tube limiting grooves are formed in the inner walls of the two ends of the medium fixing tube, the top of the limiter is located in the medium fixing tube limiting groove, the bottom of the limiter is located in the detonation blocking tube limiting groove, and the angle of the protective wall is changed by adjusting the different detonation blocking tube limiting grooves located on the detonation blocking tube at the bottom of the limiter.
In the above technical scheme, further, a plurality of groups of equidistant energy gathering cover limiting grooves are formed in the inner peripheral wall of the detonation blocking pipe, the energy gathering cover is of a V-shaped structure, and two ends of the V-shaped structure are clamped in one group of energy gathering cover limiting grooves.
In the above technical scheme, further, an energy-absorbing material mounting groove is formed along the arc axis of the end face of the medium fixing tube, and the energy-absorbing material is filled in the energy-absorbing material mounting groove.
The invention has the beneficial effects that:
1. the multi-medium energy-collecting wall-protecting medicine bag designed by the invention can adjust energy collecting and wall-protecting angles, reduces vibration impact on the peripheral rock of the outline by the combined action of the multiple mediums, protects the stability of the peripheral rock of the outline as much as possible, thereby enhancing the self-stabilizing capability of the peripheral rock of the outline, and simultaneously, can reduce the time of pasting energy-absorbing materials by field workers due to adjustable wall-protecting angles, and can be directly prefabricated and molded, and the angle is directly adjusted to be filled into a blast hole, so that the charging time is saved.
2. Compared with the traditional formula for parameter optimization, the GOA algorithm provided by the invention is more accurate in blasting effect prediction, so that tunnel blasting parameters are reversely optimized, and the combined action of the GOA algorithm and the multi-medium energy-gathering wall-protecting explosive package is achieved, so that the tunnel wall-protecting controlled blasting is realized.
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.
FIG. 1 is a flow chart of a wall protection control blasting method based on a GOA-DBN neural network.
FIG. 2 is a schematic diagram of a multi-medium energy-accumulating wall-protecting package according to the present invention.
FIG. 3 is a schematic view of a medium-retaining tube of a multi-medium energy-accumulating wall-protecting package of the present invention.
Fig. 4 is a schematic view of a limiter in a multi-medium energy-accumulating wall-protecting medicine bag.
FIG. 5 is a schematic view of detonation baffle tubes in a multi-medium energy-accumulating wall-protecting drug packet of the present invention.
FIG. 6 is a schematic view of a energy concentrating cap in a multi-medium energy concentrating sidewall package of the present invention.
Fig. 7 is a schematic diagram of the energy collection and wall protection angle adjustment of the drug pack.
The device comprises a 1-medium fixing pipe, a 2-detonation blocking pipe, a 3-energy-absorbing material, 4-air, 5-explosive, a 6-limiter, a 7-energy-gathering cover 11-medium fixing pipe limit groove, a 12-energy-absorbing material mounting groove, a 21-detonation blocking pipe limit groove and a 22-energy-gathering cover limit groove.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a wall protection control blasting method based on a GOA-DBN neural network comprises the following steps:
step S1: design of blasting parameters
The blasting parameters comprise a cutting form, a tunneling footage, a blasthole parameter and a explosive charge, the cutting hole of the embodiment adopts a inclined hole cutting form, the cutting hole depth is 1.2m, and the rest blasthole depths are 1m; the diameter of the blasthole is 42mm; the single-hole dosages are respectively as follows: 0.3kg of slitting eyes, 0.19kg of tunneling eyes, 0.225kg of auxiliary eyes, 0.16kg of peripheral eyes and 0.3kg of bottom plate eyes;
step S2: establishing GOA-DBN blasting effect prediction model
Step S201: establishing a blasting effect database
Selecting the drug loading quantity of the cutting eye, tunneling the drug loading quantity of the eye, assisting the drug loading quantity of the eye and the drug loading quantity of the peripheral eye; the method comprises the following specific steps of constructing a data set by taking the eye loading quantity of a bottom plate as an input variable and the vibration speed as an output variable, and eliminating the correlation among a plurality of main influence factors of the data set by adopting PCA analysis:
