A method for repairing a shield cutter ring system by laser cladding

Abstract

The application discloses a kind of repair shield cutter ring system using laser cladding method, comprising: scanning module: the digital model topography of the cutter ring to be repaired is obtained by scanning the cutter ring to be repaired;Information acquisition module: the digital model topography of the cutter ring to be repaired scanned is compared with the complete cutter ring digital model of the same size in system library, and the digital model of the repair area is obtained by reverse recovery;Operation module: according to the digital model of the repair area, the machining parameters are obtained by inputting the ideal machining result parameters into BP neural network;Cladding repair module: according to the machining parameters obtained by operation module, the machining repair is completed.The application has potential wide application prospect in the maintenance of shield cutter ring and other components, can prolong the service life of components and improve the reliability of equipment.

Description

Technical Field

[0001] This invention relates to the field of laser cladding technology, and in particular to a method for repairing the cutterhead ring system of a tunnel boring machine using laser cladding. Background Technology

[0002] As the core of the shield tunneling method, tunnel boring machines (TBMs) are commonly used in the construction of underground transportation or large tunnels. The cutterheads, responsible for breaking rock, act like "teeth," cutting and compressing hard rock. Damage to the H13 steel cutterheads directly affects the progress and efficiency of TBM construction. Replaced cutterheads are often scrapped, and some with remanufacturing value are simply discarded, leading to significant resource waste and high construction costs. With technological advancements, remanufacturing technology has gradually developed and been applied to various industrial sectors. Remanufacturing reduces the environmental impact of products by extending their lifespan rather than replacing parts. Therefore, remanufacturing and repairing damaged cutterheads and reusing them in construction can not only reduce construction costs but also minimize waste.

[0003] Laser-based remanufacturing is a novel remanufacturing technology that utilizes reverse engineering and powder additive manufacturing techniques to regenerate damaged components. Its core lies in repairing damaged components using laser additive manufacturing technology. As a type of laser additive manufacturing, laser cladding (LC) technology has significant advantages in repairing damage to core components. Characterized by high laser energy density and precise thermal control, it achieves rapid and efficient heating and cooling, reducing thermal impact and deformation, making it an ideal choice for component repair manufacturing. However, research on cladding operations on tunnel boring machine cutterheads is scarce. Summary of the Invention

[0004] To address the above problems, this invention provides a method for repairing the cutterhead ring system of a tunnel boring machine using laser cladding.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for repairing a tunnel boring machine cutterhead ring system using laser cladding includes:

[0007] Scanning module: Scans the tool ring to be repaired to obtain a digital model of the tool ring's morphology;

[0008] Information acquisition module: retrieves a complete digital model of the same size cutter ring from the system library and compares it with the scanned digital model of the cutter ring to be repaired, and performs reverse reconstruction to obtain a digital model of the area to be repaired;

[0009] The computation module: Based on the digital model of the area to be repaired, it inputs the ideal processing result parameters into the BP neural network to obtain the processing parameters;

[0010] Cladding Repair Module: Completes the processing repair based on the processing parameters obtained from the calculation module.

[0011] Furthermore: the scanning module includes:

[0012] A fixed bracket is provided, on which a first motor is fixed. A connecting plate is fixedly connected to the power output end of the first motor. A second motor is fixedly connected to one side of the connecting plate. A gear is connected to the power output end of the second motor. The gear meshes with one side of an arc-shaped rack. A scanner is fixed to one end of the rack.

[0013] Furthermore, a pulley is fixed to the connecting plate, and the rack is mounted on the pulley on the other side.

[0014] Furthermore: the cladding repair module includes:

[0015] Four columns, and a gear rack slide on each column, wherein a retainer and a guide shaft are provided between two gear rack slides, and two side plates are also included. A servo motor is fixed on the two side plates. The output end of the servo motor is mounted on the retainer via a roller. A support bearing is also included. The support bearing is fixed on the side plate and passes through the guide shaft.

[0016] A retainer and a guide shaft are provided between the two side plates. The system also includes a gantry frame, on which a servo motor is fixed. The output end of the servo motor is mounted on the retainer via a roller. A support bearing is also fixed on the gantry frame, and the guide shaft passes through the support bearing. The system further includes a first laser head bracket, which is fixedly connected to the gantry frame. A servo motor is fixedly mounted on the first laser head bracket, and its output end is connected to a first steering connecting block. A connecting block is fixedly mounted on the first steering connecting block. A second laser head bracket is fixedly mounted on one side of the connecting block, and a servo motor is fixedly mounted on the second laser head bracket. The output end of the servo motor is connected to a second steering connecting block, and the second steering connecting block is connected to a laser cladding structure.

