Drilling combined detection method and system capable of reducing the number of advance drillings in a tunnel

Abstract

The present disclosure provides a drilling combined detection method and system which can reduce the number of advanced drilling in a tunnel, relates to the field of roadway engineering detection, and comprises the following steps: obtaining radar data and transient electromagnetic data of a measurement point depth and a target area, wherein the radar data and the transient electromagnetic data are collected by an integrated detection device in a drilling; performing feature extraction on the radar data and the transient electromagnetic data respectively, fusing the extracted features based on the contribution weights of the radar and the transient electromagnetic, and obtaining a fused feature vector; inverting the dielectric constant and the resistivity by using a trained physical information neural network based on the measurement point depth and the fused feature vector; and identifying a geological abnormal body in the target area according to the dielectric constant and the resistivity. The present disclosure combines drilling radar and drilling transient electromagnetic, reduces the number of advanced drilling, reduces the detection cost, and ensures full-area coverage of roadway pre-probing.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of roadway engineering detection, in particular to a drilling combined detection method and system capable of reducing the number of tunnel roadway advance drill holes. BACKGROUND

[0002] Before the construction of a mine, advance drill holes must be laid according to the specification requirements; in the case of complex geology and hydrology, multiple advance drill holes are needed to survey the regional geological conditions; in general, at least two advance drill holes are needed; however, advance drill holes are expensive, and multiple advance drill holes will significantly increase the cost of the mine; and only drilling will cause the problem of "one hole view" and limited understanding of the underground geological conditions; therefore, the existing detection scheme is difficult to balance the detection cost and detection accuracy. SUMMARY

[0003] The present disclosure is proposed to solve the above problems, and a drilling combined detection method and system capable of reducing the number of tunnel roadway advance drill holes are provided, which combines drilling radar and drilling transient electromagnetic methods, reduces the number of advance drill holes, reduces the detection cost, ensures full-area coverage of the roadway advance exploration, and improves the detection accuracy.

[0004] According to some embodiments, the present disclosure adopts the following technical solutions:

[0005] The drilling combined detection method capable of reducing the number of tunnel roadway advance drill holes comprises:

[0006] Obtaining radar data and transient electromagnetic data of a measurement point depth and a target area, the radar data and the transient electromagnetic data being collected by an integrated detection device in a drill hole;

[0007] Respectively extracting features of the radar data and the transient electromagnetic data, fusing the extracted features based on the contribution weights of the radar and the transient electromagnetic method, and obtaining a fused feature vector;

[0008] Based on the measurement point depth and the fused feature vector, using a trained physical information neural network to perform inversion on the dielectric constant and the resistivity;

[0009] Identifying a geological anomaly body of the target area according to the dielectric constant and the resistivity;

[0010] The integrated detection device comprises a GPR probe module and a TEM probe module, the GPR probe module adopts multiple sets of transmitting and receiving antennas, and the TEM probe module adopts coplanar rectangular transmitting and receiving coils to realize zero magnetic flux by adjusting the transmitting and receiving distance.

[0011] According to some embodiments, the present disclosure adopts the following technical solutions:

[0012] The drilling combined detection system capable of reducing the number of advanced drillings in a tunnel and gallery, comprising:

[0013] The acquisition module is configured to acquire radar data and transient electromagnetic data of a measurement point depth and a target area, the radar data and the transient electromagnetic data being collected by an integrated detection device in a drilling hole;

[0014] The extraction module is configured to perform feature extraction on the radar data and the transient electromagnetic data respectively, and fuse the extracted features based on the contribution weights of the radar and the transient electromagnetic to obtain a fused feature vector;

[0015] The inversion module is configured to perform inversion on the dielectric constant and the resistivity by using a trained physical information neural network based on the measurement point depth and the fused feature vector;

[0016] The identification module is configured to identify a geological abnormal body in the target area according to the dielectric constant and the resistivity;

[0017] The integrated detection device comprises a GPR probe module and a TEM probe module, the GPR probe module adopts multiple sets of transmitting and receiving antennas, and the TEM probe module adopts coplanar rectangular transmitting and receiving coils to realize zero magnetic flux by adjusting the transmitting and receiving distance.

[0018] According to some embodiments, the present disclosure adopts the technical scheme as follows:

[0019] A computer program product comprising a computer program, which, when executed by a processor, implements the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and gallery.

[0020] According to some embodiments, the present disclosure adopts the technical scheme as follows:

[0021] A non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implements the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and gallery.

