Tunneling equipment navigation method based on multi-source information fusion

Abstract

The invention relates to the technical field of mine intelligent and automatic tunneling, and discloses a multi-source information fusion-based tunneling equipment navigation method, which comprises the following steps of: acquiring multi-dimensional data through a multi-source sensing and data acquisition module, and optimizing visual information through an image enhancement module; the multi-dimensional data analysis module analyzes data features and drives the sensor dynamic switching module to intelligently select and match an optimal sensor combination; the complex environment interference correction module is used for eliminating complex interference of dust and shielding in a targeted manner and generating a precise positioning result; the navigation instruction execution module controls equipment operation according to the latest positioning result, and the data feedback module calibrates model parameters in real time; and the navigation state display module visually displays the operation situation, the abnormity emergency processing module quickly responds to the risk event, and all the modules cooperatively operate to form closed-loop control, so that the system has the technical advantages of high-precision positioning, strong environmental adaptability and real-time dynamic adjustment.

Description

Technical Field

[0001] This invention relates to the field of intelligent and automated tunneling technology in mining, specifically a navigation method for tunneling equipment based on multi-source information fusion. Background Technology

[0002] In complex underground operations such as coal mines and tunnel excavation, traditional single-mode navigation technology faces severe environmental adaptability challenges. On the one hand, high concentrations of dust and low light conditions severely restrict the effectiveness of visual pose detection technology. Optical measuring equipment such as total stations, lasers, and lidar are easily affected by dust scattering and equipment obstruction, and optical path blockage directly causes positioning failure. On the other hand, pose detection technology based on laser ranging suffers from response lag and data jitter under dynamic conditions, making it difficult to meet real-time requirements. While inertial navigation systems can provide high-precision output in the short term, their error accumulation over time leads to a continuous increase in long-term positioning deviation. The environmental adaptability defects of single-sensor solutions are particularly prominent. For example, wheeled odometers rely solely on wheel rotation parameters to calculate displacement. After long-term operation, factors such as slippage and idling cause significant accumulated errors, leading to the equipment becoming "lost." Further complicating matters, in special geological conditions such as fractured zones and aquifers, radar echoes are exacerbated by the inhomogeneity of the rock mass, resulting in frequent false alarms and missed detections, further weakening the reliability of the positioning system. These technological bottlenecks indicate that a single sensor is insufficient to cope with the dynamic, complex, and extreme nature of underground environments. There is an urgent need to integrate the advantages of different sensors through multi-source information fusion technology to build a robust and stable comprehensive navigation system. Summary of the Invention

[0003] (a) Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a navigation method for tunneling equipment based on multi-source information fusion, which has the advantages of high-precision positioning, strong environmental adaptability, and real-time dynamic adjustment. It solves the problems of low positioning accuracy, poor real-time performance, and insufficient reliability of traditional single-mode navigation technology in complex underground environments.

[0004] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: a tunneling equipment navigation method based on multi-source information fusion, comprising the following steps: Step 1: Establish the system, which includes a multi-source sensing and data acquisition module, an image enhancement module, a multi-dimensional data analysis module, a sensor dynamic switching module, a complex environment interference correction module, a navigation command execution module, a data feedback module, a navigation status display module, and an anomaly emergency handling module. Step 2: The multi-source sensing and data acquisition module is responsible for deploying various sensors and collecting raw data; Step 3: The image enhancement module receives visual images from the raw sensor data and environmental monitoring data, preprocesses them, and outputs the enhanced image pixel values. ; Step 4: The multi-dimensional data analysis module outputs sensor adaptability based on the collected data. Error correction value Radar data correction value ; Step 5: The sensor dynamic switching module switches based on sensor compatibility. Set an adaptation threshold; when the sensor adaptation... < When the system is in use, it automatically switches to a sensor with a higher compatibility. Step 5: Complex environment interference correction module combined with error correction value Radar data correction value The calculation formula is used to perform secondary optimization on the positioning data; Step 7: The navigation command execution module receives the corrected precise positioning data, combines it with the preset trajectory of the tunneling operation, generates navigation commands for equipment steering and speed adjustment, and controls the tunneling equipment to operate according to the planned path; Step 8: The data feedback module collects the actual pose data of the device after executing navigation commands in real time, compares it with the preset trajectory, and calculates the deviation value. ; Step 9: The navigation status display module connects to the underground visualization terminal via a 4G / 5G wireless backup network, and displays the current position of the tunneling equipment, navigation accuracy, working status of each sensor, and environmental parameters in real time through the underground visualization terminal. Step 10: The emergency handling module and the navigation status display module work together to automatically execute emergency shutdown, location locking, fault reporting, and recovery guidance when extreme abnormal situations occur.

