Intelligent spraying maintenance system for tunnel secondary lining based on real-time scanning of micro-cracks

Abstract

The present invention discloses an intelligent spraying maintenance system for a tunnel secondary lining based on real-time scanning of microcracks, and relates to the technical field of tunnel maintenance. The present invention comprises a scanning unit, a track platform, a processing unit, a spraying module, and a robotic arm. The scanning unit comprises a laser module and a vision module. The output ends of the laser module and the vision module are both connected to the input end of the processing unit. The port of the track platform establishes communication with the port of the processing unit. The output end of the processing unit is respectively connected to the input end of the spraying module and the input end of the robotic arm. The track platform is a suspended rail vehicle, which is installed on a track laid on the top surface of the tunnel. The present invention can quickly locate the coordinates of microcracks through automatic scanning of the scanning unit, classify microcracks through manual evaluation, and facilitate the implementation of different key spraying maintenance methods. By presetting and continuously updating adjustment parameters, the microcrack prediction program can be continuously corrected.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel maintenance, and in particular to an intelligent spraying maintenance system for a tunnel secondary lining based on real-time scanning of micro-cracks. Background Art

[0002] After construction, the concrete walls in the tunnel need to be sprayed at irregular intervals and in irregular quantities due to the influence of temperature and humidity to avoid problems such as cracking of the wall. Generally, manual pushing devices or direct use of water pipes for spraying are used, or automated spraying devices are used to spray and maintain the tunnel secondary lining.

[0003] The current spraying device can only spray the surface inside the tunnel evenly. When the stress and dryness in different parts of the tunnel are different, the microcracks in the tunnel are unevenly distributed and the degree of cracking is different. Focused spraying maintenance is required for microcracks of different degrees to prevent the deterioration of the crack distribution in the tunnel. Therefore, how to evaluate the microcracks and focus on spraying maintenance is a technical problem that technical personnel in this field need to solve. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent spraying maintenance system for the secondary lining of a tunnel based on real-time scanning of microcracks, which solves the problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent spray maintenance system for tunnel secondary lining based on real-time scanning of microcracks, comprising a scanning unit, a track platform, a processing unit, a spray module, and a robotic arm. The scanning unit includes a laser module and a vision module. The output ends of the laser module and the vision module are both connected to the input end of the processing unit. The port of the track platform establishes communication with the port of the processing unit. The output end of the processing unit is respectively connected to the input end of the spray module and the input end of the robotic arm.

[0006] The track platform is a suspended track car, which is installed on the track laid on the top surface of the tunnel. The suspended track car is driven by an internal motor to move on the track. The visual module includes three image sensors, and the three image sensors are oriented horizontally to the left, horizontally to the right, and vertically downward along the track direction. The three image sensors are used to obtain image information of the area where the track platform is located and transmit it to the processing unit. The laser module includes three infrared laser scanners, and the three infrared laser scanners are oriented horizontally to the left, horizontally to the right, and vertically downward along the track direction. The three infrared laser scanners are used to obtain depth information of the area where the track platform is located and transmit it to the processing unit. The spray module includes a water tank, a water pump, and an atomizing nozzle. The water tank, the water pump, and the atomizing nozzle are connected by a water pipe. The water pump draws water from the water tank and sprays it outward through the atomizing nozzle. The robotic arm is a six-axis robotic arm, and the atomizing nozzle is fixed to the end of the robotic arm. The scanning unit, spray module, processing unit, and robotic arm are all installed at the bottom of the track platform. When the track platform moves on the track in the tunnel, it drives the robotic arm, scanning unit, and spray module to move synchronously.

[0007] The processing unit executes a first scanning program to obtain a spatial model of the tunnel, executes a microcrack analysis program to obtain the coordinates of all microcracks in the spatial model, outputs the coordinates of all microcracks as a report for staff to review, and the staff goes to the tunnel to manually evaluate all microcracks based on the coordinates of the microcracks. The manual evaluation results are divided into three categories: mild, ordinary, and severe. The staff makes subjective evaluations and judgments based on the density, length, and depth of the microcracks. The manual evaluation scope includes microcracks not discovered by the microcrack analysis program. The staff uses a marker graphic to replace the evaluation result and pastes the marker graphic on the top of all microcracks. The processing unit executes a second scanning program to obtain the evaluation results of all microcracks. The processing unit executes a microcrack prediction program to obtain the spray point Pst and the spray amount Q. The processing unit controls the track platform, the robotic arm, and the spray module according to the spray point Pst and the spray amount Q to perform spray maintenance on all microcracks in the tunnel.