[0022] According to some embodiments, the present disclosure adopts the technical scheme as follows:

[0023] An electronic device comprising a processor, a memory and a computer program; wherein the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device performs the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and gallery.

[0024] Compared with the prior art, the present disclosure has the beneficial effects that:

[0025] (1) The application adopts a modular multi-parameter integrated probe, which contains a zero-flux transient electromagnetic coil and a double-frequency borehole radar antenna, and is suitable for Φ75-160mm boreholes; through the design of a ceramic wear-resistant ring, an electromagnetic telescopic arm, and a backup hydraulic retraction system, dynamic adjustment of the radial size of the probe (contraction ratio up to 1:2.5) and reliable detection in extreme environments (pressure resistance 10MPa, waterproof IP68) are realized, and the problem of sticking caused by size deviation of the borehole in traditional equipment is solved.

[0026] (2) The application adopts a combination of a low-frequency butterfly antenna and a high-frequency microstrip antenna suitable for borehole GPR, which can measure the surrounding rock cracks within 0-5m and the abnormal body section within 0-15m; the design of a standardized microstrip antenna (such as Rogers RO4350B substrate) and FPGA hardware acceleration reduces the manufacturing cost.

[0027] (3) The application adopts a zero-flux transient electromagnetic transceiver coil and proposes a method for calculating the distance between the transmitter and the receiver, which forms zero flux by eccentric placement and greatly reduces the range of the transient electromagnetic blind area.

[0028] (4) The application designs a borehole positioning system based on laser ranging (accuracy ±1mm) and inertial navigation (heading angle error <0.5°), which can provide real-time feedback of the probe inclination and depth; a double-redundancy anti-sticking mechanism is developed, including an electromagnetic trigger type telescopic arm (response time <0.5s) and a hydraulic emergency retraction system (pressure 21MPa), combined with vibration spectrum analysis and wear-resistant ceramic ring wear monitoring, to realize early warning of sticking risk and millisecond-level emergency response, and ensure the safety of deep hole detection.

[0029] (5) The application proposes a dynamic weight fusion technology based on borehole ground penetrating radar (GPR) and transient electromagnetic (TEM), which adaptively allocates the contribution weight of GPR reflection coefficient and TEM apparent resistivity through signal-to-noise ratio (SNR), and constructs a joint feature matrix (including reflection gradient and resistivity time derivative). This method overcomes the limitations of single geophysical method in complex strata (such as insufficient penetration of GPR in high-conductivity strata and low near-field resolution of TEM), improves the accuracy of geological anomaly body identification, and reduces the number of verification boreholes by more than 50%.

[0030] (6) The application proposes a joint inversion framework that combines physical priors and data-driven methods, which constructs an objective function containing data fitting, total variation (TV), and sparsity constraints, and embeds a physical constraint neural network (PINN) to satisfy Maxwell's equation; combined with genetic algorithm (GA) global search and L-BFGS local optimization, efficient inversion of complex geological models is realized, and the physical reasonableness of the inversion results is significantly enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the present disclosure, illustrate preferred embodiments of the present disclosure, and to explain the principles of the present disclosure.

[0032] Figure 1 Method flow chart for Example 1.

[0033] Figure 2 Integrated probe device structure diagram for Example 1. DETAILED DESCRIPTION

[0034] The present disclosure is further described below with reference to the accompanying drawings and examples.

[0035] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the present disclosure. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this present disclosure belongs.

[0036] It should be noted that the terms used herein are merely for the purpose of describing specific embodiments and are not intended to limit exemplary embodiments according to the present disclosure. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and it should be further understood that when the terms "comprise" and / or "comprising" are used in this specification, they indicate the presence of the features, steps, operations, devices, components, and / or combinations thereof.

[0037] The borehole exploration method is a method of placing a probe instrument in a borehole for exploration, which mainly includes borehole radar and borehole transient electromagnetic method; radar (GPR) is a detection technology based on high-frequency electromagnetic wave reflection, which can realize decimeter-level detection, but the detection distance is generally within 10m; transient electromagnetic method (TEM) is a low-frequency electromagnetic method, which inputs step current to the transmitting source and obtains underground electromagnetic induction signals during current shutdown by using the receiving source, and has the characteristics of being sensitive to low-resistance bodies and having large detection depth, but it has a shallow blind area problem.

[0038] The present application combines borehole radar and borehole transient electromagnetic method, proposes a borehole GPR-TEM integrated detection method, uses GPR probe module and TEM probe module, reduces the number of advanced boreholes, reduces the detection cost, and ensures full-area coverage of the roadway advanced exploration, based on the full-coverage GPR-TEM data, proposes a borehole GPR-TEM data fusion interpretation method.

