Intelligent detection system, method, device and medium based on robot technology

Abstract

The application relates to a wisdom detection system, method, equipment and medium based on robot technology, wherein the method comprises the following steps: an advanced detection module is used for acquiring detection data of a target robot according to a target detection element, so that the target robot performs a preset detection operation; a remote transmission module is used for acquiring environment information corresponding to the target robot according to real-time positioning information of the target robot, so as to determine a corresponding data transmission mode to transmit the detection data; a data wisdom management module is used for performing data processing and evaluation operation on the detection data, so as to obtain standard detection data, and based on a deep learning model, an adverse geological body identification result corresponding to the standard detection data is acquired. Therefore, the problems that the interpretation and evaluation process of the prior art excessively depends on professional knowledge level and engineering experience, the initial geophysical prospecting error is large, the adverse geological body is difficult to verify through drilling, and the stability of the detection element and the detection effect are greatly affected are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of advanced geological exploration, and particularly relates to a smart exploration system and method based on robot technology, equipment and a medium. BACKGROUND

[0002] With the continuous development of urbanization, underground engineering also continues to progress. Before the construction of underground engineering, exploration work is also an essential link in the region to be constructed. Scientific and reasonable exploration can effectively detect the geological conditions of the construction area, and is of great significance to ensure smooth and rapid construction and improve the personal safety of engineering construction personnel.

[0003] At present, the conventional exploration method has the following problems:

[0004] 1. The common exploration method for underground engineering is to first use different geophysical exploration methods for exploration, including but not limited to using geological radar, transient electromagnetic method, etc. After the adverse geological body is detected, drilling verification is performed. However, the geophysical exploration method often has multiple solutions, the detection accuracy decreases rapidly with the increase of the detection range (volume effect), and is greatly affected by the detection environment. For example, when using transient electromagnetic method for detection in a tunnel environment, when the transmission current is turned off, the receiving coil itself generates an induced electromotive force, forming a primary field, which is superimposed on the secondary field generated by the underground eddy current field. Therefore, it will cause distortion of the early signal of the actual transient electromagnetic survey, and form a detection blind area in the shallow detection area with low resolution. This makes the initial geophysical exploration error large, resulting in that the drilling verification does not reach the adverse geological body, and causing the "one hole" condition.

[0005] 2. The current exploration process usually first uses geophysical exploration to obtain detection data, analyzes and processes the data to obtain the position of the adverse geological body, and then performs drilling verification. The whole process is time-consuming and laborious, and the processes cannot be organically combined. In addition, the existing technology often uses the route of first geophysical exploration and then drilling verification. The geophysical exploration accuracy will affect the drilling verification, increase the error, further aggravate the "one hole" problem, and further affect the progress of underground engineering construction. Moreover, the geophysical exploration and drilling methods are often independent and cannot be organically combined and dynamically interacted. The drilling and geophysical exploration cannot be integrated, and the requirements of smart, accurate and high-level exploration for underground engineering cannot be met.

[0006] 3. The evaluation of the borehole image containing the adverse geological body obtained by the current drilling imaging and the interpretation and evaluation of the conventional geophysical signal data are often performed manually. This makes the interpretation and evaluation process excessively dependent on professional knowledge and engineering experience, and the error is large. Manual interpretation and evaluation require a lot of time and effort, which prolongs the exploration time and further aggravates the impact on the progress of underground engineering construction. The exploration process is highly subjective and cannot be intelligent.

[0007] 4. With the continuous development of advanced geological exploration and forecasting technology, the technology of geophysical exploration in boreholes is constantly improving. However, when using these new geophysical exploration technologies, it is often necessary to manually use advanced horizontal directional drilling to carry out in-hole exploration with detection elements. However, when there are small falling rocks, dust, or water vapor in the borehole, it will greatly affect the stability of the detection elements and the detection effect, thereby affecting the detection accuracy.

[0008] In summary, the existing technology interpretation and evaluation process relies excessively on professional knowledge and engineering experience, resulting in large errors in the initial geophysical exploration. This makes it difficult to verify unfavorable geological bodies during drilling, greatly affecting the stability of detection elements and the detection effect. Consequently, it fails to meet the requirements for intelligent, accurate, and high-level exploration in underground engineering, and urgently needs to be addressed. Summary of the Invention

[0009] This application provides a smart detection system, method, device, and medium based on robotics technology to address the problems of existing technologies' interpretation and evaluation processes relying excessively on professional knowledge and engineering experience, resulting in large errors in the initial geophysical exploration, making it difficult to verify unfavorable geological bodies during drilling, and greatly affecting the stability of detection elements and detection results.

[0010] The first aspect of this application provides a smart detection system based on robotics technology, comprising: an advanced detection module for acquiring detection data and real-time positioning information of a target robot, and controlling the target robot to perform preset detection and posture correction operations based on the detection data; a remote transmission module for acquiring environmental information corresponding to the target robot based on the real-time positioning information of the target robot, and determining a corresponding data transmission method through the environmental information to transmit the detection data using the data transmission method; and a data intelligent management module for performing data processing and evaluation operations on the detection data to obtain standard detection data, and inputting the standard detection data into a pre-trained smart detection model to output the identification result of the adverse geological body corresponding to the standard detection data.

[0011] Optionally, in an embodiment of the present application, the advanced detection module comprises: a detection robot subsystem; an optional unit configured to select the target detection element based on a preset underground engineering detection requirement, wherein the target detection element comprises at least one of a borehole television, a borehole radar, and a borehole transient electromagnetic method; a detection task management unit configured to determine a detection task of the target robot according to the preset underground engineering detection requirement, generate a detection instruction of the detection task, and send the detection instruction to the target robot to control the target robot to perform a corresponding detection action according to the detection instruction; and an emergency processing unit configured to acquire environment information of a current borehole of the target robot, determine whether a preset emergency event exists in the current borehole based on the environment information, and control the target robot to perform a preset emergency event processing operation if the preset emergency event exists in the current borehole.

[0012] Optionally, in an embodiment of the present application, the detection robot subsystem comprises: a positioning unit configured to determine a positioning strategy of the target robot according to the environment information to acquire real-time positioning information of the target robot through the positioning strategy; a collision avoidance unit configured to set a target shock-absorbing material at a corresponding position of the target robot, measure a distance between the target robot and a borehole wall of a current borehole of the target robot according to a preset laser ranging sensor, compare the distance with a preset collision distance threshold, and control the target robot to perform a collision avoidance operation through the target shock-absorbing material and a preset collision avoidance strategy if the distance is less than the preset collision distance threshold; a detection posture correction unit configured to dynamically adjust a preset telescopic rod type component and a rotary support to control the target robot to perform a multi-directional detection and / or a point detection operation; and a first storage unit configured to store detection data of the target robot and backup the detection data using a preset cloud storage strategy.

