Tunnel initial spraying concrete spraying quality detection method based on visual technology

Abstract

The invention relates to the technical field of tunnel construction quality detection, in particular to a tunnel initial spraying concrete spraying quality detection method based on a visual technology, which comprises the following steps: S1, arranging an automatic cleaning device at the front end of equipment through multi-modal sensor fusion and a self-adaptive exposure denoising algorithm in combination with a multi-information joint correction technology, and performing multi-modal sensor fusion and self-adaptive exposure denoising; through original point positioning calibration, high-precision robust acquisition of three-dimensional coordinates and apparent vector data of the spraying and mixing surface in a complex environment is carried out. Through multi-modal sensor fusion, anti-interference processing and accurate calibration, high-precision robust acquisition of the spraying and mixing surface data in a complex tunnel environment is ensured, a reliable data basis is provided for subsequent detection and control, the spraying and mixing surface flatness control precision is effectively improved, the material loss rate is reduced, and the working efficiency is improved. And the strategy can be adaptively adjusted according to geological conditions and construction states, and the construction efficiency and safety are both considered.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of tunnel construction quality detection, in particular to a tunnel initial concrete spraying quality detection method based on visual technology. BACKGROUND

[0002] The initial concrete spraying of a tunnel is a key process in the initial support link of tunnel construction, refers to spraying a layer of concrete to the surface of surrounding rock for the first time after tunnel excavation, so as to timely close the surrounding rock, prevent rock weathering and peeling, stabilize the working face (excavation working face) and provide a basis for the subsequent support structure. The construction quality directly affects the stability of the initial support of the tunnel, the safety of the subsequent secondary lining structure and the construction quality of the waterproof layer, and is an important link for guaranteeing the safety and structural durability of tunnel construction. However, in the prior art, in actual construction, the initial concrete spraying of a tunnel is long-term dependent on manual sampling due to complex environment, resulting in low detection efficiency, poor precision and inability to monitor the construction process in real time, further causing problems such as difficult control of over-spraying and under-spraying amount, easy invasion of the initial support into the secondary lining, repeated and inefficient construction and quality hidden dangers of the waterproof layer.

[0003] Based on this, the application provides a tunnel initial concrete spraying quality detection method based on visual technology to solve the above technical problems. SUMMARY

[0004] The application aims to provide a tunnel initial concrete spraying quality detection method based on visual technology. The multi-modal sensor fusion, anti-interference processing and precise calibration of the application ensure high-precision robust collection of spraying surface data in complex tunnel environments, provide reliable data basis for subsequent detection and control, and construct a three-dimensional model by means of artificial intelligence algorithm fusion of multi-source information and dynamically optimize spraying parameters, realize self-adaptive adaptation to complex geological conditions and intelligent iteration of construction strategies, realize linkage adjustment of nozzle position and parameters through predictive control and multi-objective optimization, take into account construction quality, efficiency and safety, effectively improve spraying surface flatness control precision, reduce material loss rate, and can adaptively adjust strategies according to geological conditions and construction state, taking into account construction efficiency and safety.

[0005] To achieve the above purpose, the application provides the following technical scheme:

[0006] The application provides a tunnel initial concrete spraying quality detection method based on visual technology, comprising the following steps:

[0007] S1: Through multi-modal sensor fusion and adaptive exposure denoising algorithm, combined with various information joint correction technology, an automatic cleaning device is arranged at the front end of the equipment, and through origin positioning calibration, high-precision robust collection of three-dimensional coordinate and apparent vector data of the spraying surface in complex environments is carried out.

[0008] S2: Based on image processing algorithms, integrate laser scanning, intelligent data processing and real-time monitoring technology to detect flatness and over-limit areas;

[0009] S3: Based on artificial intelligence self-learning data fusion and parameter optimization model, automatically identify key features in multi-angle visual data, fuse laser and image information, build high-precision three-dimensional spray mixing surface model, analyze the influence of spray distance, angle, pressure and speed parameters on spray mixing surface flatness, and dynamically optimize key construction parameters such as spray distance, angle and speed through reinforcement learning algorithm;

[0010] S4: According to the analysis results of S3, based on predictive control algorithm and multi-objective optimization control to dynamically coordinate and adjust the position and parameters of the spray head.