[0005] Preferably, the multi-source sensing and data acquisition module includes a sensor array unit and a real-time environmental monitoring unit.

[0006] Preferably, the sensor array unit collects raw sensor data through sensors, including visual image data, lidar point cloud data, inertial navigation system angular velocity and acceleration data, wheel odometer displacement data, ultrasonic / millimeter-wave radar distance data, total station absolute position data, equipment attitude data, and sensor status data.

[0007] Preferably, the real-time environmental monitoring unit integrates a laser dust concentration sensor and a high dynamic range illuminance sensor to collect environmental monitoring data, including dust concentration data, light intensity data, ambient temperature data, ambient humidity data, noise level data, vibration data, harmful gas concentration data, and electromagnetic interference data.

[0008] Preferably, the image enhancement module uses an image dehazing algorithm based on an atmospheric scattering model for enhancement, and its calculation formula is as follows: In the formula, This represents the enhanced image pixel value, that is, the image at the position after dehazing. Pixel intensity at that location Indicates the location The original image pixel intensity at that location, Indicates ambient light intensity. This represents a transmittance diagram. This represents the minimum threshold for transmittance.

[0009] Preferably, the multi-dimensional data analysis module includes a sensor environment adaptability analysis unit, a complex environment positioning error analysis unit, and a special ground-penetrating radar interference analysis unit.

[0010] Preferably, the sensor environment adaptability analysis unit calculates the sensor adaptability degree. This is used to determine the reliability of each sensor under the current environment, and its calculation formula is: In the formula, This represents the fit of the i-th type of sensor. The current effective data rate of the sensor. Indicates the standard effective data rate of the sensor. Indicates the intensity of interference to the sensor. Indicates the threshold of interference intensity. Indicates the effective data rate weight. This represents the weight of the anti-interference strength.

[0011] Preferably, the complex environment positioning error analysis unit calculates error correction values ​​for positioning deviations caused by dust and obstructions. The calculation formula is as follows: In the formula, Indicates the error correction value. , These represent the error coefficients for dust concentration and obstruction probability, respectively. This indicates the dust concentration measured in real time. Indicates the maximum dust concentration. This indicates the probability of laser beam path obstruction. This represents the original positioning value of the laser sensor.

[0012] Preferably, the special ground-penetrating radar interference analysis unit calculates radar data correction values ​​to address radar echo interference from fractured zones and aquifers. The calculation formula is as follows: In the formula, This indicates the radar data correction value. Indicates the geological disturbance coefficient. Indicates parameters of rock mass heterogeneity. Indicates the threshold of rock mass heterogeneity. This represents the original radar positioning value.

[0013] Preferably, the complex environment interference correction module combines the error correction value Radar data correction value The calculation formula is used to perform secondary optimization on the positioning data, resulting in the final positioning value. ,in This is the initial positioning value for the sensor; The data feedback module collects the actual pose data of the device after executing navigation commands in real time, compares it with the preset trajectory, and calculates the deviation value. ,in, Preset trajectory positioning values; The system will automatically trigger an audible and visual alarm when the navigation status display module detects the following situations: (1) Trajectory deviation exceeds threshold: When the deviation value A deviation of >0.3m indicates a serious deviation in the current trajectory, which could lead to over- or under-excavation of the tunnel. (2) Sensor failure risk: a certain type of main sensor A value less than 0.4 indicates that the current data reliability is extremely low and cannot support navigation. (3) Environmental parameters exceed the standard: real-time measured dust concentration When the concentration is >10mg / m³, it indicates that the current dust concentration has already endangered human health and also affects the accuracy of the sensor. (4) Extreme abnormal situations: When the entire navigation system fails or the deviation value is abnormal. If the distance is greater than 0.5m or all main sensors fail, it indicates that the current navigation system can no longer guarantee the safe operation of the equipment.