[0013] Optionally, in an embodiment of the present application, the data wisdom management module comprises: a second storage unit; a signal processing unit configured to amplify a detection signal corresponding to the detection data to generate a detection amplified signal, decompose the detection amplified signal into a plurality of intrinsic mode function components using a preset empirical mode decomposition strategy, calculate a multi-scale sample entropy value of each intrinsic mode function component of the plurality of intrinsic mode function components, calculate a signal processing threshold interval based on the multi-scale sample entropy value and a preset second-order difference strategy, and generate a target detection signal meeting a preset signal-to-noise ratio requirement according to the signal processing threshold interval and a preset soft threshold function; a data evaluation unit configured to determine whether the target detection signal is a single signal source signal, perform transient electromagnetic signal inversion imaging or radar signal inversion imaging operation on the single signal source signal if the target detection signal is the single signal source signal, convert the target detection signal into a reflection coefficient sequence if the target detection signal is a multi-signal source signal, perform time-depth conversion on the reflection coefficient sequence, and perform resampling and decomposition reconstruction on the time-depth converted result to obtain a target reflection coefficient sequence, obtain a feature image corresponding to the target reflection coefficient sequence, and perform principal component transformation processing on the feature image to obtain a multi-source data fusion image; and an image recognition unit configured to extract an adverse hole wall feature corresponding to the detection data and an adverse geological body feature corresponding to the multi-source data fusion image based on a pre-trained fast regional convolution model, and identify and label the types of the adverse hole wall feature and the adverse geological body feature.

[0014] The second aspect embodiment of the present application provides a wisdom detection method based on robot technology, comprising the following steps: obtaining detection data and real-time positioning information of a target robot, and controlling the target robot to perform a preset detection and posture correction operation based on the detection data; obtaining environment information corresponding to the target robot according to the real-time positioning information of the target robot, determining a corresponding data transmission mode through the environment information, and transmitting the detection data using the data transmission mode; performing data processing and evaluation operations on the detection data to obtain standard detection data, and inputting the standard detection data into a pre-trained wisdom detection model to output an adverse geological body identification result corresponding to the standard detection data.

[0015] Optionally, in an embodiment of the present application, the real-time positioning and posture correction of the target robot, and based on the detection data, controlling the target robot to perform a preset detection operation, comprises: determining the positioning strategy of the target robot according to the environmental information, so as to obtain the real-time positioning information of the target robot through the positioning strategy, and based on the real-time positioning information, dynamically adjusting the preset telescopic rod type member and the rotating support, and controlling the target robot to perform multi-directional detection and / or point detection operation; setting a target shock-absorbing material at the corresponding position of the target robot, and simultaneously measuring the distance between the target robot and the hole wall of the current detection hole of the target robot according to the preset laser ranging sensor, and comparing the distance with the preset collision distance threshold, and in the case that the distance is less than the preset collision distance threshold, controlling the target robot to perform anti-collision operation through the target shock-absorbing material and the preset anti-collision strategy.

[0016] Optionally, in an embodiment of the present application, the data processing and evaluation operation of the detection data to obtain standard detection data, comprises: amplifying the detection signal corresponding to the detection data to generate a detection amplified signal, and decomposing the detection amplified signal to obtain a plurality of intrinsic mode function components by using a preset empirical mode decomposition strategy, and calculating the multi-scale sample entropy value of each intrinsic mode function component in the plurality of intrinsic mode function components, so as to calculate the signal processing threshold interval based on the multi-scale sample entropy value and a preset second-order difference strategy, and generate a target detection signal meeting the preset signal-to-noise ratio requirement according to the signal processing threshold interval and a preset soft threshold function; judging whether the target detection signal is a single signal source signal, if the target detection signal is the single signal source signal, performing transient electromagnetic signal inversion imaging or radar signal inversion imaging operation on the single signal source signal, if the target detection signal is a multi-signal source signal, converting the target detection signal into a reflection coefficient sequence, and performing time-depth conversion on the reflection coefficient sequence, and resampling and decomposing and reconstructing the result after time-depth conversion to obtain a target reflection coefficient sequence, and obtaining a feature image corresponding to the target reflection coefficient sequence, and performing principal component transformation processing on the feature image to obtain a multi-source data fusion image.

[0017] Optionally, in an embodiment of the present application, the input of the standard detection data into a pre-trained intelligent detection model to output the adverse geological body identification result corresponding to the standard detection data, comprises: based on a pre-trained fast regional convolution model, extracting adverse hole wall features corresponding to the detection data and adverse geological body features corresponding to the multi-source data fusion image, and identifying and labeling the types of the adverse hole wall features and the adverse geological body features.

[0018] The third aspect of the embodiments of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the intelligent detection method based on robot technology as described in the above embodiments.

[0019] The fourth aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the intelligent detection method based on robot technology as described above.

[0020] Therefore, the embodiments of the present application have the following beneficial effects:

[0021] The embodiments of the present application can include an advanced detection module for obtaining detection data and real-time positioning information of a target robot, and based on the detection data, controlling the target robot to perform a preset detection and posture correction operation; a remote transmission module for obtaining environment information corresponding to the target robot according to the real-time positioning information of the target robot, and determining a corresponding data transmission mode through the environment information, so as to transmit the detection data by using the data transmission mode; a data intelligent management module for performing data processing and evaluation operations on the detection data to obtain standard detection data, and inputting the standard detection data into a pre-trained intelligent detection model to output an adverse geological body identification result corresponding to the standard detection data. The present application combines the robot platform with drilling and geophysical prospecting, and can realize dynamic interaction of each process of detection data-transmission data-processing data-evaluation data, effectively improving the efficiency and accuracy of underground engineering advanced prediction detection. Thus, the problems of excessive dependence on professional knowledge level and engineering experience in the interpretation and evaluation process of the prior art, large error in initial geophysical prospecting, difficulty in verifying adverse geological bodies through drilling, and great influence on the stability and detection effect of the detection element are solved.

[0022] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0024] Figure 1 FIG. 1 is an example diagram of an intelligent detection system based on robot technology according to an embodiment of the present application;

[0025] Figure 2 FIG. 2 is a schematic diagram of a logic architecture of an intelligent detection system based on robot technology according to an embodiment of the present application;

[0026] Figure 3A drilling and geophysical prospecting integrated intelligent exploration robot structure schematic diagram is provided for an embodiment of the present application.

[0027] Figure 4 An execution logic schematic diagram of an intelligent exploration system based on robot technology is provided for an embodiment of the present application.

[0028] Figure 5 A flow chart of an intelligent exploration method based on robot technology is provided for an embodiment according to the present application.

[0029] Figure 6 A structure schematic diagram of an electronic device is provided for an embodiment of the present application.