[0011] The specific steps in S1 are as follows:

[0012] S1.1: Capture three-dimensional coordinate and apparent vector original data of spray mixing surface through multi-sensor fusion of laser and vision;

[0013] S1.2: Adopt adaptive exposure denoising algorithm and automatic cleaning device to eliminate environmental interference;

[0014] S1.3: Correct and calibrate the origin through multiple information joint correction and origin positioning.

[0015] The specific steps of using adaptive exposure denoising algorithm and automatic cleaning device in S1.2 to eliminate environmental interference are as follows:

[0016] S1.2.1: Real-time acquisition of dust concentration and light intensity in the tunnel through dust sensor and light sensor, when dust concentration > 50mg / m 3 or light intensity < 300lux, trigger anti-interference mechanism;

[0017] S1.2.2: Based on dust concentration, control cleaning frequency:

[0018] ① When the concentration is 50-100mg / m 3 , start the rotating brush combined with high-pressure air flow cleaning sensor surface every 5 minutes;

[0019] ② When the concentration is > 100mg / m 3 , start continuous trigger cleaning;

[0020] S1.2.3: For low-light environment, use adaptive exposure adjustment, and perform multi-frame superposition average denoising algorithm on collected images, continuously collect 3-5 frames of images, and eliminate random noise through weighted average of pixel gray value;

[0021] S1.2.4: Time axis calibration is performed on the subsequent collected data according to the response delay of the sensor after cleaning.

[0022] The specific steps in S2 are as follows:

[0023] S2.1: Dynamic acquisition of the flatness and surface morphology detail data of the sprayed surface by laser scanning technology;

[0024] S2.2: Analysis of the collected data using image processing algorithms to identify the out-of-limit area and determine the warning level;

[0025] S2.3: Real-time display of the monitoring results through an intuitive interface to issue immediate warning prompts to the construction personnel for the out-of-limit state.

[0026] The specific steps in S3 are as follows:

[0027] S3.1: Fusion of multi-view vision and laser information, automatic extraction of key features of the sprayed surface and construction of a three-dimensional model;

[0028] S3.2: Analysis of the influence of parameters such as spraying distance, angle, pressure, and speed on flatness, and establishment of a correlation model;

[0029] S3.3: Dynamic optimization of spraying parameters and generation of construction adjustment schemes based on self-learning and reinforcement learning algorithms.

[0030] In S3.1, multi-view vision and laser information are fused to automatically extract key features of the sprayed surface and construct a three-dimensional model, with the specific steps as follows:

[0031] S3.1.1: Distortion correction and gray scale normalization processing of multi-view vision images, and simultaneous denoising and filtering of laser point cloud data;

[0032] S3.1.2: Identification of common feature points in vision images and laser point clouds through feature point matching algorithms, and establishment of spatial coordinate mapping relationships for multi-source data;

[0033] S3.1.3: Fusion of texture information from vision images and depth information from laser point clouds based on the mapping relationship, extraction of key features such as the boundary of concave and convex regions and flatness mutation points of the sprayed surface;

[0034] S3.1.4: Grid division of the fused three-dimensional point cloud data using the Poisson surface reconstruction algorithm, generation of a three-dimensional model of the sprayed surface with texture information, and model resolution set to 500-800 vertices per cubic meter.

