A rock crack change real-time detection method, system, device and platform

Abstract

The application discloses a rock crack change real-time detection method, system, device and platform; the method is used for generating and acquiring first data corresponding to the rock sample crack change in real time; wherein the first data is optical signal data reflected by the rock sample light surface; according to the first data, at least one crack characteristic change data model corresponding to the first data is created in combination with a neural network; the second data corresponding to the first data is generated through the crack characteristic change data model; wherein the second data is crack characteristic change data corresponding to the rock sample, and the system, device and platform corresponding to the method effectively solve the problem that the whole-process damage form change of rock mechanics experiments cannot be determined, and ensure that the physical data of the rock sample is recorded. The determined data can be used for rock damage constitutive model research, rock damage mechanics behavior research and fitting of numerical simulation.

Description

Technical Field

[0001] This invention belongs to the field of rock test crack measurement technology, specifically relating to a method, system, device and platform for real-time detection of rock crack changes. Background Technology

[0002] Currently, rock mechanics testing is an important tool for studying the mechanical properties of rocks, including uniaxial tests, triaxial tests, and triaxial creep tests. These testing methods can help understand the damage, deformation, and failure behavior of rocks under different stress conditions.

[0003] Among these methods, the uniaxial rock test is one of the most commonly used. In this test, the rock sample is placed under a stress loading perpendicular to its axis. By applying pressure perpendicular to the axis, the stress-strain relationship of the rock sample can be observed, and its mechanical properties can be inferred. The triaxial test is a more complex method that can simulate stress states closer to actual geological conditions. In this test, the rock sample is simultaneously subjected to radial and axial stresses to simulate multi-directional stress states in the Earth's crust. Through this test, a more comprehensive understanding of the rock's strength, deformation, and failure characteristics can be obtained. The triaxial creep test is a deformation test based on the triaxial test. It is mainly used to study the deformation and failure behavior of rocks under long-term loading. In this test, the rock sample is subjected to continuous stress and deformation to simulate creep phenomena in actual engineering.

[0004] The existing triaxial experimental setups described above cannot observe crack changes in real time during these experiments. Researchers can only infer the failure mechanism from the damage morphology of the rock samples after the experiment, and study the failure process by examining the crack morphology after failure using CT scans and electron microscopy. In addition, existing computer numerical simulations of the failure process cannot fit the actual failure situation, resulting in a significant deviation between the final results and the actual failure. These factors affect the study of rock damage mechanisms.

[0005] Therefore, in order to address the technical problem of difficulty in determining the morphology of rock damage during the above rock mechanics experiments, there is an urgent need to design and develop a method, system, device and platform for real-time detection of rock crack changes. Summary of the Invention

[0006] To overcome the shortcomings and difficulties of the existing technology, the present invention aims to provide a method, system, device, and platform for real-time detection of rock crack changes, addressing the aforementioned technical problems and defects. This effectively solves the problem of the inability to measure damage morphology changes throughout the entire rock mechanics experiment, ensuring that the physical data of the rock sample is recorded. The measured data can be used for rock damage constitutive model research, rock damage mechanical behavior research, and numerical simulation fitting.

[0007] The first objective of this invention is to provide a method for real-time detection of changes in rock cracks; the second objective of this invention is to provide a system for real-time detection of changes in rock cracks; the third objective of this invention is to provide a device for real-time detection of changes in rock cracks; and the fourth objective of this invention is to provide a platform for real-time detection of changes in rock cracks.

[0008] The first objective of this invention is achieved as follows: the method comprises the following steps:

[0009] The system generates and acquires first data corresponding to the changes in cracks in the rock sample in real time; wherein, the first data is the light signal data reflected from the smooth surface of the rock sample.

[0010] Based on the first data and combined with a neural network, at least one crack feature change data model corresponding to the first data is created.

[0011] The crack feature change data model generates second data corresponding to the first data; wherein the second data is crack feature change data corresponding to the rock sample.

[0012] Furthermore, the real-time generation and acquisition of first data corresponding to the crack changes in the rock sample further includes: generating and acquiring loading pressure data corresponding to the rock sample, and generating first control data based on the loading pressure data; wherein, the loading pressure data includes loading confining pressure data, loading axial pressure data, and loading osmotic pressure data; the first control data is control data for turning on the projection of the optical signal;

[0013] Generate and acquire light beam incident angle data corresponding to the rock sample, and generate second control data based on the light beam incident angle data; wherein, the second control data is control data for adjusting the light beam incident angle.

[0014] Furthermore, the step of creating at least one crack feature change data model corresponding to the first data based on the first data and in conjunction with a neural network further includes:

[0015] Generate third data corresponding to the first data, and establish a correspondence between the first data and the third data; wherein, the third data is the photoresistor value change data corresponding to the optical signal data;

[0016] Based on the third data, real-time status data corresponding to the changes in cracks in the rock sample is created, and a change curve corresponding to the real-time status data is generated.

[0017] Furthermore, the step of generating second data corresponding to the first data through the crack feature change data model further includes:

[0018] Create at least one photoresistor array corresponding to the first data, and generate crack feature change data corresponding to the resistance change in the photoresistor array; wherein, the crack feature change data includes crack width change data, crack length change data, and crack change location data;

[0019] Based on the crack feature change data, estimate the crack width or length in real time, corresponding to the crack feature change data.

[0020] Furthermore, the step of creating at least one photoresistor array corresponding to the first data and generating crack feature change data corresponding to the resistance change in the photoresistor array further includes:

[0021] Generate and acquire resistance change data in the photoresistor array, and generate current change data corresponding to the resistance change data;

[0022] The resistance change data is fused and processed, and combined with the corresponding current change data to generate damage change data corresponding to the rock sample.

[0023] Furthermore, the step of generating second data corresponding to the first data through the crack feature change data model further includes:

[0024] Based on the second data, generate two-dimensional shape change data corresponding to the second data;

[0025] Based on the two-dimensional shape change data and combined with the photosensitive element parameter change data, shape mapping relationship data corresponding to the cracks in the rock sample is created; wherein, the photosensitive element parameter change data includes emitted light parameter data, current parameter data and resistance parameter data;

[0026] Based on the shape mapping relationship data, a calibration curve corresponding to the crack feature change data is generated.

[0027] The second objective of this invention is achieved as follows: the system is used to implement the aforementioned real-time detection method for changes in rock fractures; the system comprises:

[0028] The first data generation unit is used to generate and acquire first data corresponding to the changes in cracks in the rock sample in real time; wherein, the first data is the light signal data reflected from the smooth surface of the rock sample;

[0029] A data model creation unit is used to create at least one crack feature change data model corresponding to the first data, based on the first data and in combination with a neural network.