[0008] After the spray module completes spray maintenance on all microcracks, the processing unit executes the microcrack analysis program again after a fixed interval of 12 hours to obtain the newly added microcrack coordinates. The processing unit updates the preset adjustment parameters fix according to the newly added microcrack coordinates. The processing unit then executes the microcrack prediction program and subsequent spray maintenance according to the updated adjustment parameters fix.

[0009] Furthermore, when the first scanning program is executed, the processing unit sends scanning instructions to the laser module and the vision module respectively, and the processing unit sends a displacement instruction to the track platform. After receiving the displacement instruction, the track platform starts the motor to drive itself to move at a constant speed along the track in the tunnel;

[0010] When the track platform starts to move, the three image sensors of the vision module acquire the image information of the tunnel in real time and transmit it to the processing unit, and the three infrared laser scanners acquire the depth information of the tunnel in real time and transmit it to the processing unit;

[0011] A displacement encoder is installed inside the track platform. The displacement encoder records the displacement distance of the track platform in real time. The track platform transmits its own displacement distance to the processing unit. The processing unit establishes a spatial coordinate system. The processing unit marks the starting point of the track platform's movement as the origin of the spatial coordinate system, marks the track in the tunnel as the x-axis of the spatial coordinate system, marks the width of the tunnel as the y-axis of the spatial coordinate system, and marks the height of the tunnel as the z-axis of the spatial coordinate system. The unit length of the spatial coordinate system is meter. The length of the track in the tunnel is obtained by the displacement distance of the track platform, and the width and height of the tunnel are obtained from the depth information.

[0012] The processing unit stitches the image information from the three image sensors to obtain a complete image model of the tunnel. The processing unit stitches the depth information from the three infrared laser scanners to obtain a complete depth model of the tunnel. The processing unit aligns and overlaps the image modules and the depth model and inputs them into a spatial coordinate system to obtain a spatial model of the tunnel.

[0013] When the track platform moves on the track inside the tunnel, the processing unit controls the end of the robotic arm to make reciprocating arc movements left and right. At the same time, the processing unit controls the spray module to spray the secondary lining surface inside the tunnel as the end of the robotic arm moves. When the processing unit obtains a complete spatial model of the tunnel, the spray module completes a comprehensive spraying of the secondary lining surface inside the tunnel, realizing preliminary maintenance of the tunnel secondary lining and facilitating subsequent focused spraying maintenance of microcracks.

[0014] Furthermore, when the microcrack analysis program is executed, the processing unit converts all pixels in the image information into grayscale pixels. The processing unit calculates the grayscale value Grey of each pixel according to the formula Grey = Red × 0.299 + Green × 0.587 + Blue × 0.114. The grayscale value Grey ranges from 0 to 255, where Red is the red channel value of the pixel, Green is the green channel value of the pixel, and Blue is the blue channel value of the pixel.

[0015] The processing unit counts the mode of the grayscale values Grey of all grayscale pixels, and marks all grayscale pixels with a grayscale value Grey within ±10% of the mode as background. The mode of the grayscale values Grey of the grayscale pixels represents the grayscale value Grey that appears the most times. The mode is the background color of the image information. It is necessary to filter out the background color before the processing unit identifies microcracks in the image information to improve the recognition speed of microcracks. The image information is affected by the brightness and darkness in the tunnel, and the recognition of the background is likely to produce errors. Therefore, the grayscale value Grey marking range of the background is expanded to improve the error tolerance rate of background recognition.

[0016] The processing unit removes all grayscale pixels marked as background in the image information, and subtracts grayscale pixels with grayscale values less than 50 from adjacent pixels to obtain adjacent pixel differences. When the adjacent pixel difference between the grayscale pixel with grayscale value less than 50 and the adjacent pixel is less than or equal to 10, the processing unit connects the grayscale pixel with grayscale value less than 50 and the adjacent pixel. When the adjacent pixel difference between the grayscale pixel with grayscale value less than 50 and the adjacent pixel is greater than 10, the processing unit disconnects the two pixels. After the processing unit completes calculating the adjacent pixel differences between all grayscale pixels with grayscale values less than 50 and the adjacent pixels, the processing unit marks the continuously connected grayscale pixels as visual cracks.

