CN117782863A - Rock mass ground stress field inversion method and system - Google Patents
Rock mass ground stress field inversion method and system Download PDFInfo
- Publication number
- CN117782863A CN117782863A CN202311811597.3A CN202311811597A CN117782863A CN 117782863 A CN117782863 A CN 117782863A CN 202311811597 A CN202311811597 A CN 202311811597A CN 117782863 A CN117782863 A CN 117782863A
- Authority
- CN
- China
- Prior art keywords
- ground stress
- rock mass
- pressure
- rock
- stress field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 98
- 239000011435 rock Substances 0.000 title claims abstract description 55
- 238000005259 measurement Methods 0.000 claims abstract description 25
- 238000004088 simulation Methods 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 230000008569 process Effects 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 22
- 238000005553 drilling Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 230000010429 evolutionary process Effects 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 238000009412 basement excavation Methods 0.000 claims description 4
- 238000002347 injection Methods 0.000 claims description 4
- 239000007924 injection Substances 0.000 claims description 4
- 238000007664 blowing Methods 0.000 claims description 3
- 238000005336 cracking Methods 0.000 claims description 3
- 238000001035 drying Methods 0.000 claims description 3
- 239000000428 dust Substances 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005498 polishing Methods 0.000 claims description 3
- 238000007789 sealing Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 239000003921 oil Substances 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000005065 mining Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Landscapes
- Investigation Of Foundation Soil And Reinforcement Of Foundation Soil By Compacting Or Drainage (AREA)
Abstract
The invention discloses a rock mass ground stress field inversion method and a system, which relate to the technical field of geotechnical engineering and comprise the following steps: measuring initial ground stress of the original rock by adopting a hydraulic fracturing method; measuring unloading ground stress by adopting a surface stress relief method; and inverting the ground stress field based on simulation analysis and artificial intelligence to obtain an inversion result. The method combines the hydraulic fracturing method with the surface stress measurement to obtain the initial ground stress and the unloading ground stress of the original rock, and compared with the traditional method, the method has the advantages of simpler and more convenient operation, strong intuitionistic property, high precision, high speed, low cost and the like, and can reach the construction standard.
Description
Technical Field
The invention relates to the technical field of geotechnical engineering, in particular to a method and a system for inverting a geotechnical stress field.
Background
For large underground works, the ground stress is the main load acting on the supporting structure, and directly influences the stability of surrounding rocks of a cavity, so that the ground stress field is accurately determined, and the problem of underground engineering design and analysis is primarily solved. In particular, for a high and steep open slope and a deep stope, under the double superposition of initial ground stress and mining disturbance stress, the magnitude and the direction of the stress field of surrounding rock in the stope are not clear, and landslide, rock burst and collapse caused by high stress concentration are extremely easy to induce. At present, the final boundary of the black-mountain copper mine and the Tai steel strip mine is extremely easy to induce local landslide disasters under the combined action of a high side slope and joints, so that clear knowledge on the distribution rule of the ground stress field of a mining area is needed.
At present, the determination of the ground stress field is mainly based on the combination of actual measurement and deduction, but is influenced by uncertain factors such as uneven rock formation distribution, random crack development and the like in the actual measurement process, the ground stress actual measurement value has strong discreteness, and is influenced by artificial subjective factors in the test process, so that the fluctuation of the test result and the ground stress field regression is relatively large.
The existing research method mainly aims at carrying out ground stress field regression on a certain state of the geologic body, ignoring the evolution process of the stress field of the geologic body, and particularly, the influence of excavation unloading effect. Therefore, under the conditions of fewer constraint conditions and complex stress paths, the problems of solution non-uniqueness or local optimum trapping and the like easily occur in inversion calculation, so that the inversion accuracy is often not high.
Therefore, how to provide a rock mass ground stress field inversion scheme with strong intuitiveness, high precision, high speed and low cost is a technical problem which needs to be solved by the technicians in the field.