[0039] Example 1

[0040] In an embodiment of the present disclosure, a borehole combined detection method is provided, which can reduce the number of advanced boreholes in a tunnel and roadway, comprising:

[0041] Step S1: Obtain the radar data and transient electromagnetic data of the measuring point depth and the target area, which are collected by the integrated detection device in the borehole;

[0042] Step S2: Feature extraction is performed on the radar data and transient electromagnetic data respectively, and the extracted features are fused based on the contribution weights of radar and transient electromagnetic to obtain a fused feature vector;

[0043] Step S3: Based on the measuring point depth and the fused feature vector, the dielectric constant and resistivity are inverted by using the trained physical information neural network;

[0044] Step S4: According to the dielectric constant and resistivity, the geological anomaly body in the target area is identified;

[0045] The integrated detection device includes a GPR probe module and a TEM probe module, the GPR probe module uses multiple sets of transmitting and receiving antennas, and the TEM probe module uses coplanar rectangular transmitting and receiving coils to realize zero magnetic flux by adjusting the transmitting and receiving distance.

[0046] As an embodiment, the drilling combined detection method for reducing the number of advanced boreholes in a tunnel and roadway can combine drilling radar and drilling transient electromagnetic methods to reduce the number of advanced boreholes and the cost of detection while ensuring full-area coverage of the roadway exploration. The specific implementation process is described below from two parts of data collection and data processing.

[0047] I. Data collection

[0048] The embodiment proposes a drilling GPR-TEM integrated detection method, which collects radar data and transient electromagnetic data for full-area coverage of the roadway exploration by the integrated detection device in the borehole.

[0049] The integrated detection device, as shown in Figure 2 , includes a GPR probe module, a TEM probe module, a control module, and an auxiliary module.

[0050] (1) GPR probe module

[0051] The GPR probe module uses two types of antennas: one is a low-frequency butterfly antenna, and the other is a high-frequency microstrip antenna. Each type of antenna is divided into two sections, the front section is the transmitting section, and the rear section is the receiving section.

[0052] The low-frequency butterfly antenna has a size of 200mm*150mm, an operating frequency of 800-150MHz, a gain of 5dBi, and a center distance of 300mm between a transmitting antenna (TX) and a receiving antenna (RX); the TX is horizontally polarized, the RX is vertically polarized, and cross-polarization isolation is further improved in power; a receiving coil is arranged in an aluminum cylindrical shielding cabin, the shielding cabin is provided with a 90° opening, and the shielding cabin is lined with an absorbing material; and the low-frequency butterfly antenna is mainly used for deep detection with a detection distance of 15m.

[0053] The high-frequency microstrip antenna adopts a rectangular microstrip patch antenna, has an operating frequency of 400±10%MHz, and has a size of 30*40mm; a substrate material of a transmitting antenna (TX) and a receiving coil (RX) is selected from high-frequency plate materials (such as Rogers RO4350B), and the substrate has a size of 50*60*1.6mm; a TX feeding mode adopts coaxial back feeding, and a RX adopts electromagnetic coupling feeding; the TX is vertically polarized, the RX is horizontally polarized, and cross-polarization isolation is further improved in power. The axial distance between the TX and the RX is set to 40cm, a metal partition plate is arranged between the two antennas, and the surface of the metal partition plate is coated with an absorbing material; and the detection distance is 10m.

[0054] (2) TEM probe module

[0055] The TEM probe module adopts a coplanar rectangular transmitting-receiving coil, and zero magnetic flux is realized by adjusting the transmitting-receiving distance, so that the influence of the primary field of the transmitting-receiving coil on the secondary field of the shallow geological body is eliminated, and the blind area range is greatly reduced.

[0056] Specifically, the TEM probe module adopts a zero-magnetic-flux coplanar transmitting-receiving coil, which is eccentrically arranged, so that the magnetic flux received by the receiving coil inside and outside the transmitting coil is mutually compensated, the mutual inductance coefficient of the transmitting-receiving coil is 0, the coverage of the primary field is eliminated, and the secondary field of the shallow geological body is collected.