[0017] The processing unit aligns and overlaps all the depth information with the image information, and establishes a depth curve graph. The vertical axis of the depth curve graph is the depth information, and the horizontal axis is the displacement distance of the track platform. The processing unit inputs the depth information corresponding to the visual crack in the image information into the depth curve graph to obtain the depth curve at the visual crack. The processing unit takes two adjacent points A (p1, q1) and B (p2, q2) in the depth curve, where p1 and p2 are the displacement distances of the track platform, and q1 and q2 are the depth information. The processing unit calculates the depth curve according to the formula Calculate the slope k between points A and B. When the slope k is ≥ 0.75, the processing unit determines that the depth curve trend is steeply rising or falling, indicating that the depth information at the visual crack fluctuates greatly and a real crack exists. The processing unit marks the visual crack with a steeply rising or falling depth curve trend as a microcrack.

[0018] The processing unit obtains the displacement distance of the track platform at the microcrack and marks it as length X. The processing unit marks the depth information obtained by the infrared laser scanner facing horizontally to the left or horizontally to the right at the microcrack as width Y. When the microcrack is located on the left side of the forward direction of the track platform, the processing unit uses the infrared laser scanner facing horizontally to the left. When the microcrack is located on the right side of the forward direction of the track platform, the processing unit uses the infrared laser scanner facing horizontally to the right. The processing unit marks the depth information obtained by the infrared laser scanner facing vertically downward at the microcrack as height Z. The processing unit binds the length X, width Y and height Z and records them as the coordinates of the microcrack.

[0019] Furthermore, the sign graphics corresponding to the manual evaluation results are circle, triangle and square respectively, and the sign graphics are all filled with red to increase the contrast with the tunnel background color, making it easier for the processing unit to identify;

[0020] During the second scanning procedure, the processing unit sends a displacement command to the track platform. After receiving the displacement command, the track platform starts the motor to drive itself to move at a constant speed along the track in the tunnel. When the track platform starts to move, the processing unit obtains image information from the three image sensors of the vision module. The processing unit extracts the red pixels in the image information. The red channel value of the red pixel is 255, the green channel value is 0, and the blue channel value is 0. The processing unit marks the clustered red pixels as the recognition target.

[0021] The processing unit scans the edge of the recognition target. When the edge of the recognition target is a continuous arc without corners, the processing unit will mark the recognition target as a circular sign graphic, and the corresponding microcrack assessment result is mild. When the edge of the recognition target is a straight line and has three corners, the processing unit will mark the recognition target as a triangular sign graphic, and the corresponding microcrack assessment result is ordinary. When the edge of the recognition target is a straight line and has four corners, the processing unit will mark the recognition target as a square sign graphic, and the corresponding microcrack assessment result is severe.

[0022] Furthermore, when the microcrack prediction program is executed, the processing unit obtains all microcrack tip connection lines in the image information as reference lines, calculates a first angle θ1 between the reference line and the horizontal direction, and calculates a second angle θ2 between the reference line and the vertical direction, θ1 and θ2 satisfy the condition θ1+θ2=90°, and presets a reference angle θ3. The processing unit compares the first angle θ1 and the second angle θ2 of the microcrack reference line. If θ1<θ2, then θ3=θ1; if θ2<θ1, then θ3=θ2; and if θ1=θ2, then θ3=θ1=θ2.

[0023] The processing unit counts the number of pixels Wpix arranged perpendicular to the reference line of each microcrack in the image information, where the number of pixels pix represents the quantized width of the microcrack. The processing unit calculates the reference line pixel length Lpix of each microcrack in the image information. The processing unit calculates the maximum depth D of each microcrack in the depth information.

[0024] The processing unit presets weight coefficients w1, w2, and w3, and the weight coefficients w1, w2, and w3 satisfy the condition w1+w2+w3=1. The specific values of the weight coefficients w1, w2, and w3 are determined according to the number of microcracks in the tunnel. The adjustment parameter fix is preset, and the initial values of the adjustment parameter fix are 0.8, 0.5, and 0.3, respectively corresponding to slight, ordinary, and severe microcracks;

[0025] The evaluation result is slight micro cracks, and the analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcracks. The evaluation result is a common microcrack. The analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcracks. If the evaluation result is severe microcracks, the analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcrack, where Pst(θ) is the angle between the spray point Pst and the midpoint of the reference line, and Pst(L) is the distance between the spray point Pst and the midpoint of the reference line. The microcrack prediction program stops.