[0030] Among them, 10-intelligent exploration system based on robot technology; 100-advanced exploration module, 200-remote transmission module, 300-data intelligent management module; 11-robot body, 111-mechanical leg, 112-laser ranging sensor, 114-wireless remote control lamp, 115-first rotary joint, 116-first connecting rod, 117-second rotary joint, 118-first telescopic rod, 119-fixed support, 120-GPS positioning system, 13-central control computer, 141-option unit, 1411-exploration element, 1412-protection shell, 142-emergency treatment unit, 1421-sprinkler, 143-first storage unit, 15-exploration posture correction unit, 151-robot posture correction subunit, 1511-second telescopic rod, 1512-second connecting rod, 1513-third rotary joint, 1514-third connecting rod, 1515-gimbal joint, 1516-third telescopic rod, 1517-metal rubber track, 152-exploration element posture correction subunit, 1521-fourth telescopic rod, 1522-rotary support, 1523-slideway; 601-memory, 602-processor, 603-communication interface. DETAILED DESCRIPTION

[0031] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0032] A robot technology-based intelligent detection system, method, device and medium are described below with reference to the accompanying drawings. To address the problems mentioned in the background, the present application provides a robot technology-based intelligent detection system. The system includes an advanced detection module for obtaining detection data and real-time positioning information of a target robot and controlling the target robot to perform preset detection and posture correction operations based on the detection data; a remote transmission module for obtaining environment information corresponding to the target robot according to the real-time positioning information of the target robot and determining a corresponding data transmission mode through the environment information to transmit the detection data using the data transmission mode; and a data intelligent management module for performing data processing and evaluation operations on the detection data to obtain standard detection data and inputting the standard detection data into a pre-trained intelligent detection model to output an adverse geological body identification result corresponding to the standard detection data. The present application combines a robot platform with drilling and geophysical prospecting to achieve dynamic interaction of detection data-transmission data-processing data-evaluation data processes, effectively improving the efficiency and accuracy of underground engineering advanced prediction and detection. Thus, the problems of excessive dependence on professional knowledge and engineering experience in the interpretation and evaluation process, large errors in initial geophysical prospecting, difficulty in verifying adverse geological bodies through drilling, and great impact on the stability of detection elements and detection results are solved.

[0033] Specifically, Figure 1 FIG. 1 is a block schematic diagram of a robot technology-based intelligent detection system according to an embodiment of the present application.

[0034] As Figure 1 shown, the robot technology-based intelligent detection system 10 includes an advanced detection module 100, a remote transmission module 200, and a data intelligent management module 300.

[0035] The advanced detection module 100 is configured to obtain detection data and real-time positioning information of a target robot and control the target robot to perform preset detection and posture correction operations based on the detection data.

[0036] The embodiment of the present application can select appropriate detection elements for advanced detection through the advanced detection module, obtain detection data (including signal data and image data, etc.) of a target robot (i.e., a detection robot), and control the detection robot to travel according to the detection data. In addition, the embodiment of the present application can also perform real-time positioning and detection posture correction on the target robot through the advanced detection module and control the detection robot to perform emergency handling operations such as anti-collision in emergency situations, thereby effectively ensuring the reliability and intelligent level of the detection robot.

[0037] Optionally, in an embodiment of the present application, the advanced detection module 100 includes a detection robot subsystem, an optional unit, a detection task management unit, and an emergency handling unit.

[0038] The detection robot subsystem detects the target geological body.

[0039] An optional unit is configured to select a target detection element based on a preset underground engineering detection requirement, wherein the target detection element comprises at least one of a borehole television, a borehole radar and a borehole transient electromagnetic method.

[0040] A detection task management unit is configured to determine a detection task of a target robot according to the preset underground engineering detection requirement, generate a detection instruction of the detection task, and send the detection instruction to the target robot to control the target robot to perform a corresponding detection action according to the detection instruction.

[0041] An emergency processing unit is configured to acquire environment information of a current borehole of the target robot, determine whether a preset emergency event exists in the current borehole based on the environment information, and control the target robot to perform a preset emergency event processing operation if the preset emergency event exists in the current borehole.

[0042] It should be noted that the advanced detection module 100 in the embodiment of the present application mainly comprises a detection robot subsystem, an optional unit 141, a detection task management unit and an emergency processing unit 142, as shown in FIG. 1. Figure 2

[0043] Specifically, the embodiment of the present application can first select different detection elements 1411 such as one or more of a borehole television, a borehole radar and a borehole transient electromagnetic method according to the advanced detection of the adverse geological body or the underground engineering detection requirement through the optional unit.

[0044] It should be noted that in the current geophysical exploration means, the transient electromagnetic method is often used to detect the distribution of underground water in front, and has high identification accuracy for water-containing bodies. The radar method is often used to detect faults, fractures, karst caves and other adverse geological bodies in front, and has high identification accuracy for such adverse geological bodies. The borehole television is often used to directly reflect the detection of adverse geological bodies in a hole and its local range, but has the disadvantage of "one hole view". Therefore, the embodiment of the present application can select at least one detection method or detection element according to the actual engineering requirement to perform advanced geological comprehensive exploration, thereby effectively improving the detection accuracy.

[0045] Secondly, in the embodiment of the present application, relevant personnel can input a detection task according to the actual underground engineering detection requirement by using the detection task management unit, and transmit the detection instruction to the robot device (i.e. the detection robot). The detection task management unit can also be used to send a re-detection instruction for a measured borehole;

[0046] ​Afterwards, when an emergency situation occurs in the hole, such as the presence of small falling rocks, dust, water vapor and other conditions that may affect the progress of the detection robot or the detection accuracy, the robot device can be controlled by the emergency processing unit 142 to handle the emergency situation in a timely manner, thereby improving the environmental adaptability and detection accuracy of the robot device. The specific emergency handling measures are as follows:

[0047] 1. When there are small falling rocks, the laser ranging sensor 112 carried by the detection robot can measure the height of the robot device and the top and bottom of the falling rocks, and cooperate with the inclination sensor data to obtain the height of the falling rocks. By dynamically adjusting the parts of the detection posture correction unit 15, stable crossing of the falling rocks can be achieved, and the detection elements are prevented from hitting the falling rocks, thereby affecting the detection effect.

[0048] 2. When there is dust, water vapor, etc., the embodiment of the present application can spray pure water through the spray head 1421 carried, use the built-in resistance heating element, and use resistance materials (such as resistance coils or resistance sheets, etc.) to generate heat energy through current to evaporate the water vapor and screen residual pure water, thereby further improving the environmental adaptability of the detection device.

[0049] Optionally, in an embodiment of the present application, the detection robot subsystem includes a positioning unit, a collision avoidance unit, a detection posture correction unit, and a first storage unit.

[0050] The positioning unit is configured to determine a positioning strategy of the target robot according to environmental information, so as to obtain real-time positioning information of the target robot through the positioning strategy.

[0051] The collision avoidance unit is configured to set a target shock-absorbing material at a corresponding position of the target robot, and simultaneously measure the distance between the target robot and the hole wall of the current exploration hole of the target robot according to a preset laser ranging sensor, compare the distance with a preset collision distance threshold, and in the case that the distance is less than the preset collision distance threshold, control the target robot to perform a collision avoidance operation through the target shock-absorbing material and a preset collision avoidance strategy.

[0052] The detection posture correction unit is configured to dynamically adjust the preset telescopic rod component and the rotating support to control the target robot to perform multi-directional detection and / or point detection operation.

[0053] The first storage unit is configured to store detection data of the target robot, and backup the detection data by using a preset cloud storage strategy.

[0054] As an implementable way, the robot subsystem in the embodiment of the present application includes a positioning unit (i.e. a GPS positioning system 120), a collision avoidance unit, a detection posture correction unit 15, and a first storage unit.