Disclosure of Invention
In view of the above, the invention provides a rock mass ground stress field inversion method and a system, which solve the problems pointed out by the background technology.
In order to achieve the above object, the present invention provides the following technical solutions:
a method of inverting a rock mass ground stress field, comprising the steps of:
measuring initial ground stress of the original rock by adopting a hydraulic fracturing method;
measuring unloading ground stress by adopting a surface stress relief method;
and inverting the ground stress field based on simulation analysis and artificial intelligence to obtain an inversion result.
Optionally, the method for testing the hydraulic fracturing method specifically comprises the following steps:
s11, seat sealing: placing two expandable packers into a selected fracturing section through a drill rod, and pressurizing to expand the packers and seal the packers on the wall of a drilling hole to form a pressure-bearing section space;
s12, water injection pressurization: after the switching valve is pushed by the drill rod, the hydraulic pump is used for injecting water and pressurizing the fracturing section, and the wall of the drilling hole bears the gradually enhanced hydraulic action;
s13, rock wall fracturing: after the hydraulic pressure is gradually increased, the wall of the drilling hole is cracked along the direction with minimum resistance, and the crack extends in a plane perpendicular to the minimum main stress on the cross section; when the pump pressure rises to the critical rupture pressure P b Then, the pressure value born by the wall of the borehole is reduced;
s14, guan Beng: closing the hydraulic pump, when the pump pressure drops to a pressure at which the fracture is in a critical closed condition, i.e. at which the minimum principal stress perpendicular to the fracture face is in equilibrium with the hydraulic circuit, referred to as the instantaneous closing pressure P s ；
S15, pressure relief: opening the pressure valve to release pressure, so that the crack is completely closed, and the pump pressure drop is zero;
s16, re-tensioning: performing multiple pressurization cycles according to the steps S12-S15, obtaining reasonable fracturing parameters, and judging the rock cracking and crack extension processes;
s17, deblocking: after fracturing, pulling the change-over valve through the drill rod to drain the liquid in the packer through the drill rod, and retracting the packer to restore the original state, namely, deblocking the packer;
s18, recording the direction of the fracture: the length and direction of the fracture was recorded by expanding the rubber of the outer layer of the impression cylinder and the automatic orienting orienter.
Optionally, in S12, the packer pressure remains unchanged while the water injection is pressurized.
Optionally, when the surface stress relief method is adopted for measurement, self-made drilling machine equipment is selected, and a drill bit of the self-made drilling machine equipment carries a strain measurement line in real time in the drilling process and performs measurement of strain data.
Optionally, the testing step of the surface stress relief method specifically includes:
selecting a position with good rock mass integrity, polishing the surface of a roadway measuring point, and blowing dust by using a blower;
installing a strain gauge, and drying the strain gauge wiring by using a blower;
and (3) starting drilling, and measuring and recording strain of the strain gauge after the temperature of the bottom of the hole is reduced to the temperature in the tunnel.
Optionally, inversion is performed on the ground stress field, specifically including the following steps:
s31, establishing a three-dimensional numerical model of the region according to the original landform and geological evolution process of the engineering region;
s32, preliminarily obtaining a local ground stress field distribution rule according to a reference region geological structure theory and a field ground stress test result, and calculating a value range of a boundary condition of the three-dimensional numerical model by utilizing a test algorithm, wherein the value range comprises normal displacement and tangential displacement;
s33, obtaining a theoretical calculation value of the ground stress measuring point of the engineering area by using a numerical simulation method;
s34, simulating the whole rock mass excavation process, and obtaining a theoretical calculation value of a ground stress measuring point of an unloading area;
s35, according to the calculation result, training samples of which the boundary conditions correspond to the theoretical calculation value of the engineering area ground stress measurement point and the theoretical calculation value of the unloading area ground stress measurement point one by one are established;
s36, training the evolutionary neural network by using a training sample to obtain a nonlinear mapping relation between boundary conditions and test stress;
s37, inputting the measured values of the initial ground stress and the unloading ground stress of the original rock into a trained evolutionary neural network, and inverting to obtain corresponding boundary conditions.