[0026] The update process of the adjustment parameter fix is as follows:

[0027] The processing unit calculates the distance Dn between the newly added microcrack coordinates and the spray point Pst. If the value of the distance Dn is equal to or greater than the length of the original microcrack reference line, it means that the prediction is deviated and the effect of the spray curing is not obvious. The processing unit will adjust the initial value of the parameter fix down by a value of 0.01. Conversely, if the value of the distance Dn is less than the length of the original microcrack reference line, it means that the prediction is more accurate and the effect of the spray curing is obvious. The processing unit will adjust the initial value of the parameter fix up by a value of 0.01.

[0028] The present invention has the following beneficial effects:

[0029] 1. The automatic scanning of the scanning unit can quickly locate the coordinates of microcracks, avoiding manual investigation. Microcracks can be classified through manual evaluation, which facilitates the implementation of different key spray maintenance methods and prevents the deterioration of crack distribution in the tunnel.

[0030] 2. By presetting and updating the adjustment parameters, the micro-crack prediction program can be continuously corrected, and the effect of key spray maintenance can be continuously optimized.

[0031] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 This is a block diagram of the intelligent spraying maintenance system for the tunnel secondary lining based on real-time scanning of microcracks according to the present invention. DETAILED DESCRIPTION

[0034] 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 any creative efforts shall fall within the scope of protection of the present invention.

[0035] See also Figure 1 The present invention provides a technical solution: an intelligent spray maintenance system for tunnel secondary lining based on real-time scanning of microcracks, comprising a scanning unit, a track platform, a processing unit, a spray module and a robotic arm. The scanning unit comprises a laser module and a vision module. The output ends of the laser module and the vision module are both connected to the input end of the processing unit. The port of the track platform establishes communication with the port of the processing unit. The output end of the processing unit is respectively connected to the input end of the spray module and the input end of the robotic arm.

[0036] The track platform is a suspended track vehicle, which is installed on the track laid on the top surface of the tunnel. The suspended track vehicle is driven by an internal motor to move on the track. The vision module includes three image sensors, which are oriented horizontally to the left, horizontally to the right, and vertically downward along the track direction. The three image sensors are used to obtain image information of the area where the track platform is located and transmit it to the processing unit. The laser module includes three infrared laser scanners, which are oriented horizontally to the left, horizontally to the right, and vertically downward along the track direction. The three infrared laser scanners are used to obtain depth information of the area where the track platform is located and transmit it to the processing unit. The spray module includes a water tank, a water pump, and an atomizing nozzle. The water tank, water pump, and atomizing nozzle are connected by a water pipe. The water pump draws water from the water tank and sprays it outward through the atomizing nozzle. The robotic arm is a six-axis robotic arm, and the atomizing nozzle is fixed to the end of the robotic arm. The scanning unit, spray module, processing unit, and robotic arm are all installed at the bottom of the track platform. When the track platform moves on the track in the tunnel, it will drive the robotic arm, scanning unit, and spray module to move synchronously.

[0037] The processing unit executes a first scanning program to obtain a spatial model of the tunnel, executes a microcrack analysis program to obtain the coordinates of all microcracks in the spatial model, outputs the coordinates of all microcracks as a report for staff to review, and the staff goes to the tunnel to manually evaluate all microcracks based on the coordinates of the microcracks. The manual evaluation results are divided into three categories: mild, ordinary, and severe. The staff makes subjective evaluations and judgments based on the density, length, and depth of the microcracks. The manual evaluation scope includes microcracks not discovered by the microcrack analysis program. The staff uses a marker graphic to replace the evaluation result and pastes the marker graphic on the top of all microcracks. The processing unit executes a second scanning program to obtain the evaluation results of all microcracks. The processing unit executes a microcrack prediction program to obtain the spray point Pst and the spray amount Q. The processing unit controls the track platform, the robotic arm, and the spray module according to the spray point Pst and the spray amount Q to perform spray maintenance on all microcracks in the tunnel.

[0038] After the spray module completes spray maintenance on all microcracks, the processing unit executes the microcrack analysis program again after a fixed interval of 12 hours to obtain the newly added microcrack coordinates. The processing unit updates the preset adjustment parameters fix according to the newly added microcrack coordinates. The processing unit then executes the microcrack prediction program and subsequent spray maintenance according to the updated adjustment parameters fix.