[0017] Furthermore, it also includes a base, the fixed bracket and the four columns are fixed on the base, a guide rail and a ball screw are provided in the base, and an operating table is also included. The ball screw passes through the operating table and is connected to it. The guide rail is embedded in the operating table, and a three-jaw chuck is provided on the operating table.

[0018] The technological advancements achieved by this invention compared to existing technologies are as follows:

[0019] This invention obtains the digital model morphology of the cutterhead to be repaired through a scanning module. The information acquisition module retrieves a complete digital model of the same size cutterhead from the system library and compares it with the scanned model. Reverse engineering is then performed to obtain the digital model of the area to be repaired. This invention utilizes reverse engineering technology to obtain a three-dimensional digital model of the damaged cutterhead, providing an accurate model basis for subsequent laser cladding repair. This effectively repairs damage and improves the lifespan and efficiency of the cutter. This invention has broad potential applications in the maintenance of components such as tunnel boring machine cutterheads, extending component lifespan and improving equipment reliability. Beyond laser cladding repair, this invention also has wide potential applications in other fields requiring automatic parameter matching, such as material processing and manufacturing processes. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0021] In the attached diagram:

[0022] Figure 1 This is a structural diagram of the entire invention;

[0023] Figure 2 This is a right view of the entire invention;

[0024] Figure 3 This is a structural diagram of the cladding repair module of the present invention;

[0025] Figure 4 This is a top view of the entire invention;

[0026] Figure 5 This is a flowchart of the process for obtaining the model to be repaired in this invention;

[0027] Figure 6 A flowchart illustrating the operation of the computation module of this invention;

[0028] Figure 7 This is a flowchart of the backpropagation of input parameters by the BP neural network of this invention;

[0029] Figure 8 This is a schematic diagram of the microstructure of the repaired broken blade ring according to the present invention.

[0030] In the picture:

[0031] 1-Fixed bracket; 2-First motor; 3-Connecting plate; 4-Second motor; 5-Gear; 6-Rack; 7-Scanner; 8-Pulley; 9-Column; 10-Gear and rack slide; 11-Cage; 12-Guide rail shaft; 13-Side plate; 14-Servo motor; 15-Roller; 16-Support bearing; 17-Gantry frame; 18-First laser head bracket; 19-First steering connecting block; 20-Second laser head bracket; 21-Second steering connecting block; 22-Base; 23-Guide rail; 24-Ball screw; 25-Operating table; 26-Three-jaw chuck; 27-Cutter ring; 28-Display; 29-Laser cladding structure; 30-Connecting block. Detailed Implementation

[0032] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0033] This invention discloses a method for repairing a shield tunnel cutterhead ring system using laser cladding, comprising:

[0034] Scanning module: Scans the tool ring to be repaired to obtain a digital model of the tool ring's morphology;

[0035] Information acquisition module: retrieves a complete digital model of the same size cutter ring from the system library and compares it with the scanned digital model of the cutter ring to be repaired, and performs reverse reconstruction to obtain a digital model of the area to be repaired;

[0036] The computation module: Based on the digital model of the area to be repaired, it inputs the ideal processing result parameters into the BP neural network to obtain the processing parameters;

[0037] Cladding Repair Module: Completes the processing repair based on the processing parameters obtained from the calculation module.

[0038] Specifically, refer to Figures 1 to 4 This embodiment uses a 17-inch single-edged damaged cutterhead ring of a tunnel boring machine as an experimental model for repair experiments. The substrate material for the single-pass cladding experiment is H13 mold steel, with dimensions of 120mm × 100mm × 10mm. Before conducting the laser cladding test, the test substrate and the surface of the cutterhead ring 27 were polished and rinsed with acetone to ensure processing quality. The powder material is H13 steel, and spherical powder with a particle size of 50-70μm was prepared using the plasma rotating electrode method.

[0039] This invention includes a base 22, within which a guide rail 23 and a ball screw are disposed, and an operating table 25, through which the ball screw passes and connects. The guide rail 23 is embedded in the operating table 25, and a three-jaw chuck 26 is provided on the operating table 25. Figure 1As shown, the scanning module includes a fixed bracket 1, on which a first motor 2 is fixed. The power output end of the first motor 2 is fixedly connected to a connecting plate 3. A second motor 4 is fixedly connected to one side of the connecting plate 3. The power output end of the second motor 4 is connected to a gear 5. The gear 5 meshes with one side of an arc-shaped rack 6. A scanner 7 is fixed to one end of the rack 6. A pulley 8 is fixed to the connecting plate 3. The other side of the rack 6 is mounted on the pulley 8.