a. the data preprocessing is carried out by adopting a 'mapmin max' normalization formula, and the formula is as follows:
wherein: y is max Is the maximum value of the normalized data; y is min The minimum value of the data after normalization processing; x is x max Is the maximum value of the data before normalization processing; x is x min The minimum value of the data before normalization processing;
the range of the processed data is [ -1,1], and the formula (1) can be simplified as follows:
b. constructing an observation data matrix, providing an overall U with n samples (U 1 ,U 2 ,U 3 ,…U n ) Each sample has m dimensions, m>n. I.e. the observation data matrix can be represented by formula (3):
c. the correlation coefficient matrix is constructed and can be represented by the following formulas (4) and (5):
wherein: u (u) ki 、u kj Representing u, t in the observation data matrix ij Representing the correlation coefficient, calculating the correlation coefficient between two different elements, i, j E [1, n ]]And j=i, t ij ＝1；
d. Calculating eigenvalue and eigenvector of correlation coefficient matrix T
From the characteristic equation: i T-lambda I P The eigenvalue λ can be calculated by =0 1 ≥λ 2 ≥…≥λ n Not less than 0 and feature vector e 1 ,e 2 ,…e n ；I P Representing an n-order identity matrix;
e. the principal component expression can be represented by formula (6):
wherein: l is less than or equal to n;
f. the calculated contribution rate and the cumulative contribution rate can be represented by the formulas (7), (8):
lambda in the above i Indicating the characteristic value of the i-th principal component,representing the total eigenvalue cumulative sum,/->Representing the cumulative sum of the characteristic values of the s principal components; if the cumulative value of the contribution rates of the first P variables is greater than 85%, the first P principal components are consideredAll variable information can be represented, and the first P main components are taken as a data set for analysis;
step S202: initializing DBN model parameters and GOA algorithm parameters;
step S203: optimizing the hidden layer number and learning rate of the DBN model by using GOA algorithm, and outputting particles with proper fitness as initial parameters of the DBN model
S2.3.1 first initializes the parameters of the GOA algorithm.
S2.3.2 calculate fitness of each particle;
s2.3.3 calculating the current best fitness;
s2.3.4 judging whether the iteration times are reached, if so, ending the program, wherein the current position of the global optimal solution is the optimal solution;
s2.3.5 updating the position of GOA particles, calculating the fitness of the updated GOA particles, comparing with the historical optimum, and updating if the fitness is better than the historical optimum, otherwise, not updating;
s2.3.6 updates the iteration number and returns to S2.3.4;
step S204: inputting the blasting effect data set into a DBN model for training, and outputting a GOA-DBN blasting effect prediction model;
step S3: predicting the vibration speed of the blasting parameters in the step S1 by adopting the GOA-DBN blasting effect prediction model in the step S2;
step S4: vibration speed prediction result inspection
Comparing the predicted result of the vibration speed in step S3 with the limited vibration speed, if v > v max Redesign until the vibration speed prediction results meet the requirements, i.e. v.ltoreq.v max Outputting the blasting parameters of the predicted result as tunnel blasting parameters;
step S5: taking the explosion parameters which are qualified in inspection as construction explosion parameters;
step S6: measuring a lofting hole, and drilling and filling the hole to be blocked;
step S7: blasting and checking blasting effect.
As shown in FIG. 2, the pack employs a multi-medium energy-accumulating wall-protecting pack comprising
The detonation blocking pipe 2 is of a cylinder structure;
the medium fixing tube 1 is wrapped on the outer side of the detonation obstructing tube 2 and is of a half-arc structure, and two ends of the half-arc structure are clamped with the detonation obstructing tube 2;
the energy absorbing material 3 is embedded on the cambered surface of the medium fixing pipe 1;
the explosive 5 is filled in the cylinder of the detonation obstruction tube 2, and the end part of the explosive is limited by the energy gathering cover 7.