Optionally, the optimization of the evolutionary neural network is divided into an inner layer optimization process and an outer layer optimization process, wherein the outer layer evolution cycle is the evolution of the BP network structural parameter, and the inner layer cycle is the change of the initial weight.
Alternatively, the algorithm for evolving the neural network mainly comprises two steps: constructing a training sample library and setting algorithm parameters;
the algorithm parameters are set up by: setting attribute parameters and operation control parameters of a genetic evolutionary algorithm in a neural network structure parameter evolutionary process and a neural network initial weight evolutionary process, and setting learning parameters and operation control parameters of a BP algorithm.
An inversion system for implementing the rock mass ground stress field inversion method of any one of the above claims, comprising:
the first measuring module is used for measuring initial ground stress of the original rock by adopting a hydraulic fracturing method;
the second measuring module is used for measuring unloading ground stress by adopting a surface stress relief method;
and the inversion module is used for inverting the ground stress field through simulation analysis and artificial intelligence to obtain an inversion result.
Compared with the prior art, the rock mass ground stress field inversion method and system provided by the invention combine the hydraulic fracturing method and the surface stress relief method to obtain the initial ground stress and unloading ground stress of the original rock, and have the characteristics of strong intuitiveness, high precision, high speed, low cost and the like. Compared with the traditional method, the method is simpler and more convenient to operate, staff can operate by hand rapidly, the obtained result is high in quality, and the construction standard can be met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a rock mass ground stress field inversion method provided by the invention;
fig. 2 (a) and fig. 2 (b) are schematic diagrams of a measurement procedure and a measurement fracturing process curve of the hydraulic fracturing method provided by the invention;
FIG. 3 is a schematic diagram of the basic idea of the evolutionary neural network algorithm provided by the invention;
FIG. 4 is a schematic diagram of the steps of the evolutionary neural network algorithm provided by the invention;
fig. 5 (a) and fig. 5 (b) are schematic diagrams of an operation interface of the evolutionary neural network software provided by the invention;
FIG. 6 is a schematic diagram of the process of the ground stress field refinement inversion method provided by the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
The key to the ground stress inversion is the ground stress measurement. The hydraulic fracturing ground stress is applied to oil field engineering for the first time, and aims to manufacture artificial cracks through oil field drilling so as to improve the oil field crude oil yield. Later m.k.hubbert and d.g.willis in practice summed up the relationship between the original rock stress and the fracture, this finding was also applied in the ground stress measurement by fehelchester and helmsen, which method can obtain the ground stress magnitude by repeated hydraulic pressure and determine the direction of maximum principal stress from the trace on the stamp. The method is a direct measurement method, and the test result is accurate.
After the tunnel or tunnel is excavated and unloaded, as the stress condition of the surface rock mass is complex, if the hydraulic fracturing method is adopted to test the unloading stress of the surrounding rock, holes are needed to be drilled in the surrounding rock, secondary damage to the surrounding rock is very easy to be caused, and the testing precision and success rate are reduced, so that the unloading stress test adopts a surface stress relief method, and the method has the characteristics of strong intuitiveness, high precision, high speed, low cost and the like.
In order to achieve the above purpose, the embodiment of the invention discloses a rock mass ground stress field inversion method, as shown in fig. 1, comprising the following steps:
measuring initial ground stress of the original rock by adopting a hydraulic fracturing method;
measuring unloading ground stress by adopting a surface stress relief method;
and inverting the ground stress field based on simulation analysis and artificial intelligence to obtain an inversion result.
