Gate automatic rust removal control system and rust removal method

Abstract

The application provides a gate automatic rust removal control system and a rust removal method, which comprises a detection unit, a control unit, a moving unit and a rust removal unit; the detection unit, the moving unit and the rust removal unit are all signal connected with the control unit; the detection unit is used for obtaining a three-dimensional point cloud data set of the gate; the control unit is used for controlling the detection unit, the moving unit and the rust removal unit, and establishing a three-dimensional model and generating a rust removal path based on the three-dimensional point cloud data set; the moving unit is used for driving the rust removal unit to move along the rust removal path; and the rust removal unit is used for rust removal. The application provides a gate automatic rust removal control system and a rust removal method, which does not need manual operation of a rust removal device to remove rust from the gate, increases the convenience and safety of rust removal, automatically carries out the whole rust removal process, increases the efficiency of rust removal, guarantees the rust removal effect, is convenient for rust removal of the complex structure of the gate, and has a better rust removal effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gate rust removal, and particularly relates to a gate automatic rust removal control system and a rust removal method. BACKGROUND

[0002] A ship lock is a kind of chamber-shaped hydraulic structure used to ensure the smooth passing of a ship through a concentrated water level difference on a waterway, such as the three-line continuous five-stage ship lock in the Three Gorges, which is the main navigation facility of the Three Gorges hub; a plurality of gates are generally provided in the ship lock for cooperative use, and the gates are coated with a protective coating to ensure long-term stable use of the gates, such as the three-line five-stage ship lock in the Three Gorges, which has been safely and stably operated for nearly 20 years.

[0003] However, after long-term use of the metal structure equipment such as the gate of the ship lock, the surface coating will gradually approach the design protection period, and therefore needs to be subjected to rust removal treatment.

[0004] The commonly used rust removal mode is generally to use a high-altitude operation platform or a bridge detection vehicle to send workers to the position of the gate requiring rust removal, and then the workers perform rust removal operation through a rust removal tool.

[0005] However, in the actual rust removal operation process, since manual rust removal operation needs to be performed at the gate rust removal station, the operation is inconvenient, there is a certain safety hazard, the work efficiency is low, and manual operation is prone to incomplete rust removal, which affects the rust removal quality. SUMMARY

[0006] The main purpose of the present application is to provide a gate automatic rust removal control system and a rust removal method, which solve the problems of inconvenient operation and low efficiency of the existing mode for gate rust removal.

[0007] To solve the above technical problems, the technical scheme adopted by the present application is as follows:

[0008] A gate automatic rust removal control system comprises a detection unit, a control unit, a moving unit and a rust removal unit.

[0009] The detection unit, the moving unit and the rust removal unit are signal connected with the control unit.

[0010] The detection unit is used to acquire a three-dimensional point cloud data set of the gate.

[0011] The control unit is used to control the detection unit, the moving unit and the rust removal unit, and to establish a three-dimensional model and generate a rust removal path based on the three-dimensional point cloud data set.

[0012] The moving unit is used to drive the rust removal unit to move along the rust removal path.

[0013] The rust removal unit is used for rust removal.

[0014] In a preferred scheme, the detection unit comprises a laser scanning module and a wireless transmission module, and the signal transmission module is in signal connection with the detection unit.

[0015] In a preferred scheme, the moving unit comprises a lifting module, a forward-backward moving module, a left-right moving module and a rotating module.

[0016] The lifting module is used to drive the rust removal unit to lift, the forward-backward moving module is used to drive the rust removal unit to move forward and backward, the left-right moving module is used to drive the rust removal unit to move left and right, and the rotating module is used to drive the rust removal unit to rotate 360 degrees.

[0017] In a preferred scheme, the rust removal unit comprises a rust removal module and an image recording module.

[0018] The image recording module is used to record images of the rust removal process and after the rust removal, and send the image signals to the control unit, and the control unit receives the image signals and judges the rust removal effect according to the image signals.