[0035] In S3.3, dynamic optimization of spraying parameters and generation of construction adjustment schemes based on self-learning and reinforcement learning algorithms, with the specific steps as follows:

[0036] S3.3.1: Construct the state space of reinforcement learning, including the parameters of spray mixing surface flatness, spray distance, angle, speed, pressure, and geological type label;

[0037] S3.3.2: Define the action space, including the adjustment range and adjustment step of spray distance, angle, and speed;

[0038] S3.3.3: Set the reward function, with the optimization targets of spray flatness compliance rate, material utilization rate, and construction efficiency, and the reward function is expressed as:

[0039] R = w1 flatness compliance rate + w2 material utilization rate + w3 construction efficiency

[0040] Where w1, w2, and w3 are weighting coefficients, satisfying w1 + w2 + w3 = 1;

[0041] S3.3.4: Train the optimization model using PPO algorithm, and continuously adjust the spray parameter strategy through interaction with the environment;

[0042] S3.3.5: Output the optimal spray parameter combination, including spray distance, angle, and speed, to guide construction adjustment;

[0043] S3.3.6: The model continuously receives new data and updates online for self-learning optimization of the spray strategy.

[0044] The specific steps in S4 are as follows:

[0045] S4.1: Receive the optimization parameters and adjustment instructions output by S3;

[0046] S4.2: Based on the predictive control algorithm, real-time adjust the pose parameters of the distance between the spray head and the rock surface and the spray angle;

[0047] S4.3: Through multi-objective optimization control, the spray head pose and spray parameters are adjusted in linkage.

[0048] The specific steps of S4.2 based on the predictive control algorithm to real-time adjust the pose parameters of the distance between the spray head and the rock surface and the spray angle are as follows:

[0049] S4.2.1: Establish a dynamic prediction model of the spray head pose and spray parameters, input the current spray head position, spray angle, rock surface distance, and spray mixing surface flatness feedback information;

[0050] S4.2.2: Based on the prediction model, rollingly calculate the future N time step changes of the spray head pose and spray parameters;

[0051] S4.2.3: Set the objective function, with the minimum spray error and control energy as the target, and the objective function is expressed as:

[0052]

[0053] wherein e k is the injection error of the kth step, Δu k is the control variation, Q, R are weighting matrices;

[0054] S4.2.4: Obtain the optimal control sequence by solving the optimization problem, and select the optimal control output at the current time to the actuator;

[0055] S4.2.5: Update the model state according to the actual feedback error and return it to S3.3.6 in real time through the OPC-UA protocol.

[0056] In S4.3, the nozzle pose and injection parameters are adjusted through multi-objective optimization control, and the specific operation is as follows:

[0057] S4.3.1: Establish a three-objective optimization model including construction quality, efficiency and cost:

[0058] ① Quality target: flatness deviation Δh≤3mm;

[0059] ② Efficiency target: injection speed v≥1.8m 2 / min;

[0060] ③ Cost target: material loss rate η≤5%;

[0061] S4.3.2: Solve the Pareto optimal solution set by using the improved NSGA-III algorithm, wherein:

[0062] ① The population size is set to 100, and the iteration number is ≥50 generations;

[0063] ② Add nozzle mechanical limiting constraint for tunnel construction scene;

[0064] ③ Adopt dynamic reference point mechanism to adapt to different surrounding rock grades;

[0065] S4.3.3: Select the final parameter combination from the Pareto front through fuzzy decision, and preferentially meet:

[0066] ① Class IV surrounding rock: quality target weight 0.7;

[0067] ② Class V surrounding rock: safety target weight 0.6 for initial support thickness standard rate ≥95%;

[0068] S4.3.4: When the rock mass displacement rate is >2mm / h, automatically switch to the conservative injection mode.

[0069] Compared with the prior art, the beneficial effects of the present application are:

[0070] The present application ensures high-precision robust collection of the sprayed mixing surface data under complex tunnel environment through multi-modal sensor fusion, anti-interference processing and precise calibration, provides reliable data basis for subsequent detection and control, and constructs a three-dimensional model by means of artificial intelligence algorithm fusion of multi-source information and dynamically optimizes the spraying parameters, realizes self-adaptive adaptation to complex geological conditions and intelligent iteration of construction strategies, realizes linkage adjustment of the nozzle position and parameters through predictive control and multi-objective optimization, and takes into account the construction quality, efficiency and safety, effectively improves the sprayed mixing surface flatness control precision, reduces the material loss rate, and can adaptively adjust the strategy according to the geological conditions and construction state, and takes into account the construction efficiency and safety. BRIEF DESCRIPTION OF DRAWINGS

[0071] Fig. 1 The flowchart of the tunnel initial spraying concrete spraying quality detection method based on visual technology according to the present application.