[0030] The second data generation unit is used to generate second data corresponding to the first data through the crack feature change data model; wherein, the second data is crack feature change data corresponding to the rock sample.

[0031] Furthermore, the first data generation unit further includes:

[0032] The first data generation module is used to generate and acquire loading pressure data corresponding to the rock sample, and generate first control data based on the loading pressure data; wherein, the loading pressure data includes loading confining pressure data, loading axial pressure data, and loading osmotic pressure data; the first control data is control data for turning on the projection of the light signal;

[0033] The second data generation module is used to generate and acquire light beam incident angle data corresponding to the rock sample, and generate second control data based on the light beam incident angle data; wherein, the second control data is control data for adjusting the light beam incident angle.

[0034] And / or, the data model creation unit further includes:

[0035] The third data generation module is used to generate third data corresponding to the first data and establish a correspondence between the first data and the third data; wherein, the third data is the photoresistor value change data corresponding to the optical signal data;

[0036] The first data creation module is used to create real-time status data corresponding to the changes in cracks in the rock sample based on the third data, and to generate a change curve corresponding to the real-time status data.

[0037] And / or, the second data generation unit further includes:

[0038] The second data creation module is used to create at least one photoresistor array corresponding to the first data, and generate crack feature change data corresponding to the resistance change in the photoresistor array; wherein, the crack feature change data includes crack width change data, crack length change data, and crack change location data.

[0039] The fourth data generation module is used to generate estimated crack width or length data corresponding to the crack feature change data in real time based on the crack feature change data.

[0040] And / or, the second data creation module further includes:

[0041] The fifth data generation module is used to generate and acquire resistance change data in the photoresistor array, and generate current change data corresponding to the resistance change data.

[0042] The data fusion processing module is used to fuse and process the resistance change data, and combine it with the corresponding current change data to generate damage change data corresponding to the rock sample.

[0043] And / or, the second data generation unit further includes:

[0044] The sixth data generation module is used to generate two-dimensional shape change data corresponding to the second data based on the second data;

[0045] The third data creation module is used to create shape mapping relationship data corresponding to the cracks in the rock sample based on the two-dimensional shape change data and combined with the photosensitive element parameter change data; wherein, the photosensitive element parameter change data includes emitted light parameter data, current parameter data and resistance parameter data;

[0046] The seventh data generation module is used to generate a calibration curve corresponding to the crack feature change data based on the shape mapping relationship data.

[0047] The third objective of this invention is achieved as follows: the device is used to implement the aforementioned method for real-time detection of rock fracture changes; the device comprises:

[0048] An axial loading rod for applying axial pressure to a rock sample via a top seat; a seepage loading system for loading osmotic pressure to the bottom of a rock sample via a pre-reserved channel; a confining pressure loading system for loading confining pressure to the periphery of a rock sample via a pre-reserved channel; and a triaxial loading system for providing axial pressure, osmotic pressure, and confining pressure applied to a rock sample.

[0049] The device is also equipped with a light-sensitive receiving screen for recording changes in light signals caused by the generation and development of cracks when rocks are damaged; the rock sample is a rock sample with a coating on its surface.

[0050] The fourth objective of this invention is achieved as follows: it includes a processor, a memory, and a real-time rock fracture change detection platform control program; wherein the real-time rock fracture change detection platform control program is executed in the processor, the real-time rock fracture change detection platform control program is stored in the memory, and the real-time rock fracture change detection platform control program implements the real-time rock fracture change detection method.

[0051] This invention generates and acquires first data corresponding to changes in cracks in rock samples in real time through a method. The first data is light signal data reflected from the smooth surface of the rock sample. Based on the first data and combined with a neural network, at least one crack feature change data model corresponding to the first data is created. Through the crack feature change data model, second data corresponding to the first data is generated. The second data is crack feature change data corresponding to the rock sample. The invention also includes a system, device, and platform corresponding to the method, which effectively solves the problem of being unable to measure damage morphology changes throughout the rock mechanics experiment, ensuring that the physical data of the rock sample is recorded. The measured data can be used for rock damage constitutive model research, rock damage mechanical behavior research, and numerical simulation fitting.

[0052] In other words, the triaxial experimental setup of this invention can record the real-time changes in cracks in rock samples. Furthermore, the optical receiving screen can be installed in existing conventional uniaxial experiments, making it simple and easy to operate. In addition, the crack change data recorded by this invention can be used for numerical model fitting. That is, this invention can measure the changes in cracks in rock samples in real time and record relevant data; this data can be used for rock damage constitutive model research, rock damage mechanical behavior research, and numerical simulation fitting. Compared with existing technologies, this invention has the advantages of real-time crack change measurement, simplicity, and ease of operation, and can improve the accuracy and reliability of rock mechanics experiments. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a schematic diagram of the process for real-time detection of rock crack changes according to the present invention;

[0055] Figure 2 This is a three-dimensional schematic diagram of the structure of a real-time detection device for rock crack changes according to the present invention;

[0056] Figure 3 This is a schematic diagram of the experimental operation of a real-time detection device for rock crack changes according to the present invention;

[0057] Figure 4 This is a schematic diagram of the photosensitive receiving screen of a real-time rock crack change detection device of the present invention;

[0058] Figure 5This is a schematic diagram of the reflection principle for real-time detection of rock crack changes according to the present invention;

[0059] Figure 6 This is a schematic diagram of the architecture of a real-time rock crack change detection system according to the present invention;

[0060] Figure 7 This is a schematic diagram of the architecture of a real-time rock crack change detection platform according to the present invention;

[0061] In the diagram: 1-Axial pressure rod; 2-Pressure pump inlet valve; 3-Triaxial inlet valve; 4-Triaxial return valve; 5-Pressure pump return valve; 6-Hydraulic pump pressurization key; 7-Hydraulic pump stop key; 8-Return negative pressure key; 9-Water pump outlet valve; 10-Triaxial water inlet valve; 11-Triaxial return valve; 12-Water pump return valve; 13-Base; 14-Base water channel; 15-Base water inlet; 16-Top seat; 17-Top seat outlet; 18- Upper water channel; 19-High-strength glass cover; 20-Water pressure pump pressurization key; 21-Water pressure pump stop key; 22-Return water negative pressure key; 23-Osmotic pressure loading system; 24-Projection light source area; 25-Photosensitive receiving screen; 26-Surface coating rock sample; 27-Optical signal sensing strip; 28-Side adhesion strip of receiving screen; 29-Opaque layer of receiving screen; 30-Optical signal acquisition channel; 31-Optical signal receiver; 32-Containing pressure loading system; 33-Triaxial loading system;

[0062] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] To facilitate a clearer understanding of the objectives, technical solutions, and advantages of this invention, the invention will be further described below in conjunction with the accompanying drawings and specific embodiments. Those skilled in the art can easily understand other advantages and effects of this invention from the content disclosed in this specification.