[0039] When the first scanning program is executed, the processing unit sends scanning instructions to the laser module and the vision module respectively, and the processing unit sends a displacement instruction to the track platform. After receiving the displacement instruction, the track platform starts the motor to drive itself to move at a constant speed along the track in the tunnel;

[0040] When the track platform starts to move, the three image sensors of the vision module acquire the image information of the tunnel in real time and transmit it to the processing unit, and the three infrared laser scanners acquire the depth information of the tunnel in real time and transmit it to the processing unit;

[0041] A displacement encoder is installed inside the track platform. The displacement encoder records the displacement distance of the track platform in real time. The track platform transmits its own displacement distance to the processing unit. The processing unit establishes a spatial coordinate system. The processing unit marks the starting point of the track platform's movement as the origin of the spatial coordinate system, marks the track in the tunnel as the x-axis of the spatial coordinate system, marks the width of the tunnel as the y-axis of the spatial coordinate system, and marks the height of the tunnel as the z-axis of the spatial coordinate system. The unit length of the spatial coordinate system is meter. The length of the track in the tunnel is obtained by the displacement distance of the track platform, and the width and height of the tunnel are obtained from the depth information.

[0042] The processing unit stitches the image information from the three image sensors to obtain a complete image model of the tunnel. The processing unit stitches the depth information from the three infrared laser scanners to obtain a complete depth model of the tunnel. The processing unit aligns and overlaps the image modules and the depth model and inputs them into a spatial coordinate system to obtain a spatial model of the tunnel.

[0043] When the track platform moves on the track inside the tunnel, the processing unit controls the end of the robotic arm to make reciprocating arc movements left and right. At the same time, the processing unit controls the spray module to spray the secondary lining surface inside the tunnel as the end of the robotic arm moves. When the processing unit obtains a complete spatial model of the tunnel, the spray module completes a comprehensive spraying of the secondary lining surface inside the tunnel, realizing preliminary maintenance of the tunnel secondary lining and facilitating subsequent focused spraying maintenance of microcracks.

[0044] When the microcrack analysis program is executed, the processing unit converts all pixels in the image information into grayscale pixels. The processing unit calculates the grayscale value Grey of each pixel according to the formula Grey = Red × 0.299 + Green × 0.587 + Blue × 0.114. The grayscale value Grey ranges from 0 to 255, where Red is the red channel value of the pixel, Green is the green channel value of the pixel, and Blue is the blue channel value of the pixel.

[0045] The processing unit counts the mode of the grayscale values Grey of all grayscale pixels, and marks all grayscale pixels with a grayscale value Grey within ±10% of the mode as background. The mode of the grayscale values Grey of the grayscale pixels represents the grayscale value Grey that appears the most times. The mode is the background color of the image information. It is necessary to filter out the background color before the processing unit identifies microcracks in the image information to improve the recognition speed of microcracks. The image information is affected by the brightness and darkness in the tunnel, and the recognition of the background is likely to produce errors. Therefore, the grayscale value Grey marking range of the background is expanded to improve the error tolerance rate of background recognition.

[0046] The processing unit removes all grayscale pixels marked as background in the image information, and subtracts grayscale pixels with grayscale values less than 50 from adjacent pixels to obtain adjacent pixel differences. When the adjacent pixel difference between the grayscale pixel with grayscale value less than 50 and the adjacent pixel is less than or equal to 10, the processing unit connects the grayscale pixel with grayscale value less than 50 and the adjacent pixel. When the adjacent pixel difference between the grayscale pixel with grayscale value less than 50 and the adjacent pixel is greater than 10, the processing unit disconnects the two pixels. After the processing unit completes calculating the adjacent pixel differences between all grayscale pixels with grayscale values less than 50 and the adjacent pixels, the processing unit marks the continuously connected grayscale pixels as visual cracks.

[0047] The processing unit aligns and overlaps all the depth information with the image information, and establishes a depth curve graph. The vertical axis of the depth curve graph is the depth information, and the horizontal axis is the displacement distance of the track platform. The processing unit inputs the depth information corresponding to the visual crack in the image information into the depth curve graph to obtain the depth curve at the visual crack. The processing unit takes two adjacent points A (p1, q1) and B (p2, q2) in the depth curve, where p1 and p2 are the displacement distances of the track platform, and q1 and q2 are the depth information. The processing unit calculates the depth curve according to the formula Calculate the slope k between points A and B. When the slope k is ≥ 0.75, the processing unit determines that the depth curve trend is steeply rising or falling, indicating that the depth information at the visual crack fluctuates greatly and a real crack exists. The processing unit marks the visual crack with a steeply rising or falling depth curve trend as a microcrack.