[0040] After cleaning and polishing, the blade ring 27 first enters the scanning and recognition module for scanning. The ball screw 24 drives the operating table 25 to move the three-jaw chuck 26 to the scanning module, and fixes the blade ring 27 on the three-jaw chuck 26. The blade ring 27 moves to the bottom of the scanning module, and the second motor 4 drives the lower rack 6 to extend and retract. The second motor 4 drives the rack 6 to rotate, completing a 360° scan. In this embodiment, the position of the scanner 7 is precisely controlled by the PLC / microcontroller. The morphology of the scanned digital model is displayed on the display 28. By touching the display 28, the missing parts are identified and scanned multiple times to finally obtain a complete digital model.

[0041] The information collection module includes:

[0042] The flowchart for obtaining the model to be repaired is as follows: Figure 5 As shown, the point cloud of the cutter ring 27 is obtained using scanner 7. To ensure the accuracy of the point cloud, the surface of the cutter ring 27 can be cleaned before scanning. The morphology of the complete digital model of the cutter ring 27 of the same size in the system library is compared with that of the scanned digital model of the cutter ring 27 to be repaired. By reverse engineering the measurement points, the original point cloud map of the cutter ring 27 is generated. Then, the original point cloud is further processed to construct the final CAD model of the damaged cutter ring. The processing includes steps such as setting up reference points, creating a new measurement series, acquiring surface 3D data, establishing the shear plane, data stitching processing, defect cross-section sheeting, volume deviation detection, and deviation verification. Finally, the broken tooth model is obtained in the CAD software through solid Boolean operations, which is the final CAD model of the damaged cutter ring. The broken tooth model is then imported into the calculation module.

[0043] The computing module includes:

[0044] like Figure 6 As shown, the calculation module performs the following steps based on the broken tooth model:

[0045] Step 1: Define the input layer and the output layer. The input layer sets an input node for each parameter (dilution rate, aspect ratio, microhardness), and the output layer sets the output nodes to laser power, scanning speed, and powder feeding speed.

[0046] Step 2: Collect a dataset containing various parameter combinations, including tag data for laser power, scanning speed, and powder feeding speed.

[0047] Step 3: Standardize the input and output parameters to ensure they are within a similar range of values, in order to improve training effectiveness.

[0048] Step 4: Train the BP neural network using the dataset to learn the relationship between the input parameters and the output parameters.

[0049] Step 5: For any input parameter, enable the BP neural network to infer the other two parameters based on the known parameters.

[0050] Step 6: Input the three parameters into the BP neural network to obtain the output of laser power, scanning speed, and powder feeding speed.

[0051] Specifically, step 1 includes:

[0052] In this step, the structure of the neural network needs to be determined, including the number of nodes in the input and output layers. In this embodiment, there are three input parameters (dilution rate, aspect ratio, and microhardness) and three output parameters (laser power, scanning speed, and powder feeding speed). Therefore, the BP neural network structure is as follows:

[0053] Input layer:

[0054] Node 1: Dilution rate

[0055] Node 2: Aspect Ratio

[0056] Node 3: Microhardness

[0057] Output layer:

[0058] Node 1: Laser Power

[0059] Node 2: Scanning speed

[0060] Node 3: Powder delivery speed

[0061] The input layer uses x1, x2, and x3 to represent dilution rate, aspect ratio, and microhardness, respectively. The input layer's a... (1) The output is represented as:

[0062] a (1) =[x1,x2,x3]

[0063] The output layer uses y1, y2, and y3 to represent laser power, scanning speed, and powder feeding speed, respectively, and the output a of the output layer is... (2) Represented as:

[0064] a (2) =[y1,y2,y3]

[0065] Use W (1) Let b represent the weight matrix from the input layer to the hidden layer. (1)W represents the bias vector of the hidden layer. (2) b represents the weight matrix from the hidden layer to the output layer. (2) Represents the bias vector of the output layer:

[0066] z (1) =W (1) ·a (1) ·b (1)

[0067] a (1) =a(z (1) )

[0068] z (2) =W (2) ·a (2) ·b (2)

[0069] a (2) =σ(z) (2) )

[0070] Where σ represents the activation function, and in this embodiment, the tanh function is used.