As shown in fig. 3-6, two ends of the medium fixing tube 1 are connected with the detonation blocking tube 2 through a limiter 6, air 4 is arranged between the inner wall of the medium fixing tube 1 and the outer wall of the detonation blocking tube 2 along the arc axis of the end face of the medium fixing tube 1, and an energy absorbing material mounting groove 12 is formed in the medium fixing tube 1, and the energy absorbing material 3 is filled in the energy absorbing material mounting groove 12. A plurality of equally-spaced detonation blocking tube limiting grooves 21 are formed in the peripheral wall of the detonation blocking tube 2, symmetrical medium fixing tube limiting grooves 11 are formed in the inner walls of the two ends of the medium fixing tube 1, the top of the limiter 6 is located in the medium fixing tube limiting grooves 11, the bottom of the limiter 6 is located in the detonation blocking tube limiting grooves 21, and the angle of the protective wall is changed by adjusting the different detonation blocking tube limiting grooves 21 of the limiter 6, which are located on the detonation blocking tube 2.
As shown in fig. 5 and 6, a plurality of groups of equidistant energy-gathering cover limiting grooves 22 are arranged on the inner peripheral wall of the detonation baffle tube 2, the energy-gathering cover 7 is of a V-shaped structure, and two ends of the V-shaped structure are clamped in one group of energy-gathering cover limiting grooves 22. And the position and the angle of the energy gathering cover 7 on the end face of the detonation obstructing tube 2 can be adjusted.
In the hole arrangement, drilling and charging of the step S6, firstly, explosive is plugged into the detonation blocking pipe 2, then the position of the medium fixing pipe 1 is rotated according to the position of the peripheral hole, then the medium fixing pipe 1 is fixed by adopting the limiter 6, and then the energy absorbing material 3 is plugged into the energy absorbing material mounting groove 12 and plugged into the blast hole.
And S7, monitoring the vibration speed by installing a three-phase vibration meter at the monitoring point, and entering the face to check the damage condition of the peripheral rock of the outline after the blasting is finished.
The foregoing is merely illustrative of the present invention and not restrictive, and other modifications and equivalents thereof may occur to those skilled in the art without departing from the spirit and scope of the present invention.
Claims (9)
1. The wall protection control blasting method based on the GOA-DBN neural network is characterized by comprising the following steps of:
step S1: designing blasting parameters;
step S2: establishing a GOA-DBN blasting effect prediction model;
step S3: predicting the vibration speed of the blasting parameters in the step S1 by adopting the GOA-DBN blasting effect prediction model in the step S2;
step S4: checking a vibration speed prediction result;
step S5: taking the explosion parameters which are qualified in inspection as construction explosion parameters;
step S6: measuring a lofting hole, and drilling and filling the hole to be blocked;
step S7: blasting and checking blasting effect.
2. The dado control blasting method based on the GOA-DBN neural network according to claim 1, wherein in step 2, the GOA-DBN blasting effect prediction model building process is as follows:
step S201: establishing a blasting effect database
Selecting the drug loading quantity of the cutting eye, tunneling the drug loading quantity of the eye, assisting the drug loading quantity of the eye and the drug loading quantity of the peripheral eye; taking the eye drug loading amount of the bottom plate as an input variable and the vibration speed as an output variable to construct a data set;
step S202: initializing DBN model parameters and GOA algorithm parameters;
step S203: optimizing the hidden layer number and the learning rate of the DBN model by using a GOA algorithm, and outputting particles with proper fitness as initial parameters of the DBN model;
step S204: and inputting the blasting effect data set into the DBN model for training, and outputting the GOA-DBN blasting effect prediction model.