[0064] This invention can also be implemented or applied through other different specific examples, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of this invention.

[0065] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0066] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Secondly, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0067] Preferably, the real-time detection method for rock fracture changes of the present invention is applied in one or more terminals or servers. The terminal is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0068] The terminal can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal can interact with the customer via a keyboard, mouse, remote control, touchpad, or voice control device.

[0069] This invention provides a method, system, and platform for real-time detection of changes in rock fractures. For example... Figure 1 The diagram shown is a flowchart of a real-time rock fracture change detection method provided in an embodiment of the present invention.

[0070] In this embodiment, the real-time detection method for changes in rock cracks can be applied to a terminal or fixed terminal with display function. The terminal is not limited to personal computers, smartphones, tablets, desktop computers or all-in-one computers with cameras, etc.

[0071] The real-time rock crack change detection method can also be applied to a hardware environment consisting of a terminal and a server connected to the terminal via a network. The network includes, but is not limited to, a wide area network (WAN), a metropolitan area network (MAN), or a local area network (LAN). The real-time rock crack change detection method of this embodiment can be executed by a server, by a terminal, or by both a server and a terminal.

[0072] For example, for terminals requiring real-time detection of rock crack changes, the real-time rock crack change detection function provided by the method of this invention can be directly integrated into the terminal, or a client for implementing the method of this invention can be installed. Alternatively, the method provided by this invention can also run on servers or other devices in the form of a Software Development Kit (SDK), providing an interface for the real-time rock crack change detection function in the form of an SDK. Terminals or other devices can then implement the real-time rock crack change detection function through the provided interface. The invention will be further described below with reference to the accompanying drawings.

[0073] like Figure 1 As shown, the present invention provides a method for real-time detection of changes in rock cracks, the method comprising the following steps:

[0074] S1. Generate and acquire first data corresponding to the changes in cracks in the rock sample in real time; wherein, the first data is the light signal data reflected from the smooth surface of the rock sample;

[0075] S2. Based on the first data and combined with a neural network, create at least one crack feature change data model corresponding to the first data;

[0076] S3. Using the crack feature change data model, generate second data corresponding to the first data; wherein, the second data is crack feature change data corresponding to the rock sample.

[0077] The real-time generation and acquisition of first data corresponding to the changes in cracks in the rock sample also includes:

[0078] S11. Generate and acquire loading pressure data corresponding to the rock sample, and generate first control data based on the loading pressure data; wherein, the loading pressure data includes loading confining pressure data, loading axial pressure data, and loading osmotic pressure data; the first control data is control data for turning on the projection of the light signal;

[0079] S12. Generate and acquire light beam incident angle data corresponding to the rock sample, and generate second control data based on the light beam incident angle data; wherein, the second control data is control data for adjusting the light beam incident angle.

[0080] The step of creating at least one crack feature change data model corresponding to the first data, based on the first data and in conjunction with a neural network, further includes:

[0081] S21. Generate third data corresponding to the first data, and establish a correspondence between the first data and the third data; wherein, the third data is the photoresistor value change data corresponding to the optical signal data;

[0082] S22. Based on the third data, create real-time status data corresponding to the changes in cracks in the rock sample, and generate a change curve corresponding to the real-time status data.

[0083] The step of generating second data corresponding to the first data through the crack feature change data model further includes:

[0084] S31. Create at least one photoresistor array corresponding to the first data, and generate crack feature change data corresponding to the resistance change in the photoresistor array; wherein, the crack feature change data includes crack width change data, crack length change data, and crack change location data;

[0085] S32. Based on the crack feature change data, generate crack width or length estimation data corresponding to the crack feature change data in real time.

[0086] The step of creating at least one photoresistor array corresponding to the first data and generating crack feature change data corresponding to the resistance change in the photoresistor array further includes:

[0087] S311. Generate and acquire resistance change data in the photoresistor array, and generate current change data corresponding to the resistance change data;

[0088] S312. The resistance change data is fused and processed, and combined with the corresponding current change data, damage change data corresponding to the rock sample is generated.

[0089] The step of generating second data corresponding to the first data through the crack feature change data model further includes:

[0090] S33. Generate two-dimensional shape change data corresponding to the second data based on the second data;

[0091] S34. Based on the two-dimensional shape change data and combined with the photosensitive element parameter change data, create shape mapping relationship data corresponding to the cracks in the rock sample; wherein, the photosensitive element parameter change data includes emitted light parameter data, current parameter data, and resistance parameter data;

[0092] S35. Based on the shape mapping relationship data, generate a calibration curve corresponding to the crack feature change data.

[0093] Specifically, in embodiments of the present invention, such as Figures 2-5As shown, this invention provides a triaxial optical reflection testing device and method for real-time measurement of crack changes, addressing the problem of the inability to measure crack changes in real time during rock mechanics experiments. Traditional rock mechanics testing methods cannot directly observe crack changes; the failure mechanism can only be inferred from the rock samples after the experiment. This invention designs a device for real-time measurement of crack changes, capable of recording the real-time changes in cracks in rock samples. The main component of this device is a photosensitive receiving screen. Before the experiment, a light-reflecting material is uniformly coated onto the surface of the rock sample, followed by confining pressure loading, axial pressure loading, and osmotic pressure loading. During the experiment, the photosensitive receiving screen is wrapped around a high-strength glass cover, and the light source projection area projects a beam of light onto the rock sample. When cracks are formed due to rock damage, they cannot reflect light because the cracks lack coating. Changes in light reflection are recorded in real time through a light signal acquisition channel and a light signal receiver.

[0094] Preferably, the triaxial reflective testing device for real-time measurement of crack changes includes the following functional structures: an axial loading rod, made of high-strength steel, which applies axial pressure to the rock sample through a top seat; a seepage loading system, consisting of water, a water pump, valves, and hoses, which applies osmotic pressure to the bottom of the rock sample through a pre-reserved channel; a confining pressure loading system, consisting of hydraulic oil, a hydraulic pump, valves, and hoses, which applies confining pressure to the periphery of the rock sample through a pre-reserved channel; a triaxial loading system, which applies axial pressure, osmotic pressure, and confining pressure to the rock sample; a photosensitive receiving screen, which records the changes in light signals caused by crack formation and development during rock damage; and a surface-coated rock sample, which reflects the projected light beam.