1. Hydraulic fracturing method
The testing step of the hydraulic fracturing method, referring to fig. 2, specifically includes:
s11, seat sealing: placing two expandable packers into a selected fracturing section through a drill rod, and pressurizing to expand the packers and seal the packers on the wall of a drilling hole to form a pressure-bearing section space;
s12, water injection pressurization: after the switching valve is pushed by the drill rod, the hydraulic pump is used for injecting water and pressurizing the fracturing section (the pressure of the packer is kept unchanged at the moment), and the wall of the borehole hole bears the gradually-enhanced hydraulic action;
s13, rock wall fracturing: after the hydraulic pressure is gradually increased, the wall of the drilling hole is cracked along the direction with minimum resistance, and the crack extends in a plane perpendicular to the minimum main stress on the cross section; when the pump pressure rises to the critical rupture pressure P b Then, the pressure value born by the wall of the borehole is reduced;
s14, guan Beng: closing the hydraulic pump, and rapidly reducing the pump pressure, and then slowly reducing the pump pressure along with the penetration of the fracturing fluid into the rock stratum; the pressure at which the pump pressure drops to bring the fracture into critical closure, i.e. the pressure at which the minimum principal stress perpendicular to the fracture plane is in equilibrium with the hydraulic circuit, is called the instantaneous closure pressure P s ；
S15, pressure relief: opening the pressure valve to release pressure, so that the crack is completely closed, and the pump pressure drop is zero;
s16, re-tensioning: performing multiple pressurization cycles according to the steps S12-S15, obtaining reasonable fracturing parameters, and judging the rock cracking and crack extension processes;
s17, deblocking: after fracturing, pulling the change-over valve through the drill rod to drain the liquid in the packer through the drill rod, and retracting the packer to restore the original state, namely, deblocking the packer;
s18, recording the direction of the fracture: the length and direction of the fracture was recorded by expanding the rubber of the outer layer of the impression cylinder and the automatic orienting orienter.
2. Surface stress relief method
First, a proper disturbance stress measuring instrument, application software and a computer thereof are required to be selected for strain measurement, and homemade drilling equipment can be adopted. Compared with a common water drill, the drill bit of the self-made drilling machine equipment carries a strain measurement line in real time in the drilling process and performs strain data measurement.
Before measurement, firstly selecting a position with good rock mass integrity, polishing the surface of a roadway measuring point, and blowing dust by using a blower; installing a strain gauge, and drying the strain gauge wiring by using a blower, so that the influence of moisture on the measurement error is reduced; and (3) starting drilling, and measuring and recording strain of the strain gauge after the temperature of the bottom of the hole is reduced to the temperature in the tunnel.
3. Inversion of ground stress field based on simulation analysis and artificial intelligence
1) Inversion principle of evolutionary neural network
The evolutionary neural network software is based on a genetic evolutionary algorithm and a BP algorithm, and combines the global searching capability of the genetic algorithm and the local optimal value searching capability of the BP algorithm to form an optimized combination, thereby greatly improving the performance of the network training algorithm. The genetic algorithm has perfect global searching capability, but cannot go deep in the aspect of local precision, so after BP network structure optimization and initial weight optimization, a sample is also subjected to learning training according to the BP algorithm to perform local optimization. Feeding inThe basic idea flow chart of the chemical neural network software algorithm is shown in FIG. 3, in which, for convenience of description, BPNN represents BP network model, n and m are the input and output numbers of the model, nh respectively 1 ,nh 2 … is the number of neurons contained in each hidden layer; w is a weight matrix. The optimization of the evolutionary neural network is divided into an inner layer optimization process and an outer layer optimization process, wherein the outer layer evolution cycle is the evolution of the BP network structural parameter, and the inner layer cycle is the change of the initial weight. Finally, the software further circulates the BP algorithm on the basis of optimizing the initial weight of the network structure, and the whole evolutionary learning process of the software is formed.