[0048] The processing unit obtains the displacement distance of the track platform at the microcrack and marks it as length X. The processing unit marks the depth information obtained by the infrared laser scanner facing horizontally to the left or horizontally to the right at the microcrack as width Y. When the microcrack is located on the left side of the forward direction of the track platform, the processing unit uses the infrared laser scanner facing horizontally to the left. When the microcrack is located on the right side of the forward direction of the track platform, the processing unit uses the infrared laser scanner facing horizontally to the right. The processing unit marks the depth information obtained by the infrared laser scanner facing vertically downward at the microcrack as height Z. The processing unit binds the length X, width Y and height Z and records them as the coordinates of the microcrack.

[0049] The sign graphics corresponding to the manual assessment results are circle, triangle, and square, respectively. The sign graphics are all filled with red to increase the contrast with the tunnel background color and facilitate recognition by the processing unit.

[0050] During the second scanning procedure, the processing unit sends a displacement command to the track platform. After receiving the displacement command, the track platform starts the motor to drive itself to move at a constant speed along the track in the tunnel. When the track platform starts to move, the processing unit obtains image information from the three image sensors of the vision module. The processing unit extracts the red pixels in the image information. The red channel value of the red pixel is 255, the green channel value is 0, and the blue channel value is 0. The processing unit marks the clustered red pixels as the recognition target.

[0051] The processing unit scans the edge of the recognition target. When the edge of the recognition target is a continuous arc without corners, the processing unit will mark the recognition target as a circular sign graphic, and the corresponding microcrack assessment result is mild. When the edge of the recognition target is a straight line and has three corners, the processing unit will mark the recognition target as a triangular sign graphic, and the corresponding microcrack assessment result is ordinary. When the edge of the recognition target is a straight line and has four corners, the processing unit will mark the recognition target as a square sign graphic, and the corresponding microcrack assessment result is severe.

[0052] When the microcrack prediction program is executed, the processing unit obtains all microcrack tip connection lines in the image information as reference lines, calculates a first angle θ1 between the reference line and the horizontal direction, and calculates a second angle θ2 between the reference line and the vertical direction. θ1 and θ2 satisfy the condition θ1+θ2=90°. The processing unit presets a reference angle θ3. The processing unit compares the first angle θ1 and the second angle θ2 of the microcrack reference line. If θ1<θ2, then θ3=θ1; if θ2<θ1, then θ3=θ2; if θ1=θ2, then θ3=θ1=θ2.

[0053] The processing unit counts the number of pixels Wpix arranged perpendicular to the reference line of each microcrack in the image information, where the number of pixels pix represents the quantized width of the microcrack. The processing unit calculates the reference line pixel length Lpix of each microcrack in the image information. The processing unit calculates the maximum depth D of each microcrack in the depth information.

[0054] The processing unit presets weight coefficients w1, w2, and w3, and the weight coefficients w1, w2, and w3 satisfy the condition w1+w2+w3=1. The specific values of the weight coefficients w1, w2, and w3 are determined according to the number of microcracks in the tunnel. The adjustment parameter fix is preset, and the initial values of the adjustment parameter fix are 0.8, 0.5, and 0.3, respectively corresponding to slight, ordinary, and severe microcracks;

[0055] The evaluation result is slight micro cracks, and the analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcracks. The evaluation result is a common microcrack. The analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcracks. If the evaluation result is severe microcracks, the analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcrack, where Pst(θ) is the angle between the spray point Pst and the midpoint of the reference line, and Pst(L) is the distance between the spray point Pst and the midpoint of the reference line. The microcrack prediction program stops.

[0056] The update process of the adjustment parameter fix is as follows:

[0057] The processing unit calculates the distance Dn between the newly added microcrack coordinates and the spray point Pst. If the value of the distance Dn is equal to or greater than the length of the original microcrack reference line, it means that the prediction is deviated and the effect of the spray curing is not obvious. The processing unit will adjust the initial value of the parameter fix down by a value of 0.01. Conversely, if the value of the distance Dn is less than the length of the original microcrack reference line, it means that the prediction is more accurate and the effect of the spray curing is obvious. The processing unit will adjust the initial value of the parameter fix up by a value of 0.01.