[0095] The triaxial loading system features a high-strength glass cover on its sides, allowing light to pass through and project onto the rock sample. The light-sensing receiving screen uses dark rubber as its main material to isolate external light source interference, facilitating its fit around the glass cover and the installation of the projection light source area and light signal sensing strip.

[0096] The light-sensing receiving screen has a projection light source area composed of many neatly arranged small lamps, the angle of which can be pre-adjusted to adjust the incident angle of the light beam and cover the entire surface of the rock sample.

[0097] The aforementioned light-sensing receiving screen is composed of photoresistors. When the light source changes or disappears, its resistance value changes, which in turn affects the change in the current magnitude. When cracks appear on the rock surface, since the cracks have no coating and cannot reflect the light source, the light signal sensing band at the corresponding position records the changes in rock sample damage.

[0098] The aforementioned light-sensing receiving screen has side adhesive straps at both ends for fixed installation. The surface coating uses reflective coatings such as silver and aluminum, which can reflect the incident light beam onto the light signal sensing strip at a reflection angle.

[0099] In other words, the present invention proposes a triaxial test device and method for real-time measurement of crack changes by optical reflection. Its main features include: an osmotic pressure loading system 23, a light-sensing receiving screen 25, a confining pressure loading system 32, and a triaxial loading system 33.

[0100] The axial loading rod 1 is made of high-strength steel and is used to apply axial stress to the rock sample.

[0101] The pressurization pump inlet valve 2 belongs to the confining pressure loading system 32 and uses a screw switch to control the entry of hydraulic oil into the confining pressure loading system 32.

[0102] The triaxial oil inlet valve 3 belongs to the triaxial loading system 33. It is connected to the pressure pump oil inlet valve 2 through a rubber tube and is sealed by a nut. It is kept open for a long time to allow hydraulic oil in the triaxial loading system 33 to enter.

[0103] The triaxial return valve 4 belongs to the triaxial loading system 33. It is connected to the return valve 5 of the pressure pump through a rubber tube and is sealed by a nut. It is kept open for a long time to allow the hydraulic oil in the triaxial loading system 33 to return.

[0104] The pressurization pump return valve 5 belongs to the confining pressure loading system 32 and uses a screw switch to control the hydraulic oil return flow in the confining pressure loading system 32.

[0105] The hydraulic pump pressurization key 6 can generate positive pressure on the hydraulic oil, thereby increasing the confining pressure of the triaxial loading system 33.

[0106] The oil pump stop button 7 can stop the oil pump from working, thereby stopping pressurization or stopping oil return.

[0107] The aforementioned return oil negative pressure key 8 can generate negative pressure on the hydraulic oil, thereby drawing the hydraulic oil in the axial pressure loading system 33 back to the confining pressure loading system 32 to achieve hydraulic oil recycling.

[0108] The water pressure pump outlet valve 9 belongs to the osmotic pressure loading system 23 and uses a screw switch to control the osmotic pressure water flow into the confining pressure loading system 32.

[0109] The triaxial inlet valve 10 belongs to the triaxial loading system 33. It is connected to the water pressure pump outlet valve 9 through a rubber tube and is sealed by a nut. It can be opened and closed by a knob to allow the osmotic pressure water in the triaxial loading system 33 to enter or unload the osmotic pressure.

[0110] The triaxial return water valve 11 belongs to the triaxial loading system 33. It is connected to the water pressure pump outlet valve 12 through a rubber tube and is sealed by a nut. It is kept open for a long time to allow the osmotic pressure water in the triaxial loading system 33 to flow back.

[0111] The water pressure pump return valve 12, belonging to the osmotic pressure loading system 23, uses a screw switch to control the backflow of osmotic pressure water in the confining pressure loading system 32. The base 13, made of high-strength steel, serves to fix the bottom of the rock sample and bear weight. The base water channel 14, a hollow iron pipe, connects the triaxial inlet valve 10 to the base inlet 15, allowing osmotic pressure water to seep upwards from the bottom of the rock sample.

[0112] The base inlet 15 is a hollow hole through which water flows, subjecting the bottom of the rock sample to osmotic pressure. The top seat 16, made of high-strength steel, serves to fix the top of the rock sample and transmit axial pressure. The top seat outlet 17 is a hollow circular hole that allows pore water seeping from the bottom of the rock to the top to flow out. The upper water pipe 18 is a hollow iron pipe that connects the top seat outlet 17 to the three-axis return water valve 12, allowing pore water to be discharged. The high-strength glass cover 19 is made of high-compression-strength glass. The light-sensing receiving screen 25 is mounted around the high-strength glass cover, and the projection light source area 24 can project a beam of light at a certain angle onto the surface-coated rock sample 26 through the high-strength glass cover 19. The water pressure pump pressurization button 20 applies positive water pressure when started, causing the water in the seepage loading system 23 to be loaded to the bottom of the rock sample. During startup, the osmotic pressure gradually increases until the preset osmotic pressure is reached. Pressing the water pressure pump stop button 21 then completes the process.

[0113] The water pump stop button 21 can stop the water pump from applying positive pressure and applying negative pressure backflow. The water return negative pressure button 22 can start the water pump to increase negative pressure, thereby adjusting the osmotic pressure at the top of the rock, or to pump the water in the pipe back for recycling at the end of the test. The seepage pressurization system 23 consists of the water pump outlet valve 9, the water pump return valve 11, the water pump pressurization button 20, the water pump stop button 21, and the water return negative pressure button 22. It can apply osmotic pressure at the bottom of the rock and adjust the osmotic pressure at the top of the rock. The projection light source area 24 is the upper structure of the light-sensing receiving screen 25 and consists of many small lamps. When the small lamps are activated, they can project light beams, and the light beams projected by the numerous lamps can cover the rock sample. The light-sensing receiving screen 25 consists of the projection light source area 24, the light signal sensing strip 27, the receiving screen side adhesive strip 28, the receiving screen opaque layer 29, and the light signal acquisition channel 30. It can project a beam of light onto the surface-coated rock sample 26 through the projection light source area 24, and reflect it at a certain reflection angle onto the light signal sensing band 27. During installation, the light-sensing receiving screen 25 is wrapped around the high-strength glass cover 19 and tightly fixed by the side adhesive tapes 28 on both sides. The surface-coated rock sample 26 uses a mirror-like silver or aluminum reflective coating, which evenly covers the surface of the rock sample and reflects light beams. The light signal sensing band 27 is composed of photoresistors; the increase or disappearance of light causes a change in resistance, thereby changing the current magnitude, which can be further converted into crack morphology data. When cracks appear in the rock sample, since the cracks cannot reflect light, the photoresistors in the corresponding reflection area change, recording the crack morphology. The side adhesive tapes 28, present at both ends of the light-sensing receiving screen 25, can be adjusted in tightness by adjusting the adhesive width, ensuring the light-sensing receiving screen 25 is firmly installed on the high-strength glass cover 19.