The algorithm steps of the evolutionary neural network software are shown in fig. 4, and the operation flow of the software mainly comprises the following two steps:
a. constructing a training sample library: according to the input-output mode determined by the input-output characteristics of the problem to be solved, input-expected output learning sample pairs are extracted from example data, the sample pairs are divided into two parts, one part is used as a learning sample for respectively calculating adaptive values in the evolution process of the neural network structural parameters and initial weights and training the weights in the BP algorithm, and the other part is used for testing the popularization prediction capability of the classification model obtained in the sample monitoring evolution process and the BP training process and optimally selecting the optimal learning times.
b. Setting algorithm parameters: setting attribute parameters and operation control parameters of a genetic evolutionary algorithm in a neural network structure parameter evolutionary process and a neural network initial weight evolutionary process, and setting learning parameters and operation control parameters of a BP algorithm. The identification objects of two evolutionary processes in the evolutionary neural network method are quite different in the number of parameters, numerical characteristics and complexity, so that the identification objects are treated differently when the parameters are set. In the evolution process of network structure parameters, the number of parameters is small (generally not more than 3 layers) and is an integer (the number of nodes in each hidden layer), and the general range is not suitable to be too large (too large network can influence the popularization generalization capability of the network). To reduce the amount of computation while avoiding premature convergence, the population size can be given smaller and the probability of variation set to be larger (corresponding to lower hybridization probability).
The evolving neural network software is the software GANN developed in visual++6.0 platform (as shown in fig. 5). The software can realize the common optimization of the neural network structure and the initial weight, can also carry out independent neural network sample training, and can carry out inverse analysis on input and output data. The learning training samples and the test samples are input in txt text document format in the software operation process, and the visual input of algorithm parameters is realized.
2) Fine inversion method for ground stress field
Inversion of the ground stress field, referring to fig. 6, specifically includes the following steps:
s31, establishing a three-dimensional numerical model of the region according to the original landform and geological evolution process of the engineering region;
s32, preliminarily obtaining a local ground stress field distribution rule according to a reference region geological structure theory and a field ground stress test result, and calculating a value range of a boundary condition of the three-dimensional numerical model by utilizing a test algorithm, wherein the value range comprises normal displacement and tangential displacement;
s33, obtaining a theoretical calculation value of the ground stress measuring point of the engineering area by using a numerical simulation method;
s34, simulating the whole rock mass excavation process, and obtaining a theoretical calculation value of a ground stress measuring point of an unloading area;
s35, according to the calculation result, training samples of which the boundary conditions correspond to the theoretical calculation value of the engineering area ground stress measurement point and the theoretical calculation value of the unloading area ground stress measurement point one by one are established;
s36, training the evolutionary neural network by using a training sample to obtain a nonlinear mapping relation between boundary conditions and test stress;
s37, inputting the measured values of the initial ground stress and the unloading ground stress of the original rock into a trained evolutionary neural network, and inverting to obtain corresponding boundary conditions.
Corresponding to the method shown in fig. 1, the embodiment of the invention also provides a rock mass ground stress field inversion system, which is used for realizing the method shown in fig. 1, and the rock mass ground stress field inversion system provided by the embodiment of the invention can be applied to a computer terminal or various mobile devices and specifically comprises:
the first measuring module is used for measuring initial ground stress of the original rock by adopting a hydraulic fracturing method;
the second measuring module is used for measuring unloading ground stress by adopting a surface stress relief method;
and the inversion module is used for inverting the ground stress field through simulation analysis and artificial intelligence to obtain an inversion result.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. The inversion method of the rock mass ground stress field is characterized by comprising the following steps of:
measuring initial ground stress of the original rock by adopting a hydraulic fracturing method;
measuring unloading ground stress by adopting a surface stress relief method;
and inverting the ground stress field based on simulation analysis and artificial intelligence to obtain an inversion result.