[0057] The coplanar coil usually adopts a square coil, and the mutual inductance coefficient calculation formula is as follows:

[0058]

[0059] wherein, N is the number of turns of the receiving coil; N is the number of turns of the transmitting coil; is the vacuum permeability; is the path of the transmitting coil, represents the first side of the square transmitting coil; is the path of the receiving coil, represents the first side of the square receiving coil; is the microelement of the transmitting coil; is the distance between a source point Q1 on the transmitting coil and an arbitrary point Q2 on the receiving coil; and r is a micro-element of the receiving coil. By calculating the distance between the transmitting coil and the receiving coil when the mutual inductance coefficient is 0, zero magnetic flux can be achieved.

[0060] In this embodiment, the transmitting antenna (TX) and the receiving coil (RX) of the TEM probe module adopt a rectangular coil with a size of 30 mm x 200 mm, the TX wire diameter is 1 mm, the number of turns is 20 turns, the receiving coil wire diameter is 0.1 mm, and the number of turns is 200 turns; a cylindrical shield is arranged outside the coil, a 120° opening is arranged, and the material is selected from foamed nickel; and the detection distance is between 10-30 m.

[0061] (3) Control module

[0062] The control module controls the transmission and reception of the borehole GPR and TEM, has a built-in real-time calculation module, and realizes intelligent switching of low-frequency and high-frequency channels according to real-time lithology conditions.

[0063] Specifically, the internal circuit of the control module includes a transmitting circuit and a receiving circuit, an output continuous voltage adjustable power supply circuit, a bipolar pulse transmitting circuit, and a logic control circuit, etc.

[0064] As some possible implementations, the power supply circuit can support connection with an external power supply or internally set a battery power supply; the receiving circuit is connected with each receiving coil through an insulating wire, stores the collected data in the receiving control system, has an empty slot arranged therein for placing electronic elements such as a collection card, an amplifier, a data transmission unit, and an embedded computer, etc.

[0065] The transmitting circuit adopts an ARM Cortex-A processor as the main controller, integrates an FPGA (Field Programmable Gate Array), processes signals in real time, and performs time synchronization; a GPR pulse signal generator is arranged, which is based on an avalanche transistor circuit, generates a pulse with an adjustable pulse width of 0.1-5 ns and a peak voltage of 1 kV, and has a repeatable frequency of 1 kHz-1 MHz adjustable; a TEM transient electromagnetic current source is arranged, which adopts an SIC MOSFET H-bridge topology, has a maximum output current of 50 A, and supports bipolar square wave output.

[0066] The receiving circuit sets a GPR receiving channel, which adopts a 12-bit ADC, has a sampling rate of 5 GS / s, a bandwidth of 2 GHz, and an input impedance of 50 Ω; a TEM receiving channel is set, which adopts a 24-bit Σ-Δ ADC, has a sampling rate of 100 kS / s, a dynamic range of 120 dB, and an integrated programmable gain amplifier (PGA) with a gain adjustable from 1 to 1000 times.

[0067] The power supply is designed with double input, compatible with AC 220V or DC 24V, and multiple output, including: ±12V (analog circuit), 5V (digital circuit), 3.3V (FPGA), efficiency > 90%. The battery pack can use lithium iron phosphate battery pack, (48V / 20Ah), support hot plug and fast charging; after GPR pulse emission, a protection interval (50μs) is reserved to start TEM current off measurement; GPR / TEM circuit is separated and independently shielded, and power ground-signal ground-chassis ground three-level isolation is set.

[0068] (4) Auxiliary module

[0069] The auxiliary module includes a probe positioning system and an anti-stuck mechanism. The probe positioning system includes a borehole laser ranging unit and an inertial navigation unit, with a distance accuracy of 1mm and a heading angle error of <0.5°, and can transmit data back to the borehole to display the probe inclination and depth in real time. The anti-stuck mechanism includes a trigger type retractable arm based on an electromagnet, an emergency retracting device of a backup hydraulic retracting system, and a wear detection device using a shell inlaid with a wear-resistant ceramic ring and an internal vibration sensor.

[0070] The borehole laser ranging unit uses a 1550nm infrared laser emitter, and an APD avalanche photodiode is arranged at the tail end of the probe. The laser is vertically emitted from the borehole, reflected back by the tail mirror of the probe, and the distance is calculated by measuring the round trip time, i.e. the depth of the current measuring point of the probe .

[0071] The inertial navigation unit uses a three-axis MEMS gyroscope, a three-axis accelerometer, and a three-axis magnetometer. The three-axis magnetometer is used for heading angle correction; the real-time three-axis direction angle of the probe is generated and input to the control module for storage.