[0055] It should be noted that the embodiment of the present application can perform the positioning work of the detection robot through the positioning unit, for example, the embodiment of the present application can realize the positioning function of the detection robot by using the GPS (Global Positioning System), when the GPS signal of the tunnel and other underground projects is weak, the positioning function cannot be accurately realized by the GPS, the GPS signal amplifier device can be carried, and the auxiliary positioning is performed by cooperating with the inertial positioning auxiliary system, so that the positioning function in the complex environment such as the tunnel is realized.

[0056] In addition, the anti-collision unit of the embodiment of the present application can avoid the collision of the detection robot in the borehole with the hole wall, specifically, the embodiment of the present application can detect the distance between the detection robot device and the hole wall by carrying the laser ranging sensor 112, when the detected distance is less than a certain set value, the anti-collision function of the robot device is realized by the detection posture correction unit, and the anti-collision unit further comprises a damping material, and the damping material is applied to each corner point of the detection robot and the detection element fixing frame, so as to further improve the stability of the robot device.

[0057] In the embodiment of the present application, the detection posture correction unit comprises a robot posture correction sub-unit 151 and a detection element posture correction sub-unit 152. Wherein, the robot posture correction sub-unit 151 can detect the robot when traveling in the borehole, improve the stability of the robot device when traveling by dynamically adjusting the telescopic rod and other components, so as to reduce the distortion of the detection signal or image of the detection element caused by the shaking of the robot device; the detection element posture correction sub-unit 152 can realize the detection of different directions in the hole by adjusting the rotating support 1522 and other components, and can cooperate with the robot posture correction sub-unit 151 to realize the fixed-point detection. Therefore, the detection posture correction unit 15 in the embodiment of the present application has the functions of fixed-point detection and multi-directional detection, and is suitable for complex borehole environment.

[0058] In addition, the first storage unit in the embodiment of the present application can carry a storage card to store the detection element signal data and image, and cooperate with the cloud storage technology to back up, the stored detection element signal data and image can be transmitted to the data intelligent management module in real time through the remote transmission module, for subsequent data analysis.

[0059] The remote transmission module 200 is configured to acquire environment information corresponding to the target robot according to real-time positioning information of the target robot, and determine a corresponding data transmission mode according to the environment information, so as to transmit detection data by using the data transmission mode.

[0060] In actual implementation, the remote transmission module in the embodiment of the application is composed of the detection robot device, the 5G module carried by the control room and the base station. The remote transmission module can adopt wireless transmission technology. When the underground engineering is a complex environment such as a tunnel, the 5G signal is poor, and the wired transmission technology can be used to ensure that the detection signal data and images of the detection robot device can be transmitted to the data management module in real time and accurately, and signal loss is avoided.

[0061] Therefore, the embodiment of the application can realize the dynamic interaction between the robot device and the advanced detection module and the data intelligent management module through the remote transmission module, so as to transmit the signal data and images detected by the robot device to the advanced detection module and the data intelligent management module in real time.

[0062] The data intelligent management module 300 is configured to perform data processing and evaluation on the detection data to obtain standard detection data, and input the standard detection data into a pre-trained intelligent detection model to output an adverse geological body identification result corresponding to the standard detection data.

[0063] Further, the embodiment of the application can also process and evaluate the signal data transmitted by the advanced detection module through the data intelligent management module, and intelligently identify the images containing the adverse geological body through the deep learning method, so as to realize intelligent exploration.

[0064] Optionally, in an embodiment of the application, the data intelligent management module 300 includes a second storage unit, a signal processing unit, a data evaluation unit and an image recognition unit.

[0065] The second storage unit is configured to store the detection data.

[0066] The signal processing unit is configured to amplify the detection signal corresponding to the detection data to generate a detection amplified signal, decompose the detection amplified signal to obtain a plurality of intrinsic mode function components by using a preset empirical mode decomposition strategy, calculate a multi-scale sample entropy value of each intrinsic mode function component in the plurality of intrinsic mode function components, calculate a signal processing threshold interval based on the multi-scale sample entropy value and a preset second-order difference strategy, and generate a target detection signal meeting a preset signal-to-noise ratio requirement according to the signal processing threshold interval and a preset soft threshold function.

[0067] The data evaluation unit is configured to determine whether the target detection signal is a single signal source signal, perform transient electromagnetic signal inversion imaging or radar signal inversion imaging on the single signal source signal if the target detection signal is a single signal source signal, convert the target detection signal into a reflection coefficient sequence if the target detection signal is a multi-signal source signal, perform time-depth conversion on the reflection coefficient sequence, and perform resampling and decomposition reconstruction on the time-depth converted result to obtain a target reflection coefficient sequence, and obtain a characteristic image corresponding to the target reflection coefficient sequence, and perform principal component transformation on the characteristic image to obtain a multi-source data fusion image.

[0068] The image recognition unit is configured to extract an adverse hole wall feature corresponding to the detection data and an adverse geological body feature corresponding to the multi-source data fusion image based on a pre-trained fast regional convolution model, and identify and label the types of the adverse hole wall feature and the adverse geological body feature.

[0069] It should be noted that the data wisdom management module in the embodiments of the present application mainly includes a second storage unit, a signal processing unit, a data evaluation unit and an image recognition unit.

[0070] The second storage unit can be used to store and view detection signal data and borehole television images transmitted by the detection robot.

[0071] The signal processing unit can perform signal amplification and signal noise reduction on the detection signal data transmitted by the second storage unit, effectively improving the signal-to-noise ratio. The specific signal processing steps are as follows:

[0072] 1. The signal amplification device amplifies the transmitted detection signal, and decomposes the amplified electromagnetic wave and radar signal by the empirical mode decomposition method. Compared with other time-frequency analysis methods, the empirical mode decomposition method has the characteristics of adaptive filtering and denoising, and is very suitable for processing non-stationary signals.

[0073] 2. Calculate the multi-scale sample entropy value of each order intrinsic mode function component. After the second-order difference calculation is completed, the maximum value and the minimum value are obtained, which are set as the threshold value. The signals in the threshold value interval (i.e. the signal processing threshold value interval) are further processed by the soft threshold function. The signals greater than the maximum value are filtered and removed, and the signals less than the minimum value are retained, thereby obtaining the processed high signal-to-noise ratio electromagnetic wave and radar signal.

[0074] Further, the data evaluation unit in the embodiments of the present application can perform data interpretation on the probe signal data transmitted by the signal processing unit, so as to convert the probe signal data into a geological image containing an adverse geological body, and select a suitable probe element 1411 according to actual requirements. When a single probe element is used according to actual requirements, the embodiments of the present application can use a single data interpretation technology to perform signal interpretation; when multiple probe elements 1411 are used for probing according to actual requirements, the embodiments of the present application can use a data fusion technology to perform fusion imaging on multi-source probe data, so as to further improve the probing accuracy.