[0114] The opaque layer 29 of the receiving screen is mainly composed of dark-colored rubber such as black, which on the one hand avoids interference from external light sources, and on the other hand facilitates the setting and installation of the projection light source area 24 and the light signal sensing strip 27.

[0115] The optical signal acquisition channel 30 is a preset circuit signal transmission channel, connecting the optical signal sensing band 27 and the optical signal receiving instrument 31. The optical signal receiving instrument 31 can convert the electrical signals recorded by the optical signal sensing band 27 into crack morphology data.

[0116] The triaxial loading system 33 consists of an axial loading rod 1, a triaxial oil inlet valve 3, a triaxial oil return valve 4, a triaxial water inlet valve 10, a triaxial water return valve 12, a base 13, a base water channel 14, a base water inlet 15, a top seat 16, a top seat water outlet 17, an upper water pipe 18, and a high-strength glass cover 19. It can apply axial pressure, osmotic pressure, and circumferential pressure to the rock sample.

[0117] To achieve the above-mentioned device function, this embodiment of the invention also provides a method for measuring a triaxial surface reflection test device for real-time measurement of crack changes, comprising the following steps:

[0118] S01. Apply a light-reflecting material evenly to the surface of the rock sample. Reflective coatings typically include metallic coatings (such as aluminum or silver), mirror coatings, high-gloss coatings (such as high-gloss polymer coatings), and some specially designed optical coatings. These coatings effectively reflect light, producing a shiny effect. S02. Seal and fix the bottom of the coated rock sample to the upper part of the base with a waterstop, and seal and fix the top of the rock sample to the lower part of the top seat with a waterstop. S03. Apply confining pressure: Open the inlet valve and return valve of the pressure pump, start the hydraulic pump pressurization key, and hydraulic oil enters the triaxial chamber through the triaxial inlet valve; when hydraulic oil flows out from the triaxial return valve, the confining pressure chamber is full of oil, and the pressure pump return valve is closed; the confining pressure continuously increases, and when the preset confining pressure is reached, close the pressure pump inlet valve and then open the hydraulic pump stop key. S04. Apply axial pressure, driving the axial loading rod to move downwards. After contacting the top seat, the rock sample obtains initial pressure. S05. After preloading pressure, stop; S06. Apply osmotic pressure by opening the triaxial inlet valve, the water pump outlet valve, the water pump return valve, and the water pump pressurization button. The osmotic pressure will continuously increase until it reaches the preset value, then start the water pump stop button; S07. Wrap the light-sensing receiving screen around the high-strength glass cover and connect the adhesive tapes on the sides of the receiving screen at both ends to ensure a tight connection. Connect the light signal acquisition channel to the light signal receiver; S08. Apply downward pressure continuously at a fixed displacement rate using the axial loading rod until the rock sample fractures; S09. Remove the light-sensing receiving screen and untie the adhesive tapes on the sides of the receiving screen at both ends. A photoresistor strip is sewn onto the receiving screen. A photoresistor, also known as a photoresistor or photodependent resistor, is a photosensitive element whose resistance changes with light intensity. They are widely used in light detection, automatic brightness adjustment, and security systems. Currently, there are many photoresistor brands on the market, including but not limited to Vishay, ON Semiconductor, ROHM, and Panasonic. The products vary in specifications and performance to meet the needs of different application scenarios.

[0119] Photoresistors are mainly divided into two categories: cadmium sulfide (CdS) photoresistors and zinc sulfide (ZnS) photoresistors. CdS photoresistors are more sensitive to visible light, while ZnS photoresistors are more sensitive to ultraviolet light. Their working principle is based on the internal photoelectric effect: the stronger the light, the lower the resistance. As the light intensity increases, the resistance decreases rapidly, reaching below 1 kΩ. Photoresistors are extremely sensitive to light; in the absence of light, their dark resistance can typically reach 1.5 MΩ. This instrument is used for indoor light detection; products that are more sensitive to artificial light sources can be selected.

[0120] When selecting a photoresistor, the following key parameters need to be considered: Photoresistor value: The resistance value under no-light conditions, typically ranging from several thousand ohms to several megaohms. Photosensitivity: The degree to which the resistance value changes with light intensity, usually expressed as the rate of change of resistance with varying light intensity. Response time: The time required for the resistance value to stabilize after a change in light intensity, including rise time (from dark to bright) and fall time (from bright to dark). Spectral response: The sensitivity of the photoresistor to different wavelengths of light, which determines its performance under different light sources. Operating temperature: The temperature range within which the photoresistor can operate normally.

[0121] The product parameters are as follows: Product Model: 5528; Maximum Pressure (VDC): 150; Maximum Power Consumption (MW): 100; Ambient Temperature (°C): -30~+70; Spectral Peak (Nm): 540; Bright Resistance (kiloohms): 10-20; Dark Resistance (megaohms): 1; Response Time (ms): Rise: 20, Fall: 30; Illuminance Resistance Characteristic: 3.

[0122] S06. Unload osmotic pressure: Close the triaxial inlet valve. S010. Unload axial pressure: Raise the axial loading rod upwards at a fixed rate to remove the load. S011. Unload confining pressure: Open the pressurized pump return valve, then open the pressurized pump inlet valve, and activate the return negative pressure key until the triaxial return valve stops discharging oil.

[0123] In this invention, light intensity at different locations on a surface can be detected using an array of photosensitive elements, each of which can independently respond to the light intensity on its surface. The following are some of the techniques employed:

[0124] Photodiode Array: A photodiode array consists of multiple photodiodes, each capable of independently detecting the light intensity on it. These arrays are commonly used in spectrometers and image sensors. The current output of a photodiode is proportional to the light intensity on it, and can be used to measure the distribution of light intensity.

[0125] CMOS image sensor: A CMOS image sensor contains an array of many individual pixels, each pixel containing one or more photosensitive elements. These sensors can capture images and also measure the distribution of light intensity. The output of each pixel can be used to determine the light intensity at that pixel location.

[0126] CCD image sensors: Similar to CMOS sensors, CCD (charge-coupled device) image sensors also consist of an array, but their working principle is slightly different. CCD sensors can also be used to capture images and measure light intensity distribution.