[0072] Fig. 2 The overall architecture diagram of the tunnel initial spraying concrete spraying quality detection method based on visual technology according to the present application.

[0073] Fig. 3 The multi-target collaborative control flowchart in the tunnel initial spraying concrete spraying quality detection method based on visual technology according to the present application. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0075] Embodiment:

[0076] As Figs. 1-3As shown, the embodiment provides a tunnel initial concrete spraying quality detection method based on visual technology, including the following steps: S1: through multi-modal sensor fusion and adaptive exposure denoising algorithm, combined with multi-information joint correction technology, an automatic cleaning device is arranged at the front end of the equipment, through origin positioning calibration, high-precision robust collection of three-dimensional coordinates and apparent vector data of the sprayed concrete surface in complex environment is carried out; S2: based on image processing algorithm, integrating laser scanning, intelligent data processing and real-time monitoring technology, flatness and over-limit area are detected; S3: based on artificial intelligence self-learning data fusion and parameter optimization model, key features in multi-view visual data are automatically identified, laser and image information are fused, a high-precision three-dimensional sprayed concrete surface model is constructed, the influence law of spraying distance, angle, pressure and speed parameters on the flatness of the sprayed concrete surface is analyzed, and the key construction parameters of spraying distance, angle and speed are dynamically optimized through reinforcement learning algorithm; S4: according to the analysis result of S3, based on predictive control algorithm and multi-objective optimization control, the dynamic cooperative adjustment of nozzle pose and spraying parameters is carried out.

[0077] In the embodiment, it also needs to be explained that the specific steps in S1 are as follows: S1.1, through multi-sensor fusion of laser and vision, the three-dimensional coordinate and apparent vector original data of the sprayed concrete surface are captured; S1.2, adaptive exposure denoising algorithm and automatic cleaning device are adopted to eliminate environmental interference; the specific steps are as follows: S1.2.1: through real-time collection of dust concentration and light intensity in the tunnel by dust sensor and light sensor, when the dust concentration > 50 mg / m 3 and the light intensity < 300 lux, the anti-interference mechanism is triggered; S1.2.2: based on dust concentration grading control of cleaning frequency: ① when the concentration is 50-100 mg / m 3 , the rotating brush combined with high-pressure air flow cleaning sensor surface is started every 5 minutes; ② when the concentration > 100 mg / m 3 , continuous trigger type cleaning is started; S1.2.3: adaptive exposure adjustment is adopted for low light environment, and multi-frame superposition average denoising algorithm is executed on the collected images, 3-5 frames of images are continuously collected, and random noise is eliminated through weighted average of pixel gray value; S1.2.4: according to the response delay of the sensor after cleaning, the time axis of the subsequent collected data is calibrated. S1.3: through multi-information joint correction and origin positioning calibration.

[0078] Further, it needs to be pointed out that the laser wavelength range is 850nm, the visual sensor adopts a back-illuminated CMOS sensor, ISO is greater than or equal to 51200, and the synchronization mechanism of the "multi-sensor fusion" adopts a timestamp synchronization with an error less than or equal to 1m. The "multi-information joint correction" adopts a Bundle Adjustment algorithm assisted by a calibration board to synchronously optimize the internal and external parameters of the laser radar and the camera, and the re-projection error is controlled within ±0.5 pixels. The specific information types (such as laser point cloud, visual image, and inertial navigation data) of the "multi-information joint correction", and the origin coordinate of the "origin positioning calibration" is the center point of the tunnel face as the origin.

[0079] In the present embodiment, it also needs to be pointed out that the specific steps in S2 are as follows: S2.1: dynamically acquiring the spraying and mixing surface flatness and surface morphology detail data by laser scanning technology; S2.2: analyzing the collected data by using an image processing algorithm, identifying the out-of-limit area and determining the warning level; S2.3: real-time displaying the monitoring results through an intuitive interface and issuing an instant warning prompt to the construction personnel for the out-of-limit state.