[0075] Specifically, the data evaluation unit in the embodiments of the present application performs the following steps in the data evaluation operation:

[0076] 1. When the probe signal data transmitted by the signal processing unit is single signal source, the embodiments of the present application can use Res2DInv to perform transient electromagnetic signal inversion imaging or use Reflexw to perform radar signal inversion imaging.

[0077] 2. When the probe signal data transmitted by the signal processing unit is multi-source signal, the embodiments of the present application can convert the transient electromagnetic signal data and the radar signal data into a reflection coefficient sequence by using a reflection coefficient-based fusion imaging method, and after time-depth conversion, uniformly process the data in the spatial domain.

[0078] 3. Resample the data after time-depth conversion, and perform decomposition and reconstruction to obtain the processed reflection coefficient sequence.

[0079] 3. Perform forward imaging on the processed reflection coefficient sequence, and perform multi-layer decomposition to obtain a characteristic image.

[0080] 4. Perform principal component transformation on the obtained characteristic image, so as to obtain a multi-source data fusion image containing an adverse geological body, and transmit the image to the image recognition unit.

[0081] Then, the embodiments of the present application can use the image recognition unit to intelligently recognize and accurately locate the geological image containing the adverse geological body obtained by the data evaluation unit by using a deep learning algorithm, and compare the data with the built database, mark the type of the adverse geological body, effectively reduce the error caused by the judgment factor, and further improve the exploration accuracy and efficiency.

[0082] Specifically, the embodiments of the present application perform the following steps for image recognition:

[0083] 1. Use the fast regional convolutional neural network on the borehole television image transmitted by the second storage unit to extract adverse features such as cracks and faults in the hole wall, and compare the features with the established data set to obtain the specific adverse geological body type and mark.

[0084] 2. The image with the bad geological body transmitted by the data evaluation unit is extracted by a fast regional convolutional neural network to extract the bad geological body features such as a cave, a fault and a goaf.

[0085] 3. The specific bad geological body type is obtained by comparison with the established data set and is marked, intelligent recognition and intelligent positioning functions of the image are achieved, and the exploration data processing efficiency is effectively improved.

[0086] Further, based on the intelligent detection system of the robot technology, the application can also construct an integrated intelligent detection robot of drilling and geophysical prospecting.

[0087] Figure 3 It is a structural schematic view of the integrated intelligent detection robot of drilling and geophysical prospecting of the application. As shown in the figure, Figure 3 The integrated intelligent detection robot of drilling and geophysical prospecting mainly includes a robot body 11, a central control computer 13, an advanced detection module 100, a detection posture correction unit 15 and the like.

[0088] Specifically, the robot body 11 is a robot that can carry detection elements and is suitable for advanced exploration in a borehole. Mechanical legs 111 are installed on both sides of the robot body 11, and metal rubber tracks 1517 are installed at the bottom of the mechanical legs 111. The metal rubber tracks 1517 combine the advantages of metal chain links and rubber blocks, thereby improving the wear resistance and shock absorption performance of the tracks, and enabling good detection operation in a complex environment in the borehole and improving the stability during marching and detection.

[0089] Laser ranging sensors 112 are installed on the front and rear of the robot body 11. The laser ranging sensors 112 are used to detect the distance between the robot body 11 and the hole wall. When the measured distance is less than a certain set value, the detection posture correction unit 15 is rotated through the universal joint 1515, so that the detection robot device always marches forward along the center of the two side hole walls, thereby effectively avoiding collision with the hole wall and improving the detection stability of the detection element 1411.

[0090] The robot body 11 is equipped with a remote transmission module 200. When wireless transmission technology is used, the detection signal data and images are transmitted through the 5G module carried by the detection robot body 11. When the underground engineering is a complex environment such as a tunnel, the 5G signal is poor, and wired transmission technology can be used to ensure that the detection signal data and images of the detection robot device can be transmitted to the data management terminal in the control room in real time and accurately, avoiding signal loss.

[0091] The wireless remote control lamp 114 is mounted above the robot body 11, and the illumination direction and brightness can be conveniently adjusted to meet the imaging requirements in the borehole. The wireless remote control lamp 114 is connected with the robot body 11 through a first rotary joint 115, a first connecting rod 116, a second rotary joint 117, a first telescopic rod 118 and a fixed support 119. The first rotary joint 115 is used for vertical rotation of the wireless remote control lamp 114, the second rotary joint 117 is used for horizontal rotation of the wireless remote control lamp 114, and the first telescopic rod 118 is used for up-down movement of the wireless remote control lamp 114. When the detection robot device is imaging in the borehole, if unfavorable geological phenomena such as cracks and faults in the borehole are encountered, the first rotary joint 115, the second rotary joint 117 and the first telescopic rod 118 are rotated and telescoped, the brightness is changed, the spot illumination function is achieved, the imaging clarity of the borehole is improved, and subsequent image recognition and analysis are facilitated.

[0092] The robot body 11 is provided with a GPS positioning system 120 to realize the positioning function of the detection robot. When the GPS signal of the tunnel and other underground works is weak, the positioning function cannot be accurately realized through the GPS. Therefore, a GPS signal amplifier device can be mounted, and the inertial positioning auxiliary system is used for auxiliary positioning, so that the positioning function in the complex environment such as a tunnel is realized.

[0093] The central control computer 13 can receive the detection task input by the artificial according to the actual underground engineering detection requirements and transmitted by the control room detection task management unit. The detection robot device participates in the detection signal data and image process through the detection element 1411, and specifically includes the operation of the detection element 1411, the reception and storage of the detection signal, and the like. The detection robot device participates in the correction of the detection posture when the device is running, and adjusts each component according to the complex actual borehole environment, so as to adjust the running and specific detection posture of the detection point, and improve the applicability of the device.

[0094] The advanced detection module 100 includes an optional unit 141, an emergency processing unit 142 and a data storage unit 143. The optional unit 141 includes different detection elements 1411 and protective shells 1412 for placing the detection elements outside, which are selected according to the situation of the advanced detection of unfavorable geological bodies. The detection elements 1411 specifically include a borehole television, a borehole radar and a borehole transient electromagnetic wave, and one or more detection methods are selected according to the actual engineering situation.

[0095] The emergency processing unit 142 is used to realize the timely processing of the sudden situation by the robot device when a sudden situation occurs in the hole, including but not limited to the situation that there are small falling rocks, dust, water vapor and the like in the hole which will affect the progress or detection accuracy of the detection robot. The emergency processing unit 142 can control the robot device to timely process the sudden situation, thereby improving the environmental adaptability and detection accuracy of the robot device, specifically including: when encountering dust and water vapor affecting the exploration accuracy of the detection element 1411, the pure water can be sprayed through the spray head 1421 carried, the built-in resistance heating element is used, the resistance material is used, including but not limited to the use of resistance coil or resistance sheet, the heat energy is generated by the current through the power supply, so that the water vapor and the screen residual pure water are evaporated, and the environmental adaptability of the detection device is further improved.

[0096] The data storage unit 143 includes a storage card carried for storing detection element signal data and images, and cooperates with a cloud storage technology for backup. The stored detection element signal data and images can be transmitted to the control room data intelligent management module 300 in real time through the remote transmission module 200 for subsequent analysis.