[0014] Compared with existing technologies, this invention provides a navigation method for tunneling equipment based on multi-source information fusion, which has the following beneficial effects: 1. This invention utilizes sensor adaptability. The calculation is used to quantitatively evaluate the reliability of each sensor in the complex downhole environment, distinguish the environmental adaptability of different sensors, and provide a clear quantitative basis for dynamic sensor switching. This achieves the beneficial effect of avoiding reliance on subjective judgment to select sensors, ensuring switching to a more adaptable sensor combination, and guaranteeing the continuous and stable output of navigation data. Ultimately, it solves the problem that traditional sensor selection relies on experience and cannot adapt to dynamic changes in the underground environment.

[0015] 2. This invention uses error correction values. The calculations are used to accurately quantify the interference of dust and obstruction on laser positioning, and to specifically counteract the positioning deviation caused by these two factors, controlling the laser positioning error within an acceptable range (within ±0.1m). This improves the positioning accuracy of the laser sensor in complex environments, avoids navigation trajectory deviation caused by dust obstruction, and provides reliable error data for subsequent complex environment interference correction modules. Ultimately, this solves the problem of large errors in traditional laser positioning in underground high-dust and multi-obstruction environments.

[0016] 3. This invention uses radar data correction values. The calculations are used to accurately capture the interference of fracture zones and aquifers on radar echoes, quantify the positioning deviation caused by rock mass inhomogeneity and correct the original radar data error accordingly. This improves the positioning reliability of radar sensors under special geological conditions, avoids the decline in navigation accuracy caused by geological interference, and provides a basis for geological interference correction for the final positioning value optimization. This invention solves the problems of false alarms and missed detections and large positioning deviations in traditional radar positioning in special geological environments.

[0017] 4. This invention achieves accurate identification of abnormal situations by setting alarm trigger conditions for different scenarios, and provides targeted emergency handling measures to achieve automatic response and facilitate manual monitoring. Finally, it solves the problems of difficulty in detecting abnormal situations, lack of basis for emergency handling, low efficiency of fault recovery, and lack of intuitiveness of manual monitoring in underground tunneling navigation, thereby ensuring safe and efficient tunneling operations and reducing the incidence of construction accidents and the duration of work interruptions. Attached Figure Description

[0018] Figure 1 This is a diagram illustrating the steps of the method of the present invention. Detailed Implementation

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Please see Figure 1 A navigation method for tunneling equipment based on multi-source information fusion includes the following steps: Step 1: Establish the system, which includes a multi-source sensing and data acquisition module, an image enhancement module, a multi-dimensional data analysis module, a sensor dynamic switching module, a complex environment interference correction module, a navigation command execution module, a data feedback module, a navigation status display module, and an anomaly emergency handling module. Step 2: The multi-source sensing and data acquisition module is responsible for deploying various sensors and collecting raw data, and packaging and transmitting all raw sensor data and environmental monitoring data to the next module. Step 3: The image enhancement module receives visual images from the raw sensor data and environmental monitoring data, and preprocesses them. To address image blurring and low contrast caused by dust and low light, an image dehazing algorithm based on an atmospheric scattering model is used for enhancement, and the enhanced image pixel values ​​are output. This improves image clarity and feature recognizability, providing high-quality data support for subsequent image analysis and processing. Step 4: The multi-dimensional data analysis module outputs sensor adaptability based on the collected data. Error correction value Radar data correction value ; Step 5: The sensor dynamic switching module switches based on sensor compatibility. Set an adaptation threshold; when the sensor adaptation... < ( When the minimum threshold is reached, the system automatically switches to a sensor with higher compatibility (e.g., sensor compatibility). When the value is less than 0.6, switch to laser + inertial fusion navigation to ensure continuous and reliable navigation data; Step 5: Complex environment interference correction module combined with error correction value Radar data correction value The calculation formula is used to perform secondary optimization on the positioning data, resulting in the final positioning value. ,in This module provides the initial positioning value for the sensor and addresses positioning accuracy issues caused by dust obstruction and geological interference. Step 7: The navigation command execution module receives the corrected precise positioning data, combines it with the preset trajectory of the tunneling operation, and generates navigation commands such as equipment turning and speed adjustment to control the tunneling equipment to operate according to the planned path. Step 8: The data feedback module collects the actual pose data of the device after executing navigation commands in real time, compares it with the preset trajectory, and calculates the deviation value. , (For the preset trajectory positioning value), the deviation data is fed back to the multi-dimensional data analysis module to optimize the parameters of the subsequent fusion algorithm; Step 9: The navigation status display module connects to the underground visualization terminal via a 4G / 5G wireless backup network. The underground visualization terminal displays the current position of the tunneling equipment, navigation accuracy, working status of each sensor, and environmental parameters in real time, facilitating real-time monitoring by operators. When an abnormal situation is displayed (such as deviation exceeding the threshold), the abnormal emergency handling module is activated to issue an automatic alarm. Step 10: The emergency handling module and the navigation status display module work together. In case of extreme abnormal situations (such as overall navigation system failure, etc.), When the distance is greater than 0.5m and all main sensors fail, the system will automatically perform emergency shutdown, position locking, fault reporting, and recovery guidance.