[0080] Further, it needs to be pointed out that the determination standard of the "out-of-limit area" is that the flatness deviation is greater than 5mm, and the "warning level" is divided according to the following basis: first-level warning: deviation 5-10mm; second-level warning: deviation >10mm.

[0081] In this embodiment, it should also be noted that the specific steps in S3 are as follows: S3.1: Fuse multi-view visual and laser information, automatically extract key features of the sprayed surface and construct a three-dimensional model; the specific steps are as follows: S3.1.1: Perform distortion correction and grayscale normalization processing on the multi-view visual images, and simultaneously perform noise reduction filtering on the laser point cloud data; S3.1.2: Identify common feature points in the visual images and laser point clouds through feature point matching algorithms, and establish a spatial coordinate mapping relationship between the multi-source data; S3.1.3: Based on the mapping relationship, fuse the texture information of the visual images with the depth information of the laser point clouds, and extract key features of the concave and convex area boundaries and flatness change points of the sprayed surface; S3.1.4: Use the Poisson surface reconstruction algorithm to perform mesh division on the fused three-dimensional point cloud data, generate a three-dimensional model of the sprayed surface with texture information, and set the model resolution to contain 500-800 vertices per cubic meter. S3.2: Analyze the influence of spraying distance, angle, pressure, and speed parameters on smoothness and establish a correlation model; S3.3: Based on self-learning and reinforcement learning algorithms, dynamically optimize spraying parameters and generate construction adjustment plans. Specific steps are as follows: S3.3.1: Construct the state space for reinforcement learning, including parameters for surface smoothness, spraying distance, angle, speed, and pressure, as well as geological type labels; S3.3.2: Define the action space, including the adjustment range and step size for spraying distance, angle, and speed; S3.3.3: Set a reward function, with the smoothness compliance rate, material utilization rate, and construction efficiency as optimization objectives. The reward function is expressed as:

[0082] R = w1·flatness compliance rate + w2·material utilization rate + w3·construction efficiency

[0083] Where w1, w2, and w3 are weighting coefficients, satisfying w1+w2+w3=1; S3.3.4: The PPO algorithm is used to train and optimize the model, and the spraying parameter strategy is continuously adjusted through interaction with the environment; S3.3.5: The optimal combination of spraying parameters, including spraying distance, angle, and speed, is output to guide construction adjustments; S3.3.6: The model continuously receives new data and updates online to perform self-learning optimization of the spraying strategy.

[0084] Furthermore, it should be noted that S3.1.2 uses an improved ORB feature descriptor for matching, and feature point pairs are considered valid matches when the distance is less than 0.8 times the Hamming distance threshold. Geological type labels include coal seam interlayers, karst, and fault fracture zones.

[0085] In this embodiment, it also needs to be explained that the specific steps in S4 are as follows: S4.1: receiving the optimization parameters and adjustment instructions output by S3; S4.2: adjusting the pose parameters of the distance between the nozzle and the rock surface and the spraying angle in real time based on the predictive control algorithm; the specific steps are as follows: S4.2.1: establishing a dynamic prediction model of the nozzle pose and the spraying parameter, inputting the current nozzle position, spraying angle, rock surface distance, and spraying plane flatness feedback information; S4.2.2: based on the prediction model, rolling calculating the change trend of the nozzle pose and the spraying parameter in the future N time steps; S4.2.3: setting a target function, taking minimizing the spraying error and the control energy as the goal, and the target function is expressed as:

[0086]