[0097] The detection posture correction unit 15 includes a robot posture correction sub-unit 151 and a detection element posture correction sub-unit 152. The robot posture correction sub-unit 151 is used to adaptively adjust each component of the robot when the detection robot device is running and detecting a specific measurement point, so as to achieve the dynamic stability of the whole device. The detection element posture correction sub-unit 152 adjusts each component of the robot to achieve the detection dynamic stability of the detection element. The robot posture correction sub-unit 151 and the detection element posture correction sub-unit 152 cooperate with each other, effectively improve the detection stability of the detection robot device, can meet the detection demand under the complex condition in the hole, and effectively guarantee the detection signal data accuracy of the detection element 1411.

[0098] The robot posture correction subunit 151 comprises a second telescopic rod 1511, a second connecting rod 1512, a third rotary joint 1513, a third connecting rod 1514, a universal joint 1515, a third telescopic rod 1516, a metal rubber track 1517, one end of the second telescopic rod 1511 is fixedly connected with the robot body 11, the other end is fixedly connected with the second connecting rod 1512, the second connecting rod 1512 is fixedly connected with the third connecting rod 1514 through the third rotary joint 1513, the third connecting rod 1514 is fixedly connected with the third telescopic rod 1516 through the universal joint 1515, and the third telescopic rod 1516 is fixedly connected with the metal rubber track 1517, the second telescopic rod 1511 is adjusted through telescopic, the third rotary joint 1513 is adjusted through rotation, the universal joint 1515 is adjusted through rotation, and the third telescopic rod 1516 is adjusted through telescopic, so as to adjust the position of the mechanical leg 111, realize the inside-outside contraction function of the mechanical leg 111, realize the height change of the robot device, and effectively adapt to the complex environment with uneven height in the hole, and further improve the detection stability by reducing the overall gravity center during detection, and ensure the detection precision.

[0099] The detection element posture correction subunit 152 comprises a fourth telescopic rod 1521, a rotary support 1522 and a slide rail 1523, the fourth telescopic rod 1521 is located below the robot body 11, one end is fixedly connected with the robot body 11, the other end is connected with the rotary support 1522, the rotary support 1522 is fixedly connected with the slide rail 1523 below, and is connected with the optional unit 141 through a sliding block, the fourth telescopic rod 1521 realizes the up-down movement of the detection element 1411, the slide rail 1523 is used for realizing the left-right and front-back movement of the detection element 1411 on the horizontal plane, and the rotary support 1522 is used for realizing the rotation of the detection element 1411, through the dynamic adjustment of the fourth telescopic rod 1521, the rotary support 1522 and the slide rail 1523, the detection posture stability of the detection element 1411 is further improved.

[0100] In summary, the robot platform is combined with drilling and geophysical prospecting in one aspect of the present application, which can effectively solve the limitations of other geophysical methods in complex drilling environments. The robot is used to carry detection elements such as transient electromagnetic receiving probes, borehole radars, and imagers, which have less external interference, greater detection depth, and high resolution, effectively improving the laying efficiency and reducing the impact on the progress of underground engineering construction. For example, when the robot carries a transient electromagnetic receiving probe, it can not only realize the separation of transmission and reception to observe stronger response signals, but also effectively reduce the interference of various other signals. On the other hand, the present application combines geophysical prospecting and drilling organically to realize drilling and geophysical prospecting simultaneously, effectively improving the accuracy of geophysical prospecting and avoiding the problem of "one hole" caused by geophysical prospecting before drilling verification. At the same time, the present application intelligently acquires signals and images of detection elements, transmits data, processes data, and identifies images, realizes dynamic interaction of detection data-transmission data-processing data-evaluation data, effectively improves detection accuracy, avoids human error, and further improves exploration efficiency, which has the advantages of high efficiency, high precision, high applicability, and high intelligence level.

[0101] The execution logic of the intelligent detection system based on robot technology of the present application is described below in conjunction with the accompanying drawings.

[0102] Figure 4 The execution logic of the intelligent detection system based on robot technology is shown in the figure. As shown in the figure, the execution process of the intelligent detection system based on robot technology is as follows: Figure 4

[0103] S401: According to the actual underground engineering detection requirements, the selected detection elements are determined, and the detection task is input to the detection task management unit by the explorer in the control room, including measurement points, measurement lines, etc. The detection task management unit sends a detection command to the detection robot;

[0104] S402: The detection robot carrying the detection element starts running according to the detection command sent by the detection task management unit. In the process of the detection robot running, the laser ranging sensor carried by the detection robot detects the distance between the robot body and the hole wall. When the measured distance is less than a certain set value, the detection robot device turns through the rotation of the universal joint in the detection posture correction unit, so that the detection robot always travels along the center of the two side hole walls, thereby effectively avoiding collision with the hole wall. At the same time, the laser sensor can cooperate with the corner sensor to detect the height of the falling stones in the hole. When the height of the falling stones is greater than the distance between the detection element and the hole bottom, the dynamic adjustment posture control system is used to avoid collision of the detection element and improve the overall stability, thereby effectively improving the detection accuracy;

[0105] ​S403: When water vapor and dust appear during the robot's progress detection process, the pure water carried by the spray head is sprayed to clean the borehole television screen, and the built-in resistance heating element is used to realize water vapor evaporation, further improving the environmental adaptability. Through the dynamic cooperation of the robot posture correction subunit and the detection element correction unit, stable, multi-directional and fixed-point detection signal data and borehole image acquisition can be realized, and the signal data and image are stored and transmitted back to the control room data intelligent management module;

[0106] S404: The data signal obtained by returning is processed by the signal processing unit to amplify and denoise the signal, improve the signal-to-noise ratio, and transmit the high signal-to-noise ratio signal data to the data evaluation unit for interpretation and imaging. Multi-source data fusion imaging is performed, and the fast convolution neural network deep learning algorithm is applied to the image recognition of borehole imaging, transient electromagnetic method and radar method to realize intelligent recognition of the type and positioning of the image containing the adverse geological body.

[0107] S405: Perform the next borehole detection task or retest the current borehole.

[0108] According to the intelligent detection system based on robot technology provided by the embodiment of the present application, the advanced detection module is used to obtain the detection data and real-time positioning information of the target robot, and based on the detection data, the target robot is controlled to perform the preset detection and posture correction operation. The remote transmission module is used to obtain the environment information corresponding to the target robot according to the real-time positioning information of the target robot, and determine the corresponding data transmission mode through the environment information, so as to transmit the detection data by using the data transmission mode. The data intelligent management module is used to perform data processing and evaluation operation on the detection data to obtain standard detection data, and input the standard detection data into the pre-trained intelligent detection model to output the adverse geological body recognition result corresponding to the standard detection data. The present application combines the robot platform with drilling and geophysical prospecting, and can realize the dynamic interaction of the processes of detection data-transmission data-processing data-evaluation data, thereby effectively improving the efficiency and precision of the advanced prediction and detection of underground engineering.

[0109] Secondly, the intelligent detection method based on robot technology according to the embodiment of the present application is described with reference to the accompanying drawings.