2. The rock mass ground stress field inversion method according to claim 1, wherein the hydraulic fracturing method testing step specifically comprises:
s11, seat sealing: placing two expandable packers into a selected fracturing section through a drill rod, and pressurizing to expand the packers and seal the packers on the wall of a drilling hole to form a pressure-bearing section space;
s12, water injection pressurization: after the switching valve is pushed by the drill rod, the hydraulic pump is used for injecting water and pressurizing the fracturing section, and the wall of the drilling hole bears the gradually enhanced hydraulic action;
s13, rock wall fracturing: after the hydraulic pressure is gradually increased, the wall of the drilling hole is cracked along the direction with minimum resistance, and the crack extends in a plane perpendicular to the minimum main stress on the cross section; when the pump pressure rises to the critical rupture pressure P b Then, the pressure value born by the wall of the borehole is reduced;
s14, guan Beng: closing the hydraulic pump, when the pump pressure drops to a pressure at which the fracture is in a critical closed condition, i.e. at which the minimum principal stress perpendicular to the fracture face is in equilibrium with the hydraulic circuit, referred to as the instantaneous closing pressure P s ；
S15, pressure relief: opening the pressure valve to release pressure, so that the crack is completely closed, and the pump pressure drop is zero;
s16, re-tensioning: performing multiple pressurization cycles according to the steps S12-S15, obtaining reasonable fracturing parameters, and judging the rock cracking and crack extension processes;
s17, deblocking: after fracturing, pulling the change-over valve through the drill rod to drain the liquid in the packer through the drill rod, and retracting the packer to restore the original state, namely, deblocking the packer;
s18, recording the direction of the fracture: the length and direction of the fracture was recorded by expanding the rubber of the outer layer of the impression cylinder and the automatic orienting orienter.
3. A method of inverting a ground stress field of a rock mass according to claim 2, wherein in S12, the packer pressure is maintained while the water is being injected and pressurized.
4. The rock mass ground stress field inversion method according to claim 1, wherein self-made drilling equipment is selected when the surface stress relief method is adopted for measurement, and a drill bit of the self-made drilling equipment carries a strain measurement line in real time in the drilling process and performs measurement of strain data.
5. The rock mass ground stress field inversion method according to claim 1, wherein the testing step of the surface stress relief method specifically comprises:
selecting a position with good rock mass integrity, polishing the surface of a roadway measuring point, and blowing dust by using a blower;
installing a strain gauge, and drying the strain gauge wiring by using a blower;
and (3) starting drilling, and measuring and recording strain of the strain gauge after the temperature of the bottom of the hole is reduced to the temperature in the tunnel.
6. A method for inverting a ground stress field of a rock mass according to claim 1, characterized in that the ground stress field is inverted, comprising the steps of:
s31, establishing a three-dimensional numerical model of the region according to the original landform and geological evolution process of the engineering region;
s32, preliminarily obtaining a local ground stress field distribution rule according to a reference region geological structure theory and a field ground stress test result, and calculating a value range of a boundary condition of the three-dimensional numerical model by utilizing a test algorithm, wherein the value range comprises normal displacement and tangential displacement;
s33, obtaining a theoretical calculation value of the ground stress measuring point of the engineering area by using a numerical simulation method;
s34, simulating the whole rock mass excavation process, and obtaining a theoretical calculation value of a ground stress measuring point of an unloading area;
s35, according to the calculation result, training samples of which the boundary conditions correspond to the theoretical calculation value of the engineering area ground stress measurement point and the theoretical calculation value of the unloading area ground stress measurement point one by one are established;
s36, training the evolutionary neural network by using a training sample to obtain a nonlinear mapping relation between boundary conditions and test stress;
s37, inputting the measured values of the initial ground stress and the unloading ground stress of the original rock into a trained evolutionary neural network, and inverting to obtain corresponding boundary conditions.
7. The rock mass ground stress field inversion method according to claim 6, wherein the optimization of the evolutionary neural network is divided into an inner layer optimization process and an outer layer optimization process, wherein the outer layer evolution cycle is the evolution of the BP network structural parameter, and the inner layer cycle is the change of the initial weight.
8. A method of rock mass ground stress field inversion according to claim 6, wherein the algorithm for evolving the neural network comprises mainly two steps: constructing a training sample library and setting algorithm parameters;
the algorithm parameters are set up by: setting attribute parameters and operation control parameters of a genetic evolutionary algorithm in a neural network structure parameter evolutionary process and a neural network initial weight evolutionary process, and setting learning parameters and operation control parameters of a BP algorithm.