[0127] Photoresistor array: This involves fabricating an array of multiple photoresistors, each responding independently to the light intensity on its surface. Such arrays can be used to measure the distribution of light intensity on a surface, but may be limited by resolution and sensitivity.

[0128] The above techniques can provide detailed information about light intensity distribution. During the experiment, changes in photocurrent or voltage are measured, and these changes can then be converted into changes in resistance. These changes in resistance can further determine the development and changes of cracks. By combining these sensors with appropriate circuitry and data processing systems, it is possible to analyze and record resistance changes at different locations.

[0129] Two-dimensional shape change: When the photosensitive element is located at the crack, the reflected light weakens, the current decreases, and the resistance increases. Each element can independently capture the light intensity. The position of each element corresponds to a certain positional relationship of the rock. For the element corresponding to the crack, the current decreases, and the shape of the crack can be mapped by changing the position of the elements. When the crack width or length increases, the number of elements with corresponding current changes increases and their positions also expand.

[0130] Assuming the resistance of a normally reflecting component is x, as the crack width increases, the light source is absorbed, the reflected light weakens, the light intensity at the component's location decreases, the current decreases, and the resistance increases. The wider the crack, the larger the affected component area.

[0131] The relationship between the change in photoresistor value and the crack width depends on several factors, including the characteristics of the light source, the sensitivity of the photoresistor, and the reflection, refraction, and scattering properties of light. An increase in crack width may cause more light to be absorbed or scattered by the crack, thereby reducing the amount of light reflected back to the photoresistor and leading to an increase in resistance.

[0132] Determining this relationship requires experimental calibration. A calibration curve can be established by measuring the response of the photoresistor under known crack width and length conditions, and by analyzing a large amount of mapping data using a neural network, showing the relationship between two parameters: crack width, length, and resistance changes.

[0133] The resistance in the center of a crack might be 1 ohm, while the resistance of surrounding components might increase. This relationship can be determined through calibration. The response of a photoresistor can be measured with a known crack width, establishing a calibration curve for the crack width and length versus resistance changes. The component with the highest resistance (crack formation zone) is affected; as the crack width increases (crack formation zone), the affected component's range expands. For components at the crack's development location, as the crack develops, the decreasing resistance exhibits a predictable pattern. For example, an increase in resistance acceleration indicates the crack width development in that area.

[0134] If the relationship between crack width, length, and changes in photoresistor values ​​has been established through experiments and machine learning training, then in practical applications, the crack width and length can be estimated by measuring the resistance values ​​of the photoresistors. By monitoring which photoresistors showed changes in resistance values, the approximate location and length of the crack can be determined.

[0135] To improve accuracy, it may be necessary to use multiple photoresistor arrays to monitor different parts of the crack and use data fusion techniques to synthesize this information to obtain a more accurate crack width estimate.

[0136] In summary, using photoresistor arrays to monitor crack width and length does require a series of pre-set experimental data for machine learning to establish the relationship between changes in photoresistor values ​​and crack characteristics. There is a possibility that the actual crack length may not be accurately measured, especially when the crack shape is complex or branching. In such cases, the only solutions are to increase the array density of the photoresistors to improve measurement resolution or to use machine learning data to numerically approximate the crack length.

[0137] While machine learning techniques like convolutional neural networks (CNNs) are incredibly powerful at processing image data, their results are often black boxes, making it difficult to extract explicit mathematical formulas directly. If explicit mathematical formulas are required, traditional methods such as linear regression or multinomial regression are needed for formula fitting.

[0138] This method extracts an approximate mathematical formula, that is, it fits the output of a CNN by training a simple linear or polynomial model. This method can help understand the relationship between changes in photoresistivity and crack width and length.

[0139] To fit the mathematical model of the relationship between changes in photoresistance values ​​and crack width and length, a combination of convolutional neural networks (CNN) and linear regression was used. The specific steps are as follows:

[0140] Data preparation: First, read the data containing the position of the photosensitive elements, changes in resistance, and changes in crack width and length. Based on the position and resistance changes of the photosensitive elements, create a two-dimensional array to represent the photosensitive element array.

[0141] Features and target variables: A two-dimensional array is used as the feature, and the changes in crack width and length are used as the target variables. The dataset is then split into training and testing sets, and an additional dimension is added to adapt to the input format of the CNN.

[0142] Building and training CNN models: Use Keras to build a simple CNN model, including convolutional layers, pooling layers, and fully connected layers. Train two CNN models separately, one to predict changes in crack width and the other to predict changes in crack length.

[0143] Prediction using a CNN model: The trained CNN model is used to make predictions on the training and test sets to obtain the predicted changes in crack width and length.

[0144] Using linear regression to fit the CNN output: To extract an approximate mathematical formula, linear regression is used to fit the CNN output. The coefficients obtained through linear regression fitting provide an approximate mathematical formula to describe the relationship between the change in photoresistivity and the crack width and length.

[0145] Print mathematical formulas: Based on the coefficients obtained from linear regression fitting, print out the mathematical formulas for predicting crack width and length changes.

[0146] Evaluate the linear regression model: Use test data to make predictions and calculate the mean squared error (MSE) to evaluate the performance of the linear regression model.

[0147] The above method not only utilizes the powerful feature extraction capabilities of machine learning, but also extracts a clear mathematical formula through linear regression, thereby better fitting the relationship between the change in photoresistor value and the crack width and length.

[0148] In this invention, a machine learning (CNN convolutional neural network) model is used for prediction: first, the CNN model is used to predict the data to obtain the predicted changes in crack width and length.

[0149] Fitting the CNN output using linear regression: Then use linear regression or polynomial regression to fit the CNN output to obtain an approximate mathematical formula.

[0150] Code implementation: The previously trained CNN model will be used, and linear regression will be used to fit the CNN output.

[0151]

[0152]

[0153]

[0154]

[0155]

[0156] Code Explanation: Data Reading: Use Pandas to read data from a CSV file. Creating a 2D Array: Create a 2D array to represent the photosensitive element array based on the position and resistance changes of the photosensitive elements. Features and Target Variables: Use the 2D array as features and the changes in crack width and length as target variables. Splitting the Dataset: Split the dataset into training and test sets. Adding Dimension: Add a dimension to adapt to the input format of the CNN. Building the CNN Model: Build a simple CNN model using Keras, including convolutional layers, pooling layers, and fully connected layers. Training the Model: Train models to predict crack width and length changes separately. Predicting with the CNN Model: Use the trained CNN model to make predictions on the training and test sets. Fitting the CNN Output with Linear Regression: Fit the CNN output with linear regression to obtain an approximate mathematical formula. Printing the Mathematical Formula: Print the mathematical formulas for predicting crack width and length changes based on the coefficients obtained from the linear regression fit. Evaluating the Linear Regression Model: Use test data for prediction and calculate the mean squared error (MSE) to evaluate the performance of the linear regression model.