[0110] Figure 5 The flowchart of the intelligent detection method based on robot technology provided by the embodiment of the present application is shown in the figure.

[0111] As Figure 5 shown, the intelligent detection method based on robot technology includes the following steps:

[0112] In step S501, the detection data and real-time positioning information of the target robot are acquired, and the target robot is controlled to perform preset detection and posture correction operations based on the detection data.

[0113] Optionally, in an embodiment of the present application, the target robot is subjected to real-time positioning and posture correction, and the target robot is controlled to perform preset detection operations based on the detection data, which includes: determining a positioning strategy of the target robot according to the environmental information, so as to acquire real-time positioning information of the target robot through the positioning strategy, and dynamically adjusting the preset telescopic rod member and the rotating support based on the real-time positioning information, so as to control the target robot to perform multi-directional detection and / or point detection operations; setting a target shock-absorbing material at a corresponding position of the target robot, and simultaneously measuring the distance between the target robot and the hole wall of the current detection hole of the target robot through a preset laser ranging sensor, and comparing the distance with a preset collision distance threshold value, and in the case that the distance is less than the preset collision distance threshold value, controlling the target robot to perform anti-collision operations through the target shock-absorbing material and a preset anti-collision strategy.

[0114] In step S502, the environmental information corresponding to the target robot is acquired according to the real-time positioning information of the target robot, and a corresponding data transmission mode is determined through the environmental information, so as to transmit the detection data through the data transmission mode.

[0115] In step S503, the detection data is subjected to data processing and evaluation operations to obtain standard detection data, and the standard detection data is input into a pre-trained intelligent detection model to output an adverse geological body identification result corresponding to the standard detection data.

[0116] Optionally, in an embodiment of the present application, the detection data is subjected to data processing and evaluation operations to obtain standard detection data, which includes: amplifying the detection signal corresponding to the detection data to generate a detection amplified signal, and decomposing the detection amplified signal through a preset empirical mode decomposition strategy to obtain a plurality of intrinsic mode function components, and calculating a multi-scale sample entropy value of each intrinsic mode function component in the plurality of intrinsic mode function components, so as to calculate a signal processing threshold interval based on the multi-scale sample entropy value and a preset second-order difference strategy, and generate a target detection signal meeting a preset signal-to-noise ratio requirement according to the signal processing threshold interval and a preset soft threshold function; judging whether the target detection signal is a single signal source signal, if the target detection signal is a single signal source signal, performing transient electromagnetic signal inversion imaging or radar signal inversion imaging operations on the single signal source signal, if the target detection signal is a multi-signal source signal, converting the target detection signal into a reflection coefficient sequence, and performing time-depth conversion on the reflection coefficient sequence, and performing resampling and decomposition reconstruction operations on the result after time-depth conversion, so as to obtain a target reflection coefficient sequence, and acquire a feature image corresponding to the target reflection coefficient sequence, and performing principal component transformation processing on the feature image to obtain a multi-source data fusion image.

[0117] Optionally, in an embodiment of the present application, the standard detection data is input into a pre-trained intelligent detection model to output an adverse geological body identification result corresponding to the standard detection data, including: based on a pre-trained fast regional convolution model, extracting adverse hole wall features corresponding to the detection data and adverse geological body features corresponding to a multi-source data fusion image, and identifying and marking the types of the adverse hole wall features and the adverse geological body features.

[0118] It should be noted that the foregoing explanation and description of the embodiment of the intelligent detection system based on robot technology also apply to the embodiment of the intelligent detection method based on robot technology, which will not be described here.

[0119] According to the intelligent detection method based on robot technology provided in the embodiments of the present application, the detection data and real-time positioning information of a target robot are acquired, and based on the detection data, the target robot is controlled to perform a preset detection and posture correction operation; the environment information corresponding to the target robot is acquired according to the real-time positioning information of the target robot, and a corresponding data transmission mode is determined through the environment information, so as to transmit the detection data by using the data transmission mode; the detection data is subjected to data processing and evaluation operation to obtain standard detection data, and the standard detection data is input into a pre-trained intelligent detection model to output an adverse geological body identification result corresponding to the standard detection data. The present application can realize the dynamic interaction of the processes of detection data-transmission data-processing data-evaluation data by combining the robot platform with drilling and geophysical prospecting, and effectively improves the efficiency and precision of the advanced prediction and detection work of underground engineering.

[0120] Figure 6 The structure schematic diagram of the electronic device provided in the embodiments of the present application is shown. The electronic device can include:

[0121] The memory 601, the processor 602 and the computer program stored in the memory 601 and executable on the processor 602.

[0122] The processor 602 implements the intelligent detection method based on robot technology provided in the above embodiments when executing the program.

[0123] Further, the electronic device further includes:

[0124] The communication interface 603 is used for communication between the memory 601 and the processor 602.

[0125] The memory 601 is used for storing the computer program executable on the processor 602.

[0126] The memory 601 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0127] If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 6 In the figure, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0128] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can complete communication between each other through an internal interface.

[0129] The processor 602 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0130] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the above-mentioned wisdom detection method based on robot technology.

[0131] In the description of the application, reference to "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that a particular feature, structure, material, or characteristic being described is included in at least one embodiment or example of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. In addition, the usage of "N" means at least two, for example, two, three or the like, unless explicitly stated otherwise.

[0132] Furthermore, the terms "first", "second", or the like, are used merely as a designation of certain elements or features, and do not imply or connote relative importance or a specific order of categorization of the indicated features. Accordingly, features described as "first" or "second" can be explicitly or implicitly included in at least one of the features. In the description of the application, the term "N" means at least two, for example, two, three, etc., unless explicitly stated otherwise.

[0133] Any process or method descriptions or blocks in flow charts or otherwise described herein represent embodiments which can be managed as one or more modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions or steps, and alternate implementations are possible. In some embodiments, the processes and methods described can be executed by one or more apparatuses or devices, either directly or after conversion to another language. Alternate implementations are possible.