[0087] Wherein, e k is the spraying error of the kth step, Δu k is the control amount change, Q and R are weighting matrices; S4.2.4: by solving the optimization problem, the optimal control sequence is obtained, and the current optimal control amount is output to the actuator; S4.2.5: according to the actual feedback error, the model state is updated and returned to S3.3.6 in real time through OPC-UA protocol. S4.3: through multi-objective optimization control, the nozzle pose and the spraying parameter are adjusted. The specific operation is as follows: S4.3.1: a three-objective optimization model containing construction quality, efficiency, and cost is established: ① quality target: flatness deviation Δh≤3mm; ② efficiency target: spraying speed v≥1.8m2 / min; ③ cost target: material loss rate η≤5%; S4.3.2: the improved NSGA-III algorithm is used to solve the Pareto optimal solution set, wherein: ① the population size is set to 100, and the iteration number is ≥50 generations; ② for the tunnel construction scene, the nozzle mechanical limiting constraint is added; ③ the dynamic reference point mechanism is adopted to adapt to different surrounding rock grades; S4.3.3: the final parameter combination is selected from the Pareto frontier through fuzzy decision, and the following is prioritized: ① for grade IV surrounding rock: the quality target weight is 0.7; ② for grade V surrounding rock: the safety target weight of the initial support thickness compliance rate ≥95% is 0.6; S4.3.4: when the rock mass displacement rate is >2mm / h, the conservative spraying mode is automatically switched to.

[0088] Further, it needs to be explained that the dynamic prediction model in S4.2.1 is a state space model: Wherein, the state vector contains position, angle, speed, etc. w k and v k are Gaussian noise. The specific rules of "fuzzy decision" in S4.3.3 are as follows: when the flatness deviation is <3mm and the material loss rate is <5%, the efficiency parameter is prioritized.

[0089] In this embodiment, a method for detecting the initial shotcrete spraying quality in tunnels based on vision technology is described as follows: First, through multi-sensor fusion of laser and back-illuminated CMOS vision sensors, the original data of the three-dimensional coordinates and apparent vectors of the sprayed surface are captured synchronously with timestamps. This is combined with an automatic cleaning device (controlling the cleaning frequency according to dust concentration levels) and an adaptive exposure denoising algorithm to eliminate environmental interference. Then, the data is processed by Bundle... The Adjustment algorithm, combining laser point cloud correction, visual images, and inertial navigation data, completes positioning and calibration with the tunnel face center point as the origin, achieving high-precision and robust data acquisition in complex environments. Next, it dynamically acquires the smoothness data of the sprayed surface through laser scanning, using image processing algorithms to identify areas with smoothness deviations >5mm and classifying them into warning levels based on deviations of 5-10mm (Level 1) and >10mm (Level 2). The results are displayed and warnings are issued in real-time through an intuitive interface. Subsequently, multi-view visual and laser information are fused, and a textured 3D model is constructed through distortion correction and feature point matching. The influence of spraying parameters on smoothness is analyzed, and spraying parameters are optimized based on reinforcement learning and the PPO algorithm, generating a construction adjustment plan that is continuously updated through self-learning. Finally, the optimized parameters are received, and the nozzle pose is adjusted in real-time based on a predictive control algorithm (state-space model). An improved NSGA-III algorithm is used to achieve high quality (Δh≤3mm) and efficiency (v≥1.8m). 2 Multi-objective linkage control with parameters such as per minute and cost (η≤5%) is implemented. Differentiated weight allocation is applied to Class IV / V surrounding rock. When the rock mass displacement is >2mm / h, the system switches to conservative mode, and the control feedback is transmitted back to the optimization model via the OPC-UA protocol.

[0090] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0091] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for detecting the initial shotcrete spraying quality in tunnels based on vision technology, characterized in that, Includes the following steps: S1: By using multimodal sensor fusion and adaptive exposure denoising algorithm, combined with multiple information joint correction technology, an automatic cleaning device is set up at the front end of the equipment. Through origin positioning calibration, high-precision and robust acquisition of three-dimensional coordinates and apparent vector data of the sprayed surface in complex environments is achieved. S2: Based on image processing algorithms, it integrates laser scanning, intelligent data processing and real-time monitoring technologies to detect flatness and out-of-limit areas; S3: An AI-based self-learning data fusion and parameter optimization model that automatically identifies key features in multi-view visual data, fuses laser and image information, constructs a high-precision three-dimensional sprayed surface model, analyzes the influence of parameters such as spraying distance, angle, pressure, and speed on the smoothness of the sprayed surface, and dynamically optimizes key construction parameters such as spraying distance, angle, and speed through reinforcement learning algorithms. S4: Based on the analysis results of S3, dynamic and coordinated adjustment of nozzle pose and injection parameters is carried out based on predictive control algorithm and multi-objective optimization control.