[0058] The above are only preferred specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An intelligent spray maintenance system for tunnel secondary linings based on real-time microcrack scanning, comprising a scanning unit, a track platform, a processing unit, a spray module, and a robotic arm. The scanning unit includes a laser module and a vision module, the outputs of which are both connected to the input of the processing unit. A port on the track platform communicates with a port on the processing unit, and the output of the processing unit is connected to the inputs of the spray module and the robotic arm, respectively. Characterized by: The track platform is a suspended track vehicle, which is installed on the track laid on the top surface of the tunnel and is driven by an internal motor to move on the track. The vision module includes three image sensors, which are used to obtain image information of the area where the track platform is located and transmit it to the processing unit. The laser module includes three infrared laser scanners, which are used to obtain depth information of the area where the track platform is located and transmit it to the processing unit. The spray module includes a water tank, a water pump and an atomizing nozzle, and the atomizing nozzle is fixed to the end of the robotic arm. The scanning unit, spray module, processing unit and robotic arm are all installed at the bottom of the track platform. When the track platform moves on the track in the tunnel, it drives the robotic arm, scanning unit and spray module to move synchronously. The processing unit executes a first scanning program to obtain a spatial model of the tunnel, executes a microcrack analysis program to obtain the coordinates of all microcracks in the spatial model, and manually evaluates all microcracks, including those not discovered by the microcrack analysis program. Workers use a marker graphic to replace the evaluation results and affix the marker graphic to the top of all microcracks. A second scanning program is executed to obtain the evaluation results of all microcracks. A microcrack prediction program is executed to obtain the spray point Pst and spray volume Q. Based on the spray point Pst and spray volume Q, the track platform, robotic arm, and spray module are controlled to perform spray maintenance on all microcracks in the tunnel. After the spray module completes spray curing on all microcracks, the processing unit executes the microcrack analysis program again after a fixed interval to obtain the newly added microcrack coordinates, updates the preset adjustment parameters fix according to the newly added microcrack coordinates, and then executes the microcrack prediction program and subsequent spray curing according to the updated adjustment parameters fix; When the microcrack prediction program is executed, the processing unit obtains the connection line of all microcrack tips in the image information as a reference line, calculates the first angle θ1 between the reference line and the horizontal direction, and calculates the second angle θ2 between the reference line and the vertical direction. θ1 and θ2 satisfy the condition θ1+θ2=90°. A reference angle θ3 is preset. The first angle θ1 and the second angle θ2 of the microcrack reference line are compared. If θ1<θ2, then θ3=θ1; if θ2<θ1, then θ3=θ2; if θ1=θ2, then θ3=θ1=θ2; The processing unit counts the number of pixels arranged perpendicular to the reference line of each microcrack in the image information, Wpix, calculates the reference line pixel length Lpix of each microcrack in the image information, and calculates the maximum depth D of each microcrack in the depth information; The processing unit presets weight coefficients w1, w2, and w3, and the weight coefficients w1, w2, and w3 satisfy the condition w1+w2+w3=1. The specific values of the weight coefficients w1, w2, and w3 are determined according to the number of microcracks in the tunnel. The adjustment parameter fix is preset, and the initial values of the adjustment parameter fix are 0.8, 0.5, and 0.3, respectively corresponding to slight, ordinary, and severe microcracks; The evaluation result is slight micro cracks, and the analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcracks. The evaluation result is a common microcrack. The analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcracks. If the evaluation result is severe microcracks, the analysis unit is based on the formula Calculate the spray point Pst and spray volume Q of the microcrack, where Pst(θ) is the angle between the spray point Pst and the midpoint of the reference line, and Pst(L) is the distance between the spray point Pst and the midpoint of the reference line. The microcrack prediction program stops. The update process of the adjustment parameter fix is as follows: The processing unit calculates the distance Dn between the newly added microcrack coordinates and the spray point Pst. If the value of the distance Dn is equal to or greater than the length of the microcrack reference line, the initial value of the adjustment parameter fix is adjusted down by one value. Conversely, if the value of the distance Dn is less than the length of the microcrack reference line, the initial value of the adjustment parameter fix is adjusted up by one value.