[0072] The trigger type retractable arm is installed at the tail end of the entire device, using a solenoid electromagnet (rated voltage 24V, suction force 200N, response time <10ms) and a titanium alloy connecting rod retractable arm (length 150mm, retracting stroke 50mm). When the contact force sensor detects a resistance >50N, the electromagnet is instantaneously powered, the retractable arm is retracted, and the probe is prevented from being stuck in front.

[0073] The emergency retracting device uses a hydraulic circuit composed of a miniature gear pump, a double-acting hydraulic cylinder, and a bladder type nitrogen energy accumulator, with a hydraulic stroke of 60mm and a retracting speed of 100mm / s, when the electromagnetic trigger type retracting arm fails.

[0074] The wear detection device adopts a wear-resistant ceramic ring, such as a zirconia toughened ceramic (ZrO2), with a thickness of 8 mm and a width of 15 mm. A MEMS accelerometer is used, and the ring thickness is reduced by 0.5 mm to trigger a warning. Time domain and frequency domain vibration analysis is also performed: the time domain RMS vibration value is greater than 5g for 1s to trigger a warning; the frequency domain characteristic frequency matches the stick-slip mode (such as a 200-400Hz resonance peak).

[0075] The process of each part in the auxiliary module working together is as follows:

[0076] 1) Normal detection:

[0077] The ceramic ring of the wear detection device rubs against the hole wall during detection, and the vibration sensor monitors the baseline vibration.

[0078] 2) Stick-slip pre-judgment:

[0079] When the vibration sensor detects a sudden increase in vibration energy or the contact force sensor detects that the contact force exceeds the limit, the retractable arm triggers an electromagnetic retraction.

[0080] 3) Emergency treatment:

[0081] When electromagnetic retraction fails, the hydraulic system of the emergency retraction device takes over within 0.5s to continue retraction.

[0082] 4) Wear maintenance:

[0083] When the wear detection device detects that the cumulative wear reaches the threshold value, it stops and prompts to replace the ceramic ring.

[0084] The GPR probe module and the TEM probe module are fixedly connected, and a motor drill disc is connected behind them. An explosion-proof stepper motor (such as 42BYGH34) is used, and the rotation speed can be programmed and controlled in the range of 0.1~10rpm. The scanning mode is selected as step scanning (GPR uses a step size of 1°, and TEM uses a step size of 15°), and the acquisition process is as follows:

[0085] 1) Push the probe into the borehole to the target depth (such as 20m);

[0086] 2) Start the motor and set the scanning mode;

[0087] 3) The motor drives the antenna to rotate to the initial angle ;

[0088] 4) If it is rotated to an angle +k·1° (k is any non-zero positive integer, k=1,2,3...), the GPR probe module transmits a low-frequency 80-150MHz signal and synchronously acquires and stores it; otherwise, it does not transmit and receive;

[0089] 5) After the low-frequency signal ends, a high-frequency 400MHz signal is transmitted, and synchronous acquisition and storage are performed;

[0090] 6) If the rotation angle is +k·15° (k is any non-zero positive integer, k = 1, 2, 3,...), the TEM probe module transmits a transient electromagnetic field, and the acquisition and storage are performed during the off period; otherwise, no transmission and reception are performed;

[0091] 7) Rotate to the next angle +1°, repeat steps 3-6;

[0092] 8) After 360° scanning, GPR and TEM data at different positions in the hole are obtained;

[0093] II. Data processing

[0094] The embodiment proposes a drilling GPR-TEM data fusion interpretation method, which fuses the characteristics of ground penetrating radar (GPR) and transient electromagnetic (TEM) through dynamic weight distribution, constructs a target function of dielectric constant-resistivity joint inversion, combines physical information neural network (PINN) embedded electromagnetic field equation constraint, and realizes global search and local fine convergence by using genetic algorithm (GA) and L-BFGS hybrid optimization strategy.

[0095] The interpretation method includes feature-level fusion and joint inversion, and realizes high-precision identification of geological abnormal bodies by combining intelligent algorithms.

[0096] (1) Feature-level fusion

[0097] The features of GPR and TEM data are extracted, specifically:

[0098] The GPR time domain signal is mapped to the depth domain through time-depth conversion, the reflection coefficient R(z) of each measurement point depth z is extracted, and the spatial derivative is calculated by using central difference:

[0099]

[0100] wherein, is the difference between the depths of adjacent detection points.

[0101] The obtained reflection coefficient R(z) and spatial derivative are taken as GPR features.