[0021] The multi-source sensing and data acquisition module includes a sensor array unit and a real-time environmental monitoring unit.

[0022] The sensor array unit is equipped with explosion-proof high-definition infrared cameras (for low-light vision), micro-pulse lidar (with strong anti-dust interference capability), fiber optic inertial navigation system (for high-precision angular velocity / accelerometer), anti-slip encoder (for wheeled odometer), ultrasonic / millimeter-wave radar (for short-range obstacle detection), and total station cooperative target (providing absolute position reference) at the front, sides, and top of the tunneling equipment. It collects raw sensor data, including visual image data, lidar point cloud data, inertial navigation system angular velocity and acceleration data, wheeled odometer displacement data, ultrasonic / millimeter-wave radar distance data, total station absolute position data, equipment attitude data, and sensor status data.

[0023] The real-time environmental monitoring unit integrates a laser dust concentration sensor (for real-time dust concentration monitoring) and a high dynamic range illuminance sensor (for real-time ambient light data monitoring), and collects environmental monitoring data, including dust concentration data, light intensity data, ambient temperature data, ambient humidity data, noise level data, vibration data, harmful gas concentration data, and electromagnetic interference data. This environmental data provides key inputs for subsequent image preprocessing and sensor weight allocation.

[0024] The advantages are: by comprehensively capturing the status of the tunneling equipment and the underground environment information, it avoids navigation deviations caused by missing single data points, and provides reliable data support for subsequent image enhancement and sensor adaptation analysis. It solves the problems of incomplete navigation data collection and difficulty in perceiving environmental interference in the underground environment from the source of data.

[0025] The image enhancement module uses an image dehazing algorithm based on an atmospheric scattering model for enhancement. The calculation formula is as follows: In the formula, This represents the enhanced image pixel value, that is, the image at the position after dehazing. The pixel intensity at that location represents the pixel value of the original image. Indicates the location The original image pixel intensity at the location is collected by explosion-proof high-definition infrared cameras installed at the front, sides, and top of the tunneling equipment, and is used to provide visual information about the environment surrounding the tunneling equipment. This represents ambient light intensity, which can be estimated from data from a light sensor. It reflects the degree to which ambient light affects the image and is obtained in real time by a high dynamic range light sensor. It is used to estimate the impact of ambient light on the image and helps adjust the intensity of image enhancement. This represents the transmittance map, which shows the degree of light attenuation as it travels through a medium. Its estimated value is negatively correlated with dust concentration sensor data; that is, the higher the dust concentration, the lower the transmittance. The smaller the value, the lower the transmittance value, reflecting the degree of image blurring caused by light scattering and absorption by media such as dust. This transmittance is estimated using data from a dust concentration sensor. The dust concentration sensor monitors the dust concentration in the tunneling environment in real time. The transmittance map reflects the degree of influence of dust on light propagation; the higher the dust concentration, the lower the transmittance, and the more blurred the image. This represents the minimum threshold for transmittance, used to avoid numerical instability caused by dividing by too small a transmittance value, ensuring the stability of the calculation. It is a preset constant value used to ensure that no calculation errors occur during the calculation process due to division by zero or very small values, thus guaranteeing the stability and reliability of the image enhancement process. The advantage is that it calculates the enhanced image pixel values. By combining the collected data, the image enhancement unit can effectively restore image details and improve the success rate of feature point extraction and matching, thereby providing clearer and more accurate visual information for subsequent navigation and positioning.

[0026] The multi-dimensional data analysis module includes a sensor environment adaptability analysis unit, a complex environment positioning error analysis unit, and a special ground-penetrating radar interference analysis unit.