3. The dado control blasting method based on the GOA-DBN neural network according to claim 2, wherein the correlation among a plurality of main influencing factors is eliminated for the data set constructed in step S201, specifically comprising the following steps:
a. the data preprocessing is carried out by adopting a 'mapmin max' normalization formula, and the formula is as follows:
wherein: y is max Is the maximum value of the normalized data; y is min The minimum value of the data after normalization processing; x is x max Is the maximum value of the data before normalization processing; x is x min The minimum value of the data before normalization processing;
the range of the processed data is [ -1,1], and the formula (1) can be simplified as follows:
b. constructing an observation data matrix, providing an overall U with n samples (U 1 ,U 2 ,U 3 ,…U n ) Each sample has m dimensions, m>n, the observation data matrix, can be represented by formula (3):
c. the correlation coefficient matrix is constructed and can be represented by the following formulas (4) and (5):
wherein: u (u) ki 、u kj Representing u, t in the observation data matrix ij Representing the correlation coefficient, calculating the correlation coefficient between two different elements, i, j E [1, n ]]And j=i, t ij ＝1；
d. Calculating eigenvalue and eigenvector of correlation coefficient matrix T
From the characteristic equation: i T-lambda I P The eigenvalue λ can be calculated by =0 1 ≥λ 2 ≥…≥λ n Not less than 0 and feature vector e 1 ,e 2 ,…e n ；I P Representing an n-order identity matrix;
e. the principal component expression can be represented by formula (6):
wherein: l is less than or equal to n;
f. the calculated contribution rate and the cumulative contribution rate can be represented by the formulas (7), (8):
lambda in the above i Indicating the characteristic value of the i-th principal component,representing the total eigenvalue cumulative sum,/->Representing the cumulative sum of the characteristic values of the s principal components; if the cumulative value of the contribution rates of the first P principal components is greater than 85%, it is considered thatThe first P principal components can represent all variable information, and the first P principal components are taken as a data set for analysis.
4. The method for controlling a wall-protecting blasting with a multi-medium energy-collecting and wall-protecting pack according to claim 2, wherein the step S4 is a step of comparing the result of the prediction of the vibration velocity in the step S3 with the predetermined vibration velocity, and if v>v max Redesign until the vibration speed prediction results meet the requirements, i.e. v.ltoreq.v max And outputting the blasting parameter of the predicted result as the tunnel blasting parameter.
5. The wall protection control blasting method based on the GOA-DBN neural network as claimed in claim 2, wherein the medicine package in the step S6 adopts a multi-medium energy-gathering wall protection medicine package, which comprises
The detonation blocking pipe is of a cylinder structure;
the medium fixing tube is wrapped on the outer side of the detonation obstructing tube and is of a half-arc structure, and two ends of the half-arc structure are clamped with the detonation obstructing tube;
the energy absorbing material is embedded on the cambered surface of the medium fixing pipe;
the explosive is filled in the cylinder body of the detonation blocking pipe, and the end part of the explosive is limited by the energy gathering cover.
6. The GOA-DBN neural network-based dado control blasting method of claim 5, wherein two ends of the medium fixing tube are connected with the detonation blocking tube through a limiter, and air is used between the inner wall of the medium fixing tube and the outer wall of the detonation blocking tube.
7. The GOA-DBN neural network-based dado control blasting method is characterized in that a plurality of equally-spaced detonation baffle tube limiting grooves are formed in the outer peripheral wall of the detonation baffle tube, symmetrical medium fixing tube limiting grooves are formed in the inner walls of the two ends of the medium fixing tube, the top of the limiter is located in the medium fixing tube limiting grooves, the bottom of the limiter is located in the detonation baffle tube limiting grooves, and the angle of the dado is changed by adjusting the different detonation baffle tube limiting grooves in the detonation baffle tube at the bottom of the limiter.