[0102] TEM is based on the late field formula to calculate the apparent resistivity, which is converted to depth domain by depth migration imaging, and the time domain change rate is calculated by using central difference:

[0103]

[0104] in, It is the time step used when calculating the time derivative of apparent resistivity (or attenuated electromagnetic field signal), that is, the interval between two adjacent sampling time points.

[0105] The obtained depth domain and the rate of change in the time domain As a TEM feature.

[0106] Stack GPR and TEM features into a multidimensional matrix:

[0107]

[0108] Where, N z This represents the number of depth points.

[0109] Based on the signal-to-noise ratio (SNR), the contribution weights of GPR features are automatically adjusted. Contribution weight of TEM features :

[0110]

[0111]

[0112]

[0113] in, Represents the logarithm to base 10. These represent the signal-to-noise ratio (SNR) of the borehole radar and the transient electromagnetic signal during drilling, respectively. The SNR is determined by the signal power. and noise power Calculations show that SNR directly determines the reliability and usability of features extracted from the data (GPR features and TEM features). The contribution weights calculated using SNR will be used in the following text. and ,and Fusion Used for subsequent inversion.

[0114] For GPR: Select the target reflected wave window (such as the reflected pulse interval after the direct wave) in the time-domain waveform, and the signal power... ,in The sampled values ​​within the signal window, The mean of the signal window. N This represents the number of sampling points within the window. Noise power is calculated using a background segment without reflection (e.g., a direct wavefront). Detrending processing is required to eliminate baseline drift, among which The noise window sample value, The noise mean. MThe number of noise window points.

[0115] For TEM: signal power is integrated over the square of the voltage of the target segment (e.g. the early high SNR segment) of the decay curve, in the early time window of the signal , ], signal power , where is the time-decaying induced voltage. Noise power is taken from the period before the transmitter current is turned off or the late signal decay to the instrument noise level , ], noise power , where, is the time-decaying induced voltage, and frequency domain filtering can suppress power-line interference.

[0116] The features are fused with contribution weights, and the measured fusion feature is expressed by the formula:

[0117]

[0118] (2) Joint inversion

[0119] The objective function of joint inversion includes data fitting term , total variation regularization term , and sparse regularization term , which is expressed by the formula:

[0120]

[0121] The final prediction model parameter m is calculated by solving the minimum value of the objective function . Wherein, is the model parameter; The dielectric constant and resistivity obtained by time-depth conversion and resistivity imaging from the data forward from the model parameter m are fused, and the processing method is consistent with , and the SNR is consistent with ; λ is the data weight, generally 1; η, γ are regularization weights; is the boundary preservation term, which performs TV regularization (total variation) to suppress noise and maintain sharp boundaries, ; The sparse regularization term is used to enhance the sparsity of the physical property mutation, ;

[0122] A physical information neural network (PINN) is used to generate an initial model population for subsequent inversion. The input is the depth z of the measurement point and the fused feature vector , and the output is the model parameter , which includes the dielectric constant and resistivity Four layers are set in the hidden layer, and the input measurement point depth z is converted into intermediate features in hidden layer 1, using the swish activation function to balance the non-linear representation ability and gradient stability, i.e.:

[0123]

[0124] wherein is the weight matrix obtained by training learning, and b1 is the bias term.

[0125] In hidden layer 2, z = hidden layer 1 output is used to further extract high-order features; in hidden layer 3, repeated processing is performed, z = hidden layer 2 output, and the target function is gradually approximated. Finally, in hidden layer 4, the high-order features are converted into physical parameters:

[0126]

[0127]

[0128] PINN requires the output result to satisfy the physical law, one of which is based on the output and , combined with Maxwell equation approximation: , is the vacuum permittivity, is the electric field vector, and is calculated by automatic differentiation technology and compared on the right side; the second is to calculate the difference between the predicted electric field divergence and the charge density: physical error = .

[0129] The loss function guides the adjustment of the model parameters. First, compare the difference between the network prediction and and the measured data, here only the data fitting term is used to calculate the data loss:

[0130]

[0131] Then the physical constraint loss is calculated, which forces the network output to satisfy the above electromagnetic field equation, and finally the total loss is calculated: total loss = data loss + 0.1·physical loss, the gradient is calculated according to the total loss, and the network weight is updated through the Adam optimizer. Through the PINN neural network, 50 preliminary prediction model parameters m=[ , ] that satisfy the physical constraints are output, replacing the random initialization of the genetic algorithm, as the initial individual population for the hybrid optimization algorithm calculation in the following.