[0071] The mean squared error loss function L is used to measure the difference between the output and the true value:

[0072]

[0073] Where y is the actual output. is the output of the neural network, and n is the number of output nodes.

[0074] Specifically, step 2 includes:

[0075] In this step, it is necessary to collect and prepare the dataset, ensuring that the data includes various parameter combinations and corresponding tag data for laser power, scanning speed, and powder feeding speed. The specific implementation steps are as follows:

[0076] Define a dataset D, where each sample is represented as (x1,x2,x3,y1,y2,y3), including dilution rate, aspect ratio, microhardness, and corresponding laser power, scanning speed, and powder feeding speed.

[0077] A large number of real samples were collected, covering different dilution rates, aspect ratios, and microhardness values ​​to ensure uniform sample distribution and improve the generalization ability of the neural network.

[0078] Simulation tools were used to simulate the laser cladding repair process, and the laser power, scanning speed, and powder feeding speed labels for each sample were obtained.

[0079] The input parameters x1, x2, x3 and the output parameters y1, y2, y3 are standardized and scaled to a similar numerical range to improve training performance.

[0080] The dataset is divided into training, validation, and test sets using an 80-10-10 split to ensure sufficient validation and test data during training. The expression is as follows:

[0081]

[0082] Where i represents the index of the sample, x1, x2, x3 are the input parameters, and y1, y2, y3 are the output parameters. This represents the k-th input parameter of the i-th sample. This represents the k-th input parameter of the i-th sample.

[0083] This step establishes a dataset containing various parameter combinations, ensuring the comprehensiveness and representativeness of the data. This is the foundational data needed to train neural networks and learn the relationship between input and output parameters.

[0084] Specifically, step 3 includes:

[0085] In this step, the input and output parameters are standardized to ensure they are within a similar numerical range, which helps improve the training performance of the neural network. The specific implementation steps are as follows:

[0086] Standardize each input parameter using the mean (μ) k ) and standard deviation (σ) k The calculation formula is:

[0087]

[0088] Where k represents the specific input parameter, and i represents the index of the sample. The standardized input parameter x of the i-th sample. k .

[0089] Record the mean and standard deviation of each input parameter so that new data can be standardized in the same way when applying the model later.

[0090] For each output parameter y k To standardize, using the same mean and standard deviation, the calculation formula is:

[0091]

[0092] Where k represents the specific parameters of the output, and i represents the index of the sample. The standardized output parameter y of the i-th sample.k .

[0093] Similarly, the mean and standard deviation of each output parameter are recorded so that new data can be standardized in the same way when applying the model later.

[0094] Data standardization, by scaling the input and output parameters to a similar numerical range, helps accelerate the training process of neural networks, improves the convergence speed and generalization ability of the model, and makes the standardized data more suitable for training neural networks, enabling the network to better understand the complex relationship between input and output.

[0095] Specifically, step 4 includes:

[0096] In this step, the BP neural network is trained using a dataset to learn the relationship between the input and output parameters. In this embodiment, the backpropagation algorithm is used to adjust the network weights and biases to minimize the loss function.

[0097] The training objective is to minimize the mean squared error loss function L, expressed as:

[0098]

[0099] Where n is the number of samples, It is the output of the neural network for the i-th sample. This is the actual output.

[0100] For the output layer W (2) Weights and biases b (2) The updated formula is:

[0101]

[0102]

[0103] For the weight W of the hidden layer (1) and deviation b (1) The updated formula is:

[0104]

[0105]

[0106] Where η is the learning rate. These are the partial derivatives of the loss function with respect to the weights and biases, respectively.

[0107] The error signals of the output layer and hidden layer are calculated using the backpropagation algorithm:

[0108]

[0109] δ(1) =(W (2) ) T δ (2) ⊙σ'(z (1) )

[0110] Where ⊙ denotes element-wise multiplication, and represents the derivative of the activation function:

[0111] Update weights and biases using the error signal:

[0112]

[0113]

[0114]

[0115]

[0116] Among them, a (0) It is the output of the input layer.

[0117] This step involves training the neural network using the backpropagation algorithm. By adjusting the weights and biases, the network gradually learns the mapping relationship between the input and output parameters. This process iterates continuously until the loss function reaches a satisfactory level.

[0118] Specifically, step 5 includes:

[0119] In this step, a method is designed to enable the neural network to infer two other parameters based on a known input parameter.

[0120] Assuming the user inputs the dilution rate (x1), the aspect ratio (x2) and microhardness (x3) are inferred from the BP network.