8. The GOA-DBN neural network-based dado control blasting method is characterized in that a plurality of groups of equidistant energy gathering cover limiting grooves are formed in the inner peripheral wall of the detonation obstruction tube, the energy gathering cover is of a V-shaped structure, and two ends of the V-shaped structure are clamped in one group of energy gathering cover limiting grooves.
9. The GOA-DBN neural network-based dado control blasting method according to claim 5, wherein an energy-absorbing material installation groove is formed along an arc axis of an end face of the medium fixing tube, and the energy-absorbing material is filled in the energy-absorbing material installation groove.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310985541.3A CN116992770B (en) | 2023-08-07 | 2023-08-07 | Wall protection control blasting method based on GOA-DBN neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310985541.3A CN116992770B (en) | 2023-08-07 | 2023-08-07 | Wall protection control blasting method based on GOA-DBN neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116992770A true CN116992770A (en) | 2023-11-03 |
| CN116992770B CN116992770B (en) | 2024-03-22 |
Family
ID=88528035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310985541.3A Active CN116992770B (en) | 2023-08-07 | 2023-08-07 | Wall protection control blasting method based on GOA-DBN neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116992770B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015006650A (en) * | 2013-06-26 | 2015-01-15 | 須知 晃一 | Method of manufacturing composite bodies of system configuration structure cell and component material |
| CN106327023A (en) * | 2016-09-07 | 2017-01-11 | 国家电网公司 | Method and device for measuring transmission project man hour quota |
| CN109612708A (en) * | 2018-12-28 | 2019-04-12 | 东北大学 | Based on the power transformer on-line detecting system and method for improving convolutional neural networks |
| CN112183643A (en) * | 2020-09-29 | 2021-01-05 | 广西大学 | Hard rock tension-shear fracture identification method and device based on acoustic emission |
| CN112711904A (en) * | 2020-12-17 | 2021-04-27 | 玉溪矿业有限公司 | Blasting vibration characteristic parameter prediction method based on SA-GA-BP |
| CN114638267A (en) * | 2022-03-22 | 2022-06-17 | 四川省宜宾威力化工有限责任公司 | Electronic detonator blind shot identification method based on blast vibration multi-element characteristic information comparison |
| CN114779324A (en) * | 2022-03-11 | 2022-07-22 | 西南交通大学 | Rayleigh wave frequency dispersion curve inversion method based on deep learning and application |
| CN115455804A (en) * | 2022-08-02 | 2022-12-09 | 辽宁科技大学 | Blasting block size prediction method based on ore rock crushing mechanism |
| CN115950321A (en) * | 2022-12-28 | 2023-04-11 | 西安建筑科技大学 | Blasting method for reducing support damage of pipe shed, explosive loading device and explosive cartridge structure |
| CN116432855A (en) * | 2023-05-04 | 2023-07-14 | 云南省滇中引水工程有限公司 | Tunnel collapse condition prediction method based on tunneling data |
-
2023
- 2023-08-07 CN CN202310985541.3A patent/CN116992770B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015006650A (en) * | 2013-06-26 | 2015-01-15 | 須知 晃一 | Method of manufacturing composite bodies of system configuration structure cell and component material |
| CN106327023A (en) * | 2016-09-07 | 2017-01-11 | 国家电网公司 | Method and device for measuring transmission project man hour quota |
| CN109612708A (en) * | 2018-12-28 | 2019-04-12 | 东北大学 | Based on the power transformer on-line detecting system and method for improving convolutional neural networks |
| CN112183643A (en) * | 2020-09-29 | 2021-01-05 | 广西大学 | Hard rock tension-shear fracture identification method and device based on acoustic emission |
| CN112711904A (en) * | 2020-12-17 | 2021-04-27 | 玉溪矿业有限公司 | Blasting vibration characteristic parameter prediction method based on SA-GA-BP |