2. The method for detecting the initial shotcrete spraying quality in tunnels based on vision technology according to claim 1, characterized in that, The specific steps in S1 are as follows: S1.1: Capture the original data of the three-dimensional coordinates and apparent vectors of the sprayed surface through multi-sensor fusion of laser and vision. S1.2: Adaptive exposure denoising algorithm and automatic cleaning device are used to eliminate environmental interference; S1.3: Correction and origin positioning calibration through joint correction of multiple information sources.

3. The method for detecting the initial shotcrete quality in tunnels based on vision technology according to claim 2, characterized in that, In step S1.2, an adaptive exposure denoising algorithm and an automatic cleaning device are used to eliminate environmental interference. The specific steps are as follows: S1.2.1: Real-time collection of dust concentration and light intensity inside the tunnel using dust sensors and light sensors; when dust concentration > 50 mg / m³ 3 Or, when the light intensity is <300 lux, the anti-interference mechanism is triggered; S1.2.2: Controlling cleaning frequency based on dust concentration levels: ① Concentration 50-100 mg / m³ 3 At that time, the rotating brush is activated every 5 minutes to clean the sensor surface with high-pressure airflow; ② Concentration > 100 mg / m³ 3 At that time, continuous trigger cleaning is initiated; S1.2.3: Adaptive exposure adjustment is adopted for low-light environments, and a multi-frame superposition averaging denoising algorithm is executed on the acquired images. 3-5 frames of images are acquired continuously, and random noise is eliminated by weighted averaging of pixel gray values. S1.2.4: Based on the response delay of the sensor after cleaning, perform time axis calibration on the subsequent acquired data.

4. The method for detecting the initial shotcrete quality in tunnels based on vision technology according to claim 1, characterized in that, The specific steps in S2 are as follows: S2.1: Dynamically acquire data on the flatness and surface morphology details of the sprayed surface using laser scanning technology; S2.2: Use image processing algorithms to analyze the collected data, identify areas exceeding limits, and determine the warning level; S2.3: The monitoring results are displayed in real time through an intuitive interface, and the construction personnel are given immediate warnings when the limits are exceeded.

5. The method for detecting the initial shotcrete spraying quality in tunnels based on vision technology according to claim 1, characterized in that, The specific steps in S3 are as follows: S3.1: Integrates multi-view visual and laser information to automatically extract key features of the sprayed surface and construct a 3D model; S3.2: Analyze the influence of parameters such as spray distance, angle, pressure, and speed on smoothness, and establish a correlation model; S3.3: Based on self-learning and reinforcement learning algorithms, dynamically optimize spraying parameters and generate construction adjustment plans.

6. The method for detecting the initial shotcrete spraying quality in tunnels based on vision technology according to claim 5, characterized in that, In step S3.1, multi-view visual and laser information are integrated to automatically extract key features of the sprayed surface and construct a 3D model. The specific steps are as follows: S3.1.1: Perform distortion correction and grayscale normalization on multi-view visual images, and simultaneously perform noise reduction filtering on laser point cloud data; S3.1.2: Identify common feature points in visual images and laser point clouds using a feature point matching algorithm, and establish a spatial coordinate mapping relationship between multi-source data; S3.1.3: Based on the mapping relationship, the texture information of the visual image is fused with the depth information of the laser point cloud to extract the key features of the concave and convex regions and the abrupt change points of the smoothness of the sprayed surface. S3.1.4: The Poisson surface reconstruction algorithm is used to divide the fused 3D point cloud data into meshes to generate a sprayed surface 3D model with texture information. The model resolution is set to contain 500-800 vertices per cubic meter.