[0134] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of instructions to implement logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a computer- readable storage medium or a computer-readable signal medium. The computer- readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires (electrical connections), a portable computer diskette (a magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via, for example, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0135] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0136] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer-readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0137] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0138] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A smart detection system based on robotics technology, characterized in that, include: The advanced detection module is used to acquire the detection data and real-time positioning information of the target robot, and based on the detection data, control the target robot to perform preset detection and attitude correction operations; The remote transmission module is used to obtain the environmental information corresponding to the target robot based on the real-time positioning information of the target robot, and determine the corresponding data transmission method through the environmental information, so as to transmit the detection data using the data transmission method; The data intelligence management module is used to perform data processing and evaluation operations on the detection data to obtain standard detection data, and input the standard detection data into a pre-trained intelligent detection model to output the adverse geological body identification result corresponding to the standard detection data; The advanced detection module includes: Detection robot subsystem; The option unit is used to select target detection elements based on preset underground engineering detection requirements, wherein the target detection elements include at least one of borehole television, borehole radar, and borehole transient electromagnetic; The detection task management unit is used to determine the detection task of the target robot according to the preset underground engineering detection requirements, generate the detection instructions for the detection task, and send the detection instructions to the target robot to control the target robot to perform corresponding detection actions according to the detection instructions; An emergency processing unit is used to acquire environmental information of the current probe hole of the target robot, and determine whether there is a preset emergency event in the current probe hole based on the environmental information. If there is a preset emergency event in the current probe hole, the unit controls the target robot to perform a preset emergency event processing operation. The detection robot subsystem includes: A positioning unit is used to determine the positioning strategy of the target robot based on the environmental information, so as to obtain the real-time positioning information of the target robot through the positioning strategy; The anti-collision unit is used to set target shock-absorbing material at the corresponding position of the target robot, and at the same time measure the distance between the target robot and the hole wall of the current probe hole of the target robot according to the preset laser range sensor, compare the distance with the preset collision distance threshold, and when the distance is less than the preset collision distance threshold, control the target robot to perform anti-collision operation through the target shock-absorbing material and the preset anti-collision strategy. A detection posture correction unit is used to dynamically adjust preset telescopic rod-like components and rotating supports to control the target robot to perform multi-directional detection and / or fixed-point detection operations. The first storage unit is used to store the detection data of the target robot and to back up the detection data using a preset cloud storage strategy; The detection posture correction unit includes a robot posture correction subunit and a detection element posture correction subunit. The robot posture correction subunit includes: a second telescopic rod, a second connecting rod, a third rotary joint, a third connecting rod, a universal joint, a third telescopic rod, and a metal-rubber track. One end of the second telescopic rod is fixedly connected to the robot body, and the other end is fixedly connected to the second connecting rod. The second connecting rod is fixedly connected to the third connecting rod via the third rotary joint. The third connecting rod is fixedly connected to the third telescopic rod via the universal joint and to the metal-rubber track via the third telescopic rod. The second telescopic rod, through extension and retraction, the third rotary joint, the universal joint, and the third telescopic rod, adjust the orientation of the mechanical leg for its inward and outward retraction function. The probe element attitude correction subunit includes: a fourth telescopic rod, a rotating support, and a slide rail. The fourth telescopic rod is located below the robot body, with one end fixedly connected to the robot body and the other end connected to the rotating support. The slide rail is fixedly connected below the rotating support and connected to the option unit via a slider. The fourth telescopic rod enables the probe element to move up and down, the slide rail enables the probe element to move left, right, forward, and backward on the horizontal plane, and the rotating support enables the probe element to rotate.

2. The intelligent detection system based on robotics technology according to claim 1, characterized in that, The data intelligence management module includes: Second storage unit; The signal processing unit is used to amplify the detection signal corresponding to the detection data, generate a detection amplified signal, and decompose the detection amplified signal using a preset empirical mode decomposition strategy to obtain multi-order intrinsic mode function components. It also calculates the multi-scale sample entropy value of each order intrinsic mode function component in the multi-order intrinsic mode function components, calculates the signal processing threshold interval based on the multi-scale sample entropy value and a preset second-order difference strategy, and generates a target detection signal that meets the preset signal-to-noise ratio requirement according to the signal processing threshold interval and a preset soft threshold function. The data evaluation unit is used to determine whether the target detection signal is a single signal source signal. If the target detection signal is a single signal source signal, transient electromagnetic signal inversion imaging or radar signal inversion imaging operation is performed on the single signal source signal. If the target detection signal is a multi-signal source signal, the target detection signal is converted into a reflection coefficient sequence, and time-depth transformation is performed on the reflection coefficient sequence. The result after time-depth transformation is resampled and decomposed for reconstruction to obtain the target reflection coefficient sequence. The corresponding feature image of the target reflection coefficient sequence is obtained, and principal component transformation is performed on the feature image to obtain a multi-source data fusion image. The image recognition unit is used to extract the features of the defective borehole walls corresponding to the detection data and the features of the defective geological bodies corresponding to the multi-source data fusion image based on a pre-trained fast region convolution model, and to identify and label the types of the defective borehole wall features and the defective geological bodies.

3. A smart detection method based on robotics technology, applied to the smart detection system based on robotics technology as described in any one of claims 1-2, characterized in that, Includes the following steps: Acquire the target robot's detection data and real-time positioning information, and based on the detection data, control the target robot to perform preset detection and attitude correction operations; The environmental information corresponding to the target robot is obtained based on the real-time positioning information of the target robot, and the corresponding data transmission method is determined through the environmental information so as to transmit the detection data using the data transmission method. The detection data is processed and evaluated to obtain standard detection data, which is then input into a pre-trained intelligent detection model to output the identification result of the adverse geological body corresponding to the standard detection data.

4. The method according to claim 3, characterized in that, The step of performing real-time localization and attitude correction on the target robot, and controlling the target robot to perform preset detection operations based on the detection data, includes: The positioning strategy of the target robot is determined based on the environmental information, so as to obtain the real-time positioning information of the target robot through the positioning strategy. At the same time, based on the real-time positioning information, the preset telescopic rod-like components and rotating supports are dynamically adjusted to control the target robot to perform multi-directional detection and / or fixed-point detection operations. Target damping material is placed at the corresponding position of the target robot. At the same time, the distance between the target robot and the hole wall of the current probe hole of the target robot is measured according to the preset laser range sensor. The distance is compared with the preset collision distance threshold. If the distance is less than the preset collision distance threshold, the target robot is controlled to perform anti-collision operation through the target damping material and the preset anti-collision strategy.

5. The method according to claim 3, characterized in that, The data processing and evaluation operations performed on the probe data to obtain standard probe data include: The detection signal corresponding to the detection data is amplified to generate a detection amplified signal. The detection amplified signal is then decomposed using a preset empirical mode decomposition strategy to obtain multi-order intrinsic mode function components. The multi-scale sample entropy value of each order intrinsic mode function component is calculated. Based on the multi-scale sample entropy value and a preset second-order difference strategy, a signal processing threshold interval is calculated. A target detection signal that meets the preset signal-to-noise ratio requirement is then generated according to the signal processing threshold interval and a preset soft threshold function. If the target detection signal is a single-source signal, then transient electromagnetic signal inversion imaging or radar signal inversion imaging is performed on the single-source signal. If the target detection signal is a multi-source signal, then the target detection signal is converted into a reflection coefficient sequence, and time-depth transformation is performed on the reflection coefficient sequence. The result after time-depth transformation is then resampled and decomposed for reconstruction to obtain the target reflection coefficient sequence. The corresponding feature image is obtained, and principal component transformation is performed on the feature image to obtain a multi-source data fusion image.

6. The method according to claim 5, characterized in that, The step of inputting the standard detection data into a pre-trained intelligent detection model to output the identification result of the adverse geological body corresponding to the standard detection data includes: Based on a pre-trained fast region convolution model, the features of the defective borehole walls corresponding to the detection data and the features of the defective geological bodies corresponding to the multi-source data fusion image are extracted, and the types of the defective borehole wall features and the defective geological bodies are identified and labeled.

7. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the robotic-based intelligent detection method as described in any one of claims 3-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the robotics-based intelligent detection method as described in any one of claims 3-6.

Images