[0121] Using a pre-trained BP neural network, the input parameters are backpropagated, such as... Figure 7 The specific steps are as follows:

[0122] a. Standardize the known input parameters:

[0123] b. Input the standardized parameters into the neural network and obtain the network's output:

[0124] c. Backpropagation error signal:

[0125] d. Update the gradient of the input parameters based on the error signal:

[0126] The updated parameter gradients are inversely normalized to obtain the final inference results: x2, x3.

[0127]

[0128]

[0129] Where, σ k and μ k These are the standard deviation and mean of the aspect ratio and microhardness, respectively.

[0130] Through the above steps, the other two parameters can be inferred from the known input parameters. This allows the system to intelligently match the complete parameter combination when the user inputs a parameter, enabling more flexible and intelligent operation.

[0131] Specifically, step 6 includes:

[0132] This step will explain how to input the three parameters obtained from the matching algorithm into the neural network and obtain the outputs of laser power, scanning speed, and powder feeding speed.

[0133] Suppose that the matching algorithm obtains input parameters x1, x2, and x3, where x1 is any parameter input by the user, and x2 and x3 are obtained by the matching algorithm.

[0134] Standardize the three parameters obtained from the matching:

[0135] The standardized parameters are input into the trained neural network to obtain the output:

[0136] The neural network output is denormalized to obtain the final laser power, scanning speed, and powder feeding speed.

[0137]

[0138]

[0139]

[0140] in, and These are the standard deviation and mean of laser power, scanning speed, and powder feeding speed, respectively.

[0141] This step allows the three parameters to be input into the neural network to obtain the outputs of laser power, scanning speed, and powder feeding speed. This enables the system to intelligently output complete repair parameters based on any parameter provided by the user, improving the system's flexibility and user experience.

[0142] The cladding repair module includes:

[0143] Four columns 9, and a gear rack slide 10 set on each column 9, wherein a retainer 11 and a guide shaft 12 are provided between two gear rack slides 10, and two side plates 13 are also included. A servo motor 14 is fixed on the two side plates 13. The output end of the servo motor 14 is set on the retainer 11 through a roller 15. A support bearing 16 is also included. The support bearing 16 is fixed on the side plate 13 and passes through the guide shaft 12.

[0144] A retainer 11 and a guide shaft 12 are provided between the two side plates 13. The system also includes a gantry frame 17, on which a servo motor 14 is fixed. The output end of the servo motor 14 is mounted on the retainer 11 via a roller 15. A support bearing 16 is also fixed on the gantry frame 17, and the guide shaft 12 passes through the support bearing 16. The system also includes a first laser head bracket 18, which is fixedly connected to the gantry frame 17. The servo motor 14 is also fixed on the first laser head bracket 18. The output end of the servo motor 14 is connected to a first steering connecting block 19. A connecting block 30 is fixed on the first steering connecting block 19. A second laser head bracket 20 is fixed on one side of the connecting block 30. The servo motor 14 is fixed on the second laser head bracket 20. The output end of the servo motor 14 is connected to a second steering connecting block 21. The second steering connecting block 21 is connected to a laser cladding structure 29. During repair, in this embodiment, the processing parameters (laser power, scanning speed, powder feeding speed) output by the calculation module are obtained by the PLC / microcontroller to control the gear rack slide 10 to drive the laser cladding structure 29 to move up and down, control the servo motor 14 on the side plate 13 to drive the laser cladding structure 29 to move axially along the guide rail shaft 12, control the servo motor 14 on the gantry 17 to drive the laser cladding structure 29 to move axially along the guide rail shaft 12, and control the servo motor 14 on the first laser head support 18 and the servo motor 14 on the second laser head support 20 to drive the laser cladding structure 29 to turn, so as to repair the curved surface of the blade ring.

[0145] The working process of the laser cladding structure 29 includes: the ball screw 24 drives the operating table 25 to move the three-jaw chuck 26 to the cladding repair module. During laser cladding, a high-energy laser beam irradiates the laser head, and a focused laser beam is formed through modulation of the optical components and focusing of the focusing lens. The beam is output according to the required spot size. At the same time, H13 mold steel metal powder is input from the powder conveying unit into the laser head and ejected from the powder conveying nozzle after being pressurized. The ejected powder is melted by the high-energy laser beam in the laser-powder interaction zone, turning into molten metal droplets. The gas protection device continuously supplies argon gas to ensure that the molten metal droplets are not oxidized. High-temperature metal droplets form a metal stream that is sprayed onto the substrate, where it fuses with the metal on the substrate surface to form a molten pool. As the molten pool cools, it forms a dense and hard cladding area. After completing the cladding in this area, the laser head moves, driving the laser and powder to continue forming new, continuous molten pools. After rapid cooling, a single-pass cladding is formed. After the repair is completed, the cladding layer will be in a high-temperature state and needs to be fully cooled in an argon-filled environment to prevent oxidation. After the cladding is completed, the surface of the cladding layer is cleaned again with acetone to remove impurities adhering to the surface. The non-working surface of the tunnel boring machine cutter does not require a low roughness value; only the blade is finely polished to reduce time costs.