[0157] To achieve the above objectives, the present invention also provides a real-time detection system for changes in rock cracks, such as... Figure 6 As shown, the system is used to implement the real-time detection method for rock crack changes; the system specifically includes: a first data generation unit, used to generate and acquire first data corresponding to the crack changes of the rock sample in real time; wherein, the first data is light signal data reflected from the smooth surface of the rock sample; a data model creation unit, used to create at least one crack feature change data model corresponding to the first data based on the first data and combined with a neural network; and a second data generation unit, used to generate second data corresponding to the first data through the crack feature change data model; wherein, the second data is crack feature change data corresponding to the rock sample.

[0158] The first data generation unit further includes: a first data generation module, used to generate and acquire loading pressure data corresponding to the rock sample, and generate first control data based on the loading pressure data; wherein the loading pressure data includes loading confining pressure data, loading axial pressure data, and loading osmotic pressure data; the first control data is control data for enabling optical signal projection; and a second data generation module, used to generate and acquire light beam incident angle data corresponding to the rock sample, and generate second control data based on the light beam incident angle data; wherein the second control data is control data for adjusting the light beam incident angle.

[0159] And / or, the data model creation unit further includes: a third data generation module, used to generate third data corresponding to the first data, and establish a correspondence between the first data and the third data; wherein, the third data is photoresistor value change data corresponding to optical signal data; and a first data creation module, used to create real-time state data corresponding to the crack changes in the rock sample based on the third data, and generate a change curve corresponding to the real-time state data.

[0160] And / or, the second data generation unit further includes: a second data creation module, configured to create at least one photoresistor array corresponding to the first data, and generate crack feature change data corresponding to the resistance change in the photoresistor array; wherein the crack feature change data includes crack width change data, crack length change data, and crack change location data; and a fourth data generation module, configured to generate crack width or length estimation data corresponding to the crack feature change data in real time based on the crack feature change data.

[0161] And / or, the second data creation module further includes: a fifth data generation module, used to generate and acquire resistance change data in the photoresistor array, and generate current change data corresponding to the resistance change data; and a data fusion processing module, used to fuse and process the resistance change data, and combine it with the corresponding current change data to generate damage change data corresponding to the rock sample.

[0162] And / or, the second data generation unit further includes: a sixth data generation module, used to generate two-dimensional shape change data corresponding to the second data based on the second data; a third data creation module, used to create shape mapping relationship data corresponding to the rock sample crack based on the two-dimensional shape change data and combined with photosensitive element parameter change data; wherein the photosensitive element parameter change data includes emitted light parameter data, current parameter data and resistance parameter data; and a seventh data generation module, used to generate a calibration curve corresponding to the crack feature change data based on the shape mapping relationship data.

[0163] In the system embodiment of the present invention, the specific details of the method steps involved in the real-time detection of rock crack changes have been described above. That is to say, the functional modules in the system are used to implement the steps or sub-steps in the above method embodiment, which have been described above and will not be repeated here.

[0164] To achieve the above objectives, the present invention also provides a real-time detection device for rock crack changes, the device being used to implement the aforementioned real-time detection method for rock crack changes;

[0165] The device includes: an axial loading rod for applying axial pressure to the rock sample through a top seat; a seepage loading system for loading osmotic pressure to the bottom of the rock sample through a reserved channel; a confining pressure loading system for loading confining pressure to the periphery of the rock sample through a reserved channel; and a triaxial loading system for providing axial pressure, osmotic pressure, and confining pressure applied to the rock sample.

[0166] The device is also equipped with a light-sensitive receiving screen for recording changes in light signals caused by the generation and development of cracks when rocks are damaged; the rock sample is a rock sample with a coating on its surface.

[0167] In the embodiment of the device of the present invention, the specific details of the method steps involved in the real-time detection of rock crack changes have been described above. That is to say, the functional structure in the device is used to implement the steps or sub-steps in the above method embodiment, which have been described above and will not be repeated here.

[0168] To achieve the above objectives, the present invention also provides a real-time detection platform for changes in rock fractures, such as... Figure 7 As shown, it includes a processor, a memory, and a real-time rock fracture change detection platform control program; wherein, the processor executes the real-time rock fracture change detection platform control program, and the real-time rock fracture change detection platform control program is stored in the memory, and the real-time rock fracture change detection platform control program implements the steps of the real-time rock fracture change detection method. For example:

[0169] S1. Generate and acquire first data corresponding to the crack changes in the rock sample in real time; wherein, the first data is light signal data reflected from the smooth surface of the rock sample; S2. Based on the first data and combined with a neural network, create at least one crack feature change data model corresponding to the first data; S3. Generate second data corresponding to the first data through the crack feature change data model; wherein, the second data is crack feature change data corresponding to the rock sample.

[0170] The specific details of the steps have been explained above and will not be repeated here.

[0171] In this embodiment of the invention, the real-time rock fracture change detection platform has a built-in processor, which can be composed of integrated circuits. For example, it can be composed of a single packaged integrated circuit, or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor connects to various components using various interfaces and lines, and executes programs or units stored in memory, as well as calling data stored in memory, to perform various functions of real-time rock fracture change detection and data processing.

[0172] The memory is used to store program code and various data. It is installed in the real-time rock fracture change detection platform and can complete the access of programs or data at high speed and automatically during operation.

[0173] The memory includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0174] This invention generates and acquires first data corresponding to changes in cracks in rock samples in real time through a method. The first data is light signal data reflected from the smooth surface of the rock sample. Based on the first data and combined with a neural network, at least one crack feature change data model corresponding to the first data is created. Through the crack feature change data model, second data corresponding to the first data is generated. The second data is crack feature change data corresponding to the rock sample. The invention also includes a system, device, and platform corresponding to the method, which effectively solves the problem of being unable to measure damage morphology changes throughout the rock mechanics experiment, ensuring that the physical data of the rock sample is recorded. The measured data can be used for rock damage constitutive model research, rock damage mechanical behavior research, and numerical simulation fitting.

[0175] In other words, the triaxial experimental setup of this invention can record the real-time changes in cracks in rock samples. Furthermore, the optical receiving screen can be installed in existing conventional uniaxial experiments, making it simple and easy to operate. In addition, the crack change data recorded by this invention can be used for numerical model fitting. That is, this invention can measure the changes in cracks in rock samples in real time and record relevant data; this data can be used for rock damage constitutive model research, rock damage mechanical behavior research, and numerical simulation fitting. Compared with existing technologies, this invention has the advantages of real-time crack change measurement, simplicity, and ease of operation, and can improve the accuracy and reliability of rock mechanics experiments.