[0027] The sensor environmental adaptability analysis unit calculates the sensor adaptability. This is used to determine the reliability of each sensor under the current environment, and its calculation formula is: In the formula, This represents the fit of the i-th type of sensor (such as vision, laser, inertial). The current effective data rate of the sensor. Indicates the standard effective data rate of the sensor. This indicates the intensity of interference to the sensor (such as visual interference from dust or laser interference from obstruction). Indicates the threshold of interference intensity. This indicates the weight of the effective data rate (reflecting the priority of data continuity). This indicates the weight of the anti-interference strength (reflecting the priority of environmental adaptability).

[0028] The advantage is that, through the above sensor compatibility... The calculation is used to quantitatively evaluate the reliability of each sensor in the complex downhole environment, distinguish the environmental adaptability of different sensors, and provide a clear quantitative basis for dynamic sensor switching. This achieves the beneficial effect of avoiding reliance on subjective judgment to select sensors, ensuring switching to a more adaptable sensor combination, and guaranteeing the continuous and stable output of navigation data. Ultimately, it solves the problem that traditional sensor selection relies on experience and cannot adapt to dynamic changes in the underground environment.

[0029] The complex environment positioning error analysis unit calculates error correction values ​​to address positioning deviations caused by dust and obstructions. The calculation formula is as follows: In the formula, Indicates the error correction value. , These represent the error coefficients for dust concentration and obstruction probability, respectively. This indicates the dust concentration measured in real time. Indicates the maximum dust concentration. This represents the probability of laser path obstruction (0-1, calculated from equipment obstruction monitoring data). This represents the original positioning value of the laser sensor.

[0030] The advantage is that, through the above error correction values... The calculations are used to accurately quantify the interference of dust and obstruction on laser positioning, and to specifically counteract the positioning deviation caused by these two factors, controlling the laser positioning error within an acceptable range (within ±0.1m). This improves the positioning accuracy of the laser sensor in complex environments, avoids navigation trajectory deviation caused by dust obstruction, and provides reliable error data for subsequent complex environment interference correction modules. Ultimately, this solves the problem of large errors in traditional laser positioning in underground high-dust and multi-obstruction environments.

[0031] The special ground-penetrating radar interference analysis unit calculates radar data correction values ​​to address radar echo interference from fractured zones and aquifers. The calculation formula is as follows: In the formula, This indicates the radar data correction value. Indicates the geological disturbance coefficient. The parameters representing the heterogeneity of the rock mass are calculated using radar echo fluctuation frequencies. Indicates the threshold of rock mass heterogeneity. This represents the original radar positioning value.

[0032] The advantage is that the above radar data correction values... The calculations are used to accurately capture the interference of fracture zones and aquifers on radar echoes, quantify the positioning deviation caused by rock mass inhomogeneity and correct the original radar data error accordingly. This improves the positioning reliability of radar sensors under special geological conditions, avoids the decline in navigation accuracy caused by geological interference, and provides a basis for geological interference correction for the final positioning value optimization. This invention solves the problems of false alarms and missed detections and large positioning deviations in traditional radar positioning in special geological environments.