[0146] pass Figure 8 The interface between the cladding layer and the substrate is clearly visible, with a uniform cladding distance of 1.2 mm for each pass and a consistent molten pool depth, indicating good cladding spacing and uniform powder feeding during laser cladding repair. The cladding layer thickness is uniformly 0.3 mm, without significant deviation due to each cladding pass. The microstructure from the track boundary to the interior of the cladding layer contains cellular, columnar, and equiaxed dendrites. Dendrite growth follows the temperature gradient direction, with columnar particles being dominant. As the temperature approaches the surface of the cladding layer, the cooling rate increases, and the size of the cellular grains decreases. White needle-like elements, which are tempered martensite, appear in the overlapping regions between two consecutive layers and between two adjacent laser scans; these overlapping regions are called tempered zones. Thanks to the good scanning speed, the image of the central area of ​​the laser trajectory shows that it is dominated by cellular structure, with the typical phase distribution of laser cladding H13 steel, including austenite at the grain edges, acicular martensite and retained austenite inside the grains, and obvious acicular tempered martensite in the overlapping area. This helps to enhance the hardness of the repaired area and improve its service life.

[0147] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for repairing a shield tunnel cutterhead ring system using laser cladding, characterized in that, include: Scanning module: Scans the tool ring to be repaired to obtain a digital model of the tool ring's morphology; Information acquisition module: retrieves a complete digital model of the same size cutter ring from the system library and compares it with the scanned digital model of the cutter ring to be repaired, and performs reverse reconstruction to obtain a digital model of the area to be repaired; The computation module: Based on the digital model of the area to be repaired, it inputs the ideal processing result parameters into the BP neural network to obtain the processing parameters; Cladding Repair Module: Completes the processing repair based on the processing parameters obtained from the calculation module.

2. The method for repairing shield tunnel cutterhead rings using laser cladding as described in claim 1, characterized in that, The scanning module includes: A fixed bracket is provided, on which a first motor is fixed. A connecting plate is fixedly connected to the power output end of the first motor. A second motor is fixedly connected to one side of the connecting plate. A gear is connected to the power output end of the second motor. The gear meshes with one side of an arc-shaped rack. A scanner is fixed to one end of the rack.

3. The method for repairing shield tunnel cutterhead rings using laser cladding as described in claim 2, characterized in that, A pulley is fixed on the connecting plate, and the rack is mounted on the pulley on the other side.

4. The method for repairing shield tunnel cutterhead rings using laser cladding as described in claim 3, characterized in that, The cladding repair module includes: Four columns, and a gear rack slide on each column, wherein a retainer and a guide shaft are provided between two gear rack slides, and two side plates are also included. A servo motor is fixed on the two side plates. The output end of the servo motor is mounted on the retainer via a roller. A support bearing is also included. The support bearing is fixed on the side plate and passes through the guide shaft. A retainer and a guide shaft are provided between the two side plates. The system also includes a gantry frame, on which a servo motor is fixed. The output end of the servo motor is mounted on the retainer via a roller. A support bearing is also fixed on the gantry frame, and the guide shaft passes through the support bearing. The system further includes a first laser head bracket, which is fixedly connected to the gantry frame. A servo motor is fixedly mounted on the first laser head bracket, and its output end is connected to a first steering connecting block. A connecting block is fixedly mounted on the first steering connecting block. A second laser head bracket is fixedly mounted on one side of the connecting block, and a servo motor is fixedly mounted on the second laser head bracket. The output end of the servo motor is connected to a second steering connecting block, and the second steering connecting block is connected to a laser cladding structure.

5. A method for repairing shield tunnel cutterhead rings using laser cladding as described in claim 4, characterized in that, Also includes: The base, the fixed bracket and the four columns are fixed on the base. The base is provided with guide rails and ball screws. It also includes an operating table. The ball screw passes through the operating table and is connected to it. The guide rails are embedded in the operating table. A three-jaw chuck is provided on the operating table.

Images