| CN114779324A (en) * | 2022-03-11 | 2022-07-22 | 西南交通大学 | Rayleigh wave frequency dispersion curve inversion method based on deep learning and application |
| CN114638267A (en) * | 2022-03-22 | 2022-06-17 | 四川省宜宾威力化工有限责任公司 | Electronic detonator blind shot identification method based on blast vibration multi-element characteristic information comparison |
| CN115455804A (en) * | 2022-08-02 | 2022-12-09 | 辽宁科技大学 | Blasting block size prediction method based on ore rock crushing mechanism |
| CN115950321A (en) * | 2022-12-28 | 2023-04-11 | 西安建筑科技大学 | Blasting method for reducing support damage of pipe shed, explosive loading device and explosive cartridge structure |
| CN116432855A (en) * | 2023-05-04 | 2023-07-14 | 云南省滇中引水工程有限公司 | Tunnel collapse condition prediction method based on tunneling data |
Non-Patent Citations (3)
| Title |
|---|
| HOANG NGUYEN ET AL.: "Predicting Blast-Induced Ground Vibration in Open-Pit Mines Using Different Nature-Inspired Optimization Algorithms and Deep Neural Network", 《NATURAL RESOURCES RESEARCH》, vol. 30, pages 3 - 12 * |
| 边兴: "深埋洞室高边墙爆破振动规律及放大效应研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 8, pages 028 - 10 * |
| 雷明锋等: "深山岭隧道爆破效果神经网络评价模型及爆破参数优化决策方法研究", 《现代隧道技术》, vol. 60, no. 2, pages 55 - 59 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116992770B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104634198B (en) | Close on controlled blasting construction method in the massif excavation of highway limit | |
| CN102269554B (en) | Method for treating underground mine goaf by forming covering layer by chamber blasting technology | |
| CN106524844B (en) | Boulder reconnoitres the construction method with explosion treatment along a kind of shield tunnel | |
| CN107289828B (en) | A kind of Blasting in open-pit effect evaluation method | |
| CN108007285A (en) | A kind of stone head deep hole sublevel is segmented efficient Cut Blasting method | |
| CN107843158A (en) | The construction method of the low vibration velocity exact requirements of Tunnel Blasting is realized with common on-electric detonator | |
| CN103398637B (en) | Mean-peak micro-quake fine control blasting construction method using high-precision digital electronic detonators | |
| CN109238055B (en) | Medium-length hole segmented blasting method and device | |
| CN110132080B (en) | High-step hole inner differential blasting method for strip mine | |
| CN109115061A (en) | A kind of initiation control method reducing blasting vibration | |
| CN102809330B (en) | Large collapse rock blasting method under precise control of digital electronic detonators | |
| CN106767205A (en) | The micro- Comprehensive Control blasting method of shaking of bustling urban district subway running tunnel | |
| CN104390534B (en) | A kind of tunnel photoface exploision method of quality control | |
| CN109211041B (en) | Reserved rock bank cofferdam blasting demolition method and application thereof | |
| CN116992770B (en) | Wall protection control blasting method based on GOA-DBN neural network | |
| CN109855500A (en) | One kind being used for tunnel perimeter eye beehive-shaped charge blasting cartridge | |
| CN107605491A (en) | A kind of tunneling method | |
| CN107560510A (en) | A kind of tunnel big cross section section constructing method and its face blast arrangement | |
| CN110553561B (en) | Blasting method for medium-length hole subsection differential collapse | |
| CN107036495A (en) | Hyperboloid of one sheet reaming chock blasting method from the bottom of one's heart | |
| KR102128932B1 (en) | Deck charge blasting method with low vibration and low noise | |
| CN107270792A (en) | Blasting technology below a kind of 500kV high voltage transmission line towers | |
| CN107990798A (en) | The definite method of mountain area civil buildings blasting vibration allowable safety distance | |
| CN107024153B (en) | Underwater rock plug burst gyro distribution coyote hole method | |
| CN215810502U (en) | Blast hole charging structure for energy-gathered water pressure blasting |
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 |