[0132] A hybrid optimization algorithm (genetic algorithm (GA) + memory-limited BFGS quasi-Newton method (L-BFGS)) is used to realize the optimization of model parameters. The model parameters m=[ , ] into real number coded gene sequence, and 50 individuals (50 different and distributions) are generated by PINN. Global search is implemented by GA, and the objective function value is calculated for each individual, and the fitness is defined as 1 / ( +1), the greater the value, the better the individual. Parent individuals are selected in proportion to fitness (high fitness has a high probability of being selected), and the top 5 best individuals are directly reserved for the next generation. On this basis, the offspring is generated by mixing two parent individuals according to the weight (for example, parent A with high fitness accounts for 70%, and parent B with low fitness accounts for 30%). The termination conditions are set as the maximum number of iterations (50 times) and the optimal fitness does not improve significantly for more than 10 generations (the change is less than 1%), and the optimal individual is output. Then L-BFGS is used for local refinement, taking the optimal individual as the initial point m0, calculating the objective function gradient and the quasi-Hessian matrix H k , and updating the parameters:

[0133]

[0134] wherein, is the kth model parameter individual, and k is any positive integer; is the step size, which is determined by line search to ensure that the objective function decreases, and the initial learning rate is 0.1, which is attenuated to 0.5 times of the original value every 10 iterations; based on the objective function value calculated by .

[0135] The termination conditions are set as the gradient norm <1e-6, or the relative residual change <1e-4, or the number of iterations >100. And the parameters of the objective function are dynamically adjusted:

[0136]

[0137] wherein, is the measured data obtained by borehole radar, is the measured data obtained by borehole transient electromagnetic.

[0138] Embodiment 2

[0139] In an embodiment of the present disclosure, a borehole joint detection system capable of reducing the number of advance boreholes in a tunnel is provided, comprising:

[0140] An acquisition module configured to acquire radar data and transient electromagnetic data of a target area at a measurement point depth, wherein the radar data and transient electromagnetic data are collected by an integrated detection device in a borehole.

[0141] The extraction module is configured to extract features from the radar data and the transient electromagnetic data respectively, fuse the extracted features based on contribution weights of the radar and the transient electromagnetic, and obtain a fused feature vector;

[0142] The inversion module is configured to invert the dielectric constant and the resistivity by using the trained physical information neural network based on the depth of the measuring point and the fused feature vector;

[0143] The identification module is configured to identify a geological abnormal body in the target region according to the dielectric constant and the resistivity.

[0144] The integrated detection device includes a GPR probe module and a TEM probe module, the GPR probe module adopts multiple sets of transmitting and receiving antennas, and the TEM probe module adopts coplanar rectangular transmitting and receiving coils to realize zero magnetic flux by adjusting the transmitting and receiving distance.

[0145] Embodiment 3

[0146] In an embodiment of the present disclosure, a computer program product is provided, which includes a computer program, and the computer program is executed by a processor to implement the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and laneway.

[0147] Embodiment 4

[0148] In an embodiment of the present disclosure, a non-transitory computer readable storage medium is provided, which is used to store computer instructions, and the computer instructions are executed by a processor to implement the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and laneway.

[0149] Embodiment 5

[0150] In an embodiment of the present disclosure, an electronic device is provided, which includes a processor, a memory and a computer program; the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device implements the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and laneway.

[0151] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0152] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0153] Although the present disclosure has been described with reference to specific on embodiments thereof, a person of ordinary skill in the art understands that various modifications or changes can be made on the technical solutions of the present disclosure without paying creative labor, and these modifications or changes shall still fall within the protection scope of the present disclosure.