2. The tunnel secondary lining intelligent spraying maintenance system based on real-time micro-crack scanning according to claim 1 is characterized in that: When the first scanning program is executed, the processing unit sends scanning instructions to the laser module and the vision module respectively, and the processing unit sends a displacement instruction to the track platform. After receiving the displacement instruction, the track platform starts the motor to drive itself to move at a constant speed along the track in the tunnel; When the track platform starts to move, the three image sensors of the vision module acquire the image information of the tunnel in real time and transmit it to the processing unit, and the three infrared laser scanners acquire the depth information of the tunnel in real time and transmit it to the processing unit; A displacement encoder is installed inside the track platform. The displacement encoder records the displacement distance of the track platform in real time. The track platform transmits its own displacement distance to the processing unit to establish a spatial coordinate system. The starting point of the track platform's movement is marked as the origin of the spatial coordinate system. The track in the tunnel is marked as the x-axis of the spatial coordinate system, the width of the tunnel is marked as the y-axis of the spatial coordinate system, and the height of the tunnel is marked as the z-axis of the spatial coordinate system. The unit length of the spatial coordinate system is meter. The processing unit stitches the image information from the three image sensors to obtain a complete image model of the tunnel, stitches the depth information from the three infrared laser scanners to obtain a complete depth model of the tunnel, aligns and overlaps the image modules and depth models, and inputs them into a spatial coordinate system to obtain a spatial model of the tunnel; When the track platform moves on the track inside the tunnel, the processing unit controls the end of the robotic arm to make reciprocating arc movements left and right, and at the same time controls the spray module to spray the secondary lining surface inside the tunnel as the end of the robotic arm moves. When the processing unit obtains a complete spatial model of the tunnel, the spray module completes a comprehensive spraying of the secondary lining surface inside the tunnel.

3. The tunnel secondary lining intelligent spraying maintenance system based on real-time micro-crack scanning according to claim 1 is characterized in that: When the microcrack analysis program is executed, the processing unit converts all pixels in the image information into grayscale pixels and calculates the grayscale value Grey of each pixel according to the formula Grey = Red × 0.299 + Green × 0.587 + Blue × 0.

114. The grayscale value Grey ranges from 0 to 255, where Red is the red channel value of the pixel, Green is the green channel value of the pixel, and Blue is the blue channel value of the pixel. Count the mode of all grayscale image pixels in the grayscale value Grey, and mark the grayscale image pixels with grayscale values Grey within the range of ±10% of the mode as background; All grayscale pixels marked as background in the image information are removed. The processing unit subtracts grayscale pixels with a grayscale value less than 50 from adjacent pixels to obtain adjacent pixel differences. When the adjacent pixel difference is less than or equal to 10, the two pixels are connected. When the adjacent pixel difference is greater than 10, the two pixels are disconnected. After all adjacent pixel differences are calculated, the continuously connected grayscale pixels are marked as visual cracks. The processing unit aligns and overlaps all the depth information with the image information to establish a depth curve graph. The vertical axis of the depth curve graph is the depth information, and the horizontal axis is the displacement distance of the track platform. The depth information corresponding to the visual crack in the image information is input into the depth curve graph to obtain the depth curve at the visual crack. Take two adjacent points A (p1, q1) and B (p2, q2) in the depth curve, where p1 and p2 are the displacement distances of the track platform, and q1 and q2 are the depth information. According to the formula Calculate the slope k between point A and point B. When the slope k is ≥ 0.75, determine whether the depth curve has a steep rise or fall trend. Mark the visual cracks with a steep rise or fall trend as microcracks. The processing unit obtains the displacement distance of the track platform at the microcrack and marks it as length X, marks the depth information obtained by the infrared laser scanner facing horizontally to the left or horizontally to the right at the microcrack as width Y, and marks the depth information obtained by the infrared laser scanner facing vertically downward at the microcrack as height Z. The length X, width Y and height Z are bound and recorded as the coordinates of the microcrack.

4. The tunnel secondary lining intelligent spraying maintenance system based on real-time microcrack scanning according to claim 1 is characterized in that: The symbol graphics corresponding to the manual evaluation results are circle, triangle and square respectively, and the filling color of the symbol graphics is red; During the second scanning process, the processing unit sends a displacement command to the track platform. After receiving the displacement command, the track platform starts the motor to drive itself to move at a constant speed along the track in the tunnel. When the track platform starts to move, it obtains image information from the three image sensors of the vision module, extracts the red pixels in the image information, and marks the clustered red pixels as the recognition target. The processing unit scans the edge of the identified target. When the edge of the identified target is a continuous arc with no corners, the identified target is marked as a circular sign graphic, and the corresponding microcrack assessment result is mild. When the edge of the identified target is a straight line and has three corners, the identified target is marked as a triangular sign graphic, and the corresponding microcrack assessment result is ordinary. When the edge of the identified target is a straight line and has four corners, the identified target is marked as a square sign graphic, and the corresponding microcrack assessment result is severe.

Images