[0176] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for real-time detection of changes in rock cracks, characterized in that, The method includes the following steps: The system generates and acquires first data corresponding to the changes in cracks in the rock sample in real time; wherein, the first data is the light signal data reflected from the smooth surface of the rock sample. Based on the first data and combined with a neural network, at least one crack feature change data model corresponding to the first data is created. The data model of crack feature changes generates second data corresponding to the first data; it also includes creating at least one photoresistor array corresponding to the first data and generating crack feature change data corresponding to the resistance changes in the photoresistor array; generating and acquiring the resistance change data in the photoresistor array and generating current change data corresponding to the resistance change data; fusing and processing the resistance change data and combining it with the corresponding current change data to generate damage change data corresponding to the rock sample; and generating crack width or length estimation data corresponding to the crack feature change data in real time based on the crack feature change data; wherein, the second data is crack feature change data corresponding to the rock sample; the crack feature change data includes crack width change data, crack length change data, and crack change location data.

2. The method for real-time detection of rock crack changes according to claim 1, characterized in that, The real-time generation and acquisition of first data corresponding to the changes in cracks in the rock sample also includes: The loading pressure data corresponding to the rock sample is generated and acquired, and first control data is generated based on the loading pressure data; wherein, the loading pressure data includes loading confining pressure data, loading axial pressure data and loading osmotic pressure data; the first control data is control data for turning on the projection of the light signal; Generate and acquire light beam incident angle data corresponding to the rock sample, and generate second control data based on the light beam incident angle data; wherein, the second control data is control data for adjusting the light beam incident angle.

3. The method for real-time detection of rock crack changes according to claim 1, characterized in that, The step of creating at least one crack feature change data model corresponding to the first data, based on the first data and in conjunction with a neural network, further includes: Generate third data corresponding to the first data, and establish a correspondence between the first data and the third data; wherein, the third data is the photoresistor value change data corresponding to the optical signal data; Based on the third data, real-time status data corresponding to the changes in cracks in the rock sample is created, and a change curve corresponding to the real-time status data is generated.

4. The method for real-time detection of rock crack changes according to claim 1, characterized in that, The step of generating second data corresponding to the first data through the crack feature change data model further includes: Based on the second data, generate two-dimensional shape change data corresponding to the second data; Based on the two-dimensional shape change data and combined with the photosensitive element parameter change data, shape mapping relationship data corresponding to the cracks in the rock sample is created; wherein, the photosensitive element parameter change data includes emitted light parameter data, current parameter data and resistance parameter data; Based on the shape mapping relationship data, a calibration curve corresponding to the crack feature change data is generated.

5. A real-time detection system for changes in rock cracks, characterized in that, The system is used to implement the real-time detection method for rock fracture changes as described in any one of claims 1 to 4; the system includes: The first data generation unit is used to generate and acquire first data corresponding to the changes in cracks in the rock sample in real time; wherein, the first data is the light signal data reflected from the smooth surface of the rock sample; A data model creation unit is used to create at least one crack feature change data model corresponding to the first data, based on the first data and in combination with a neural network. The second data generation unit is used to generate second data corresponding to the first data through the crack feature change data model; wherein, the second data is crack feature change data corresponding to the rock sample.

6. The real-time detection system for rock crack changes according to claim 5, characterized in that, The first data generation unit further includes: The first data generation module is used to generate and acquire loading pressure data corresponding to the rock sample, and generate first control data based on the loading pressure data; wherein, the loading pressure data includes loading confining pressure data, loading axial pressure data, and loading osmotic pressure data; the first control data is control data for turning on the projection of the light signal; The second data generation module is used to generate and acquire light beam incident angle data corresponding to the rock sample, and generate second control data based on the light beam incident angle data; wherein, the second control data is control data for adjusting the light beam incident angle. And / or, the data model creation unit further includes: The third data generation module is used to generate third data corresponding to the first data and establish a correspondence between the first data and the third data; wherein, the third data is the photoresistor value change data corresponding to the optical signal data; The first data creation module is used to create real-time status data corresponding to the changes in cracks in the rock sample based on the third data, and to generate a change curve corresponding to the real-time status data. And / or, the second data generation unit further includes: The second data creation module is used to create at least one photoresistor array corresponding to the first data, and generate crack feature change data corresponding to the resistance change in the photoresistor array; wherein, the crack feature change data includes crack width change data, crack length change data, and crack change location data. The fourth data generation module is used to generate estimated crack width or length data corresponding to the crack feature change data in real time based on the crack feature change data. And / or, the second data creation module further includes: The fifth data generation module is used to generate and acquire resistance change data in the photoresistor array, and generate current change data corresponding to the resistance change data. The data fusion processing module is used to fuse and process the resistance change data, and combine it with the corresponding current change data to generate damage change data corresponding to the rock sample. And / or, the second data generation unit further includes: The sixth data generation module is used to generate two-dimensional shape change data corresponding to the second data based on the second data; The third data creation module is used to create shape mapping relationship data corresponding to the cracks in the rock sample based on the two-dimensional shape change data and combined with the photosensitive element parameter change data; wherein, the photosensitive element parameter change data includes emitted light parameter data, current parameter data and resistance parameter data; The seventh data generation module is used to generate a calibration curve corresponding to the crack feature change data based on the shape mapping relationship data.

7. A real-time detection device for changes in rock cracks, characterized in that, The device is used to implement the real-time detection method for rock fracture changes as described in any one of claims 1 to 4; The device includes: an axial loading rod for applying axial pressure to the rock sample through a top seat; a seepage loading system for loading osmotic pressure to the bottom of the rock sample through a reserved channel; a confining pressure loading system for loading confining pressure to the periphery of the rock sample through a reserved channel; and a triaxial loading system for providing axial pressure, osmotic pressure, and confining pressure applied to the rock sample. The device is also equipped with a light-sensitive receiving screen for recording changes in light signals caused by the generation and development of cracks when rocks are damaged; the rock sample is a rock sample with a coating on its surface.

8. A real-time detection platform for changes in rock cracks, characterized in that, The system includes a processor, a memory, and a real-time rock fracture change detection platform control program; wherein the processor executes the real-time rock fracture change detection platform control program, the real-time rock fracture change detection platform control program is stored in the memory, and the real-time rock fracture change detection platform control program implements the real-time rock fracture change detection method as described in any one of claims 1 to 4.

Images