Claims

1. A borehole joint detection method capable of reducing the number of advance boreholes in a tunnel, characterized in that, The method comprises the steps of: acquiring radar data and transient electromagnetic data of all measuring points and a target area, the radar data and the transient electromagnetic data being collected by an integrated detection device in a borehole; extracting features of the radar data and the transient electromagnetic data respectively, fusing the extracted features based on contribution weights of the radar and the transient electromagnetic data, and obtaining a fused feature vector; performing joint inversion of the dielectric constant and the resistivity by using a trained physical information neural network based on the measuring point depth and the fused feature vector; identifying a geological abnormal body in the target area according to the dielectric constant and the resistivity; wherein the integrated detection device comprises a GPR probe module and a TEM probe module, the GPR probe module adopts multiple sets of transmitting and receiving antennas, and the TEM probe module adopts coplanar rectangular transmitting and receiving coils to realize zero magnetic flux by adjusting the transmitting and receiving distance; the GPR probe module adopts multiple sets of transmitting and receiving antennas, including low-frequency butterfly antennas and high-frequency microstrip antennas, for measuring surrounding rock cracks within 0-5m and abnormal body sections within 0-15m; The feature extraction is a calculation of the reflectivity R(z) of the radar data and of the spatial derivative of the reflectivity , depth domain data of transient electromagnetic data and the time domain rate of change ; The contribution weight is a contribution weight of an automatic adjustment feature based on a signal-to-noise ratio of a borehole radar and a borehole transient electromagnetic signal; a target function of joint inversion includes a data fitting term , a total variation regularization term , and a sparse regularization term , and is expressed by a formula as by solving the minimum value of the objective function The final prediction model parameter m is calculated, wherein, is the model parameter, is the dielectric constant, is the resistivity; is the measured fusion feature, which is the reflectivity R(z) of the fusion radar data and the spatial derivative of the reflectivity , the depth domain data of the transient electromagnetic data and the time domain change rate obtained; The dielectric constant and resistivity obtained by time-depth conversion and apparent resistivity imaging from the data forward from the model parameter m are fused, and the signal-to-noise ratio SNR is consistent with one of ; λ is the data weight; η, γ are the regularization weights; is the boundary preserving term, TV regularization is performed to suppress noise and keep the boundary sharp, ; The sparse regularization term is used to enhance the sparsity of the physical property mutation, .

2. The method of claim 1, wherein the number of advance boreholes for the tunneling is reduced. the zero magnetic flux is realized by calculating the transmitting and receiving distance when the mutual inductance coefficient is 0, and the formula of the mutual inductance coefficient is: wherein, is the vacuum permeability; is the transmit coil path; is the receive coil path; is the transmit coil differential; is the receive coil differential; r is the distance between a source point Ql on the transmit coil to an arbitrary point Q2 on the receive coil; is the number of turns of the receive coil; is the number of turns of the transmit coil.

3. The method of claim 1, wherein the number of advance boreholes for the tunneling is reduced. the specific process of the collection is as follows: (1) pushing the integrated detection device into the borehole to a target depth; (2) starting a motor of the integrated detection device and setting a scanning mode; (3) rotating the antenna to an initial angle driven by the motor; (4) if the GPR preset angle is rotated to, the GPR probe module transmits a low-frequency signal and synchronously collects and stores; otherwise, no transmission and reception is performed; (5) after the low-frequency signal ends, a high-frequency signal is transmitted and synchronously collected and stored; (6) if the TEM preset angle is rotated to, the TEM probe module transmits a transient electromagnetic field, and the collection and storage are performed during the off period; otherwise, no transmission and reception is performed; (7) rotating to the next angle, repeating steps (3)-(6); (8) after 360° scanning is completed, the collection process is ended.

4. The method of claim 1, wherein the number of advance boreholes for the tunneling is reduced. The physical information neural network adopts a hybrid optimization algorithm based on a genetic algorithm and L-BFGS for training and optimization, with data loss and physical loss as loss functions.

5. A borehole joint detection system capable of reducing the number of advance boreholes in a tunnel, characterized by, The method for reducing the number of advance boreholes in a tunnel and gallery, as claimed in any one of claims 1-4, comprises: an acquisition module configured to acquire radar data and transient electromagnetic data of measuring points and a target area, the radar data and the transient electromagnetic data being collected by an integrated detection device in a borehole; an extraction module configured to extract features of the radar data and the transient electromagnetic data respectively, fuse the extracted features based on contribution weights of the radar and the transient electromagnetic data, and obtain a fused feature vector; an inversion module configured to perform inversion of the dielectric constant and the resistivity by using a trained physical information neural network based on the measuring point depth and the fused feature vector; an identification module configured to identify a geological abnormal body in the target area according to the dielectric constant and the resistivity; The integrated detection device comprises a GPR probe module and a TEM probe module, the GPR probe module adopts multiple sets of transmitting and receiving antennas, and the TEM probe module adopts coplanar rectangular transmitting and receiving coils to realize zero magnetic flux by adjusting the transmitting and receiving distance.

6. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and a roadway according to any one of claims 1-4.

7. A non-transitory computer-readable storage medium, comprising: The non-transitory computer readable storage medium is used to store computer instructions, and the computer instructions are executed by the processor to realize the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and a roadway according to any one of claims 1-4.

8. An electronic device, comprising: Comprise: A processor, a memory and a computer program; wherein the processor is connected with the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the drilling combined detection method capable of reducing the number of advanced drillings in a tunnel and a roadway according to any one of claims 1-4.

Images