[0033] When the navigation status display module detects the following conditions, the system will automatically trigger an audible and visual alarm (the terminal's built-in buzzer emits a "beep beep" alarm, and the screen flashes a red border): (1) Trajectory deviation exceeds threshold: When the deviation value A deviation >0.3m indicates a serious trajectory error, which could lead to over- or under-excavation of the tunnel. The tunneling equipment's forward speed must be immediately reduced to below 0.3m / min, while simultaneously increasing the steering adjustment force. The deviation value... ≤0.1m; if the deviation does not decrease after 30 seconds of adjustment, the operator needs to manually pause navigation through the visual terminal to check the cause of the abnormal positioning data (such as whether the lidar is blocked or whether the inertial navigation has accumulated errors). (2) Sensor failure risk: a certain type of main sensor A value less than 0.4 indicates extremely low data reliability, making navigation unsupportable. The system must automatically trigger an emergency sensor switching process, prioritizing the use of adaptive sensors. A backup sensor combination with a value ≥0.7 (such as a "fiber optic inertial navigation + total station cooperative target" mode) is required; operators must simultaneously check the status of failed sensors (e.g., clean dust from the visual camera lens, adjust the lidar installation angle), and wait... Once the value reaches ≥0.6, you can manually switch back to the original sensor combination. (3) Environmental parameters exceed the standard: real-time measured dust concentration A dust concentration >10 mg / m³ indicates that the current dust concentration has endangered personnel health and affected sensor accuracy. The underground dust suppression spray system must be activated immediately (e.g., opening the high-pressure spray devices at the front of the equipment and the top of the tunnel) to reduce the dust concentration to below 6 mg / m³. If dust suppression spraying continues for 10 minutes... If the concentration is still >10mg / m³, tunneling operations must be suspended. Operators should wear dust masks and enter the work area to check if the dust suppression system is malfunctioning. At the same time, sensors that are severely affected by dust (such as vision sensors) should be turned off, and the dust-resistant laser + inertial navigation fusion mode should be switched to. (4) Extreme abnormal situations: When the entire navigation system fails or the deviation value is abnormal. When the deviation is greater than 0.5m or all main sensors fail, it indicates that the current navigation system can no longer guarantee the safe operation of the equipment. This may lead to serious accidents such as equipment collision with the tunnel wall (e.g., if the tunneling machine is 3m wide and the tunnel is 5m wide, a deviation of 0.5m will result in the machine being only 0.5m from the side wall, with a collision risk of 90%), or personnel injury (e.g., the equipment deviating from the trajectory and colliding with the operators). In such cases, it is necessary to automatically execute emergency shutdown, position locking, fault reporting, and guidance recovery. After the fault is resolved (e.g., replacing the faulty sensor or restarting the navigation system), the module automatically retrieves the coordinates of the shutdown position and connects them to the nearest path point of the preset trajectory. Once the operator confirms, navigation can be started without having to replan the entire trajectory.

[0034] The advantages are: by setting alarm trigger conditions in the above-mentioned scenarios, the system can accurately identify abnormal situations and provide targeted emergency response measures to achieve automatic response and facilitate manual monitoring. In the end, it solves the problems of difficulty in detecting abnormal situations, lack of basis for emergency handling, low efficiency of fault recovery, and lack of intuitiveness in manual monitoring in underground tunneling navigation, thereby ensuring the safe and efficient progress of tunneling operations and reducing the incidence of construction accidents and the duration of work interruptions.

[0035] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A navigation method for tunneling equipment based on multi-source information fusion, characterized in that, Includes the following steps: Step 1: Establish the system, which includes a multi-source sensing and data acquisition module, an image enhancement module, a multi-dimensional data analysis module, a sensor dynamic switching module, a complex environment interference correction module, a navigation command execution module, a data feedback module, a navigation status display module, and an anomaly emergency handling module. Step 2: The multi-source sensing and data acquisition module is responsible for deploying various sensors and collecting raw data; Step 3: The image enhancement module receives visual images from the raw sensor data and environmental monitoring data, preprocesses them, and outputs the enhanced image pixel values. ; Step 4: The multi-dimensional data analysis module outputs sensor adaptability based on the collected data. Error correction value Radar data correction value ; Step 5: The sensor dynamic switching module switches based on sensor compatibility. Set an adaptation threshold; when the sensor adaptation... < When the system is in use, it automatically switches to a sensor with a higher compatibility. Step 5: Complex environment interference correction module combined with error correction value Radar data correction value The calculation formula is used to perform secondary optimization on the positioning data; Step 7: The navigation command execution module receives the corrected precise positioning data, combines it with the preset trajectory of the tunneling operation, generates navigation commands for equipment steering and speed adjustment, and controls the tunneling equipment to operate according to the planned path; Step 8: The data feedback module collects the actual pose data of the device after executing navigation commands in real time, compares it with the preset trajectory, and calculates the deviation value. ; Step 9: The navigation status display module connects to the underground visualization terminal via a 4G / 5G wireless backup network, and displays the current position of the tunneling equipment, navigation accuracy, working status of each sensor, and environmental parameters in real time through the underground visualization terminal. Step 10: The emergency handling module and the navigation status display module work together to automatically execute emergency shutdown, location locking, fault reporting, and recovery guidance when extreme abnormal situations occur.

2. The tunneling equipment navigation method based on multi-source information fusion according to claim 1, characterized in that: The multi-source sensing and data acquisition module includes a sensor array unit and a real-time environmental monitoring unit.