7. The method for detecting the initial shotcrete spraying quality in tunnels based on vision technology according to claim 5, characterized in that, In step S3.3, the spraying parameters are dynamically optimized and a construction adjustment plan is generated based on self-learning and reinforcement learning algorithms. The specific steps are as follows: S3.3.1: Construct the state space for reinforcement learning, including parameters such as surface smoothness, spraying distance, angle, velocity, and pressure, as well as geological type labels; S3.3.2: Define the action space, including the adjustment range and adjustment step size of the injection distance, angle, and speed; S3.3.3: Define a reward function with the following optimization objectives: spraying smoothness compliance rate, material utilization rate, and construction efficiency. The reward function is expressed as follows: R = w1·flatness compliance rate + w2·material utilization rate + w3·construction efficiency Among them, w1, w2, and w3 are weighting coefficients, satisfying w1 + w2 + w3 = 1; S3.3.4: The PPO algorithm is used to train and optimize the model, and the injection parameter strategy is continuously adjusted through interaction with the environment; S3.3.5: Outputs the optimal combination of spraying parameters, including spraying distance, angle, and speed, to guide construction adjustments; S3.3.6: The model continuously receives new data and updates online, performing self-learning optimization of the spraying strategy.

8. The method for detecting the initial shotcrete spraying quality in tunnels based on vision technology according to claim 1, characterized in that, The specific steps in S4 are as follows: S4.1: Receive the optimization parameters and adjustment instructions output by S3; S4.2: Based on predictive control algorithms, the positional parameters of the nozzle's distance from the rock surface and the spray angle are adjusted in real time; S4.3: Through multi-objective optimization control, the nozzle position and spray parameters are adjusted in a coordinated manner.

9. A method for detecting the quality of initial shotcrete spraying in tunnels based on vision technology according to claim 8, characterized in that, In step S4.2, the pose parameters of the nozzle distance and spray angle are adjusted in real time based on the predictive control algorithm. The specific steps are as follows: S4.2.1: Establish a dynamic prediction model for nozzle position and spray parameters, and input feedback information such as current nozzle position, spray angle, rock surface distance, and spray surface smoothness; S4.2.2: Based on the prediction model, the trend of nozzle pose and injection parameters over the next N time steps is calculated in a rolling manner; S4.2.3: Define the objective function, with the goal of minimizing injection error and control energy. The objective function is expressed as follows: Among them, e k Let Δu be the injection error at step k. k To control the changes in the quantity, Q and R are weighted matrices; S4.2.4: By solving the optimization problem, the optimal control sequence is obtained, and the optimal control quantity at the current moment is selected and output to the actuator; S4.2.5: Update the model state based on the actual feedback error and transmit it back to S3.3.6 in real time via the OPC-UA protocol.

10. A method for detecting the quality of initial shotcrete spraying in tunnels based on vision technology according to claim 8, characterized in that, In S4.3, multi-objective optimization control is used to adjust the nozzle pose and injection parameters in a coordinated manner. The specific operation is as follows: S4.3.1: Establish a three-objective optimization model that includes construction quality, efficiency, and cost: ① Quality target: Flatness deviation Δh ≤ 3mm; ② Efficiency target: injection speed v ≥ 1.8m 2 / min; ③ Cost target: Material loss rate η≤5%; S4.3.2: The improved NSGA-III algorithm is used to solve for the Pareto optimal solution set, where: ① Set the population size to 100 and the number of iterations to ≥50 generations; ②For tunnel construction scenarios, add mechanical limit constraints for the nozzles; ③ Adopting a dynamic reference point mechanism to adapt to different surrounding rock grades; S4.3.3: Select the final parameter combination from the Pareto front using fuzzy decision-making, prioritizing the following: ① Class IV surrounding rock: Quality target weight 0.7; ② Class V surrounding rock: The safety target weight for initial support thickness compliance rate ≥ 95% is 0.6; S4.3.4: When the rock mass displacement rate is detected to be >2mm / h, automatically switch to conservative spraying mode.

Images