9. An inversion system for carrying out the rock mass ground stress field inversion method of any one of claims 1-8, comprising:
the first measuring module is used for measuring initial ground stress of the original rock by adopting a hydraulic fracturing method;
the second measuring module is used for measuring unloading ground stress by adopting a surface stress relief method;
and the inversion module is used for inverting the ground stress field through simulation analysis and artificial intelligence to obtain an inversion result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311811597.3A CN117782863A (en) | 2023-12-27 | 2023-12-27 | Rock mass ground stress field inversion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311811597.3A CN117782863A (en) | 2023-12-27 | 2023-12-27 | Rock mass ground stress field inversion method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117782863A true CN117782863A (en) | 2024-03-29 |
Family
ID=90399632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311811597.3A Pending CN117782863A (en) | 2023-12-27 | 2023-12-27 | Rock mass ground stress field inversion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117782863A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118208229A (en) * | 2024-05-22 | 2024-06-18 | 成都理工大学 | Visual hydraulic fracturing method ground stress test system and method |
-
2023
- 2023-12-27 CN CN202311811597.3A patent/CN117782863A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118208229A (en) * | 2024-05-22 | 2024-06-18 | 成都理工大学 | Visual hydraulic fracturing method ground stress test system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mohamadian et al. | A geomechanical approach to casing collapse prediction in oil and gas wells aided by machine learning | |
| US10605074B2 (en) | Mapping of fracture geometries in a multi-well stimulation process | |
| US9164194B2 (en) | Method for modeling deformation in subsurface strata | |
| US8423337B2 (en) | Method for multi-scale geomechanical model analysis by computer simulation | |
| CN113821953B (en) | Temporary plugging repeated fracturing design method based on dynamic ground stress and residual oil characteristics | |
| US10732086B2 (en) | Device and method for measuring magnitude of seepage force and its influence on effective stress of formation | |
| CA2690992A1 (en) | Method for predicting well reliability by computer simulation | |
| CN117782863A (en) | Rock mass ground stress field inversion method and system | |
| CN109033504B (en) | Oil-water well casing damage prediction method | |
| CN113625364B (en) | Shale formation pore pressure calculation method based on double correction | |
| CN108572401B (en) | Construction method of fracture-cavity combined model and method for detecting deformation of reservoir fracture-cavity | |
| CN115017833B (en) | High-ground-stress soft rock body ground stress calculation method based on deep neural network | |
| Weissenburger et al. | The engineering approach to sand production prediction | |
| CN112412434B (en) | Improved loose sandstone ground stress calculation method | |
| CN115270533A (en) | Repeated fracturing design method and device, storage medium and electronic equipment | |
| Hamdi et al. | Huff-n-Puff (HNP) design for shale reservoirs using local dual-porosity, dual-permeability compositional simulation | |
| Jin et al. | Investigation of produced gas injection in the Bakken for enhanced oil recovery considering well interference | |
| Clarke et al. | Pressuremeter Testing in Ground Investigation. Part 1-Site Operations. | |
| Li et al. | Critical review of leak-off test as a practice for determination of in-situ stresses | |
| Mokhtari et al. | Feasibility study of EPB shield automation using deep learning | |
| CN113187463B (en) | Pore pressure while drilling prediction method based on stratum overpressure single-cause contribution rate | |
| WO2020047451A1 (en) | Digitial multi-phase flow analysis system for assisting enhanced oil recovery | |
| Dano et al. | Interpretation of dilatometer tests in a heavy oil reservoir | |
| CN112418597B (en) | Reservoir compressibility evaluation method suitable for shale gas old area development adjustment well | |
| Kumar et al. | In-situ stress measurement for the design of underground desilting chamber: A case study from Eastern Himalayas |
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 |