3. The tunneling equipment navigation method based on multi-source information fusion according to claim 2, characterized in that: The sensor array unit collects raw sensor data through sensors, including visual image data, lidar point cloud data, inertial navigation system angular velocity and acceleration data, wheel odometer displacement data, ultrasonic / millimeter-wave radar distance data, total station absolute position data, equipment attitude data, and sensor status data.

4. The tunneling equipment navigation method based on multi-source information fusion according to claim 2, characterized in that: The real-time environmental monitoring unit integrates a laser dust concentration sensor and a high dynamic range illuminance sensor to collect environmental monitoring data, including dust concentration data, light intensity data, ambient temperature data, ambient humidity data, noise level data, vibration data, harmful gas concentration data, and electromagnetic interference data.

5. The tunneling equipment navigation method based on multi-source information fusion according to claim 1, characterized in that: The image enhancement module employs an image dehazing algorithm based on an atmospheric scattering model for enhancement. The calculation formula is as follows: In the formula, This represents the enhanced image pixel value, that is, the image at the position after dehazing. Pixel intensity at that location Indicates the location The original image pixel intensity at that location, Indicates ambient light intensity. This represents a transmittance diagram. This represents the minimum threshold for transmittance.

6. The tunneling equipment navigation method based on multi-source information fusion according to claim 1, characterized in that: The multi-dimensional data analysis module includes a sensor environment adaptability analysis unit, a complex environment positioning error analysis unit, and a special ground-penetrating radar interference analysis unit.

7. The tunneling equipment navigation method based on multi-source information fusion according to claim 6, characterized in that: The sensor environmental adaptability analysis unit calculates the sensor adaptability. This is used to determine the reliability of each sensor under the current environment, and its calculation formula is: In the formula, This represents the fit of the i-th type of sensor. The current effective data rate of the sensor. Indicates the standard effective data rate of the sensor. Indicates the intensity of interference to the sensor. Indicates the threshold of interference intensity. Indicates the effective data rate weight. This represents the weight of the anti-interference strength.

8. The tunneling equipment navigation method based on multi-source information fusion according to claim 6, characterized in that: The complex environment positioning error analysis unit calculates error correction values ​​to address positioning deviations caused by dust and obstructions. The calculation formula is as follows: In the formula, Indicates the error correction value. , These represent the error coefficients for dust concentration and obstruction probability, respectively. This indicates the dust concentration measured in real time. Indicates the maximum dust concentration. This indicates the probability of laser beam path obstruction. This represents the original positioning value of the laser sensor.

9. The tunneling equipment navigation method based on multi-source information fusion according to claim 6, characterized in that: The specialized ground-penetrating radar interference analysis unit calculates radar data correction values ​​to address radar echo interference from fractured zones and aquifers. The calculation formula is as follows: In the formula, This indicates the radar data correction value. Indicates the geological interference coefficient. Indicates parameters of rock mass heterogeneity. Indicates the threshold of rock mass heterogeneity. This represents the original radar positioning value.

10. The tunneling equipment navigation method based on multi-source information fusion according to claim 1, characterized in that: The complex environment interference correction module combines error correction values Radar data correction value The calculation formula is used to perform secondary optimization on the positioning data, resulting in the final positioning value. ,in This is the initial positioning value for the sensor; The data feedback module collects the actual pose data of the device after executing navigation commands in real time, compares it with the preset trajectory, and calculates the deviation value. ,in, Preset trajectory positioning values; The system will automatically trigger an audible and visual alarm when the navigation status display module detects the following situations: (1) Trajectory deviation exceeds threshold: When the deviation value A deviation of >0.3m indicates a serious deviation in the current trajectory, which could lead to over- or under-excavation of the tunnel. (2) Sensor failure risk: a certain type of main sensor A value less than 0.4 indicates that the current data reliability is extremely low and cannot support navigation. (3) Environmental parameters exceed the standard: real-time measured dust concentration When the concentration is >10mg / m³, it indicates that the current dust concentration has already endangered human health and also affects the accuracy of the sensor. (4) Extreme abnormal situations: When the entire navigation system fails or the deviation value is abnormal. If the distance is greater than 0.5m or all main sensors fail, it indicates that the current navigation system can no longer guarantee the safe operation of the equipment.

Images