[0019] In a preferred scheme, the control unit is provided with a fault diagnosis module, an early warning module and a remote communication module.

[0020] The fault diagnosis module is used to monitor the working state of the detection unit, the moving unit and the rust removal unit in real time, and compare and analyze whether a fault occurs.

[0021] The early warning module is used to send an alarm signal so that maintenance personnel can quickly locate and solve the problem.

[0022] The remote communication module is used to transmit working signals and data.

[0023] A gate rust removal method comprises the following steps:

[0024] S1, scanning the gate comprehensively to obtain the surface morphology of the gate, and generating a three-dimensional point cloud data set;

[0025] S2, processing the three-dimensional point cloud data set to determine the specific position and size of the rust removal;

[0026] S3, calculating the best rust removal path according to the specific position and size information of the rust removal;

[0027] S4, driving the rust removal unit along the rust removal path to remove the rust on the gate through the moving unit;

[0028] In the rust removal process, the area after rust removal is scanned to generate a new three-dimensional point cloud data set;

[0029] S5, processing the three-dimensional point cloud data set to obtain the position and size of the secondary rust removal;

[0030] S6, calculating the best rust removal path according to the position and size information in S5.

[0031] S7, repeat S4-S6 until rust removal is complete.

[0032] In a preferred embodiment, in S1 and S4, a laser scanner is used to scan the target gate comprehensively;

[0033] Scan 2-5 times to generate 2-5 sets of three-dimensional point cloud data sets A n = {P1, P2, P3…P i}, A n represents the nth set of three-dimensional point cloud data, P i represents the point of the three-dimensional point cloud data set;

[0034] Process the three-dimensional point cloud data set A n , compare P i (x i , y i , z i ), P i (x i , y i , z i ) are the coordinate values of P i ;

[0035] For the same P i (x i , y i , z i ) at the same position, count A 0 , for different P i (x i , y i , z i ) at the same position, take the most frequent P i (x i , y i , z i ) count A 0 , or take the average value count A 0 , finally get complete A 0 .

[0036] In a preferred embodiment, in S2 and S5:

[0037] S21, denoising processing is performed on the three-dimensional point cloud data set, for each point P i (x i , y i , z i ) in the point cloud set, the filtered coordinate value is calculated as follows:

[0038]

[0039] Where N(i) represents the point Pi a neighborhood point set of p i , p j ) represents a weight function determined according to the spatial distance and the normal vector angle of points P i and P j ;

[0040] S22, further smoothing the data using a Gaussian filter;

[0041] S23, calculating the local features of each point using the processed three-dimensional point cloud data set;

[0042] S24, constructing a random forest model using the calculated local features as input;

[0043] S25, obtaining the location and size of the rust removal based on the random forest model.

[0044] In a preferred scheme, in S23, the local features include the normal vector n i and the curvature k i of each point.

[0045] In a preferred scheme, in S3 and S6, the gate surface is divided into multiple small regions B1, B2, B3…B n according to the location and size information of the rust removal, and then the best rust removal path is obtained based on an ant colony optimization algorithm.

[0046] In the division of the region B n , the following steps are included:

[0047] S31, dividing the gate surface into several continuous square regions, and setting the last region as B;

[0048] S32, starting from the first region, setting it as B m , and setting the rust region set in the current region as {b1, b2, b3…b n};

[0049] where b n represents the rust region in the current region;

[0050] S33, when , the next region B m+1 is calculated;

[0051] When , b x is divided into the next region B m+1 , until , the next region B m+1 is calculated;

[0052] B m =B n ;

[0053] wherein b x represents the rust area divided into B m+1 , and b0 represents the maximum rust area allowed to exist in the same area;

[0054] S34, set B m+1 =B m , and the rust area set in the area is {b1, b2, b3…b n}, which includes the rust area divided into the last area;

[0055] S35, repeat S33-S34 until B m =B;

[0056] By dividing the above part into multiple small areas B1, B2, B3…B n , in S33-S35, B n is marked one by one from B1.

[0057] The present application provides a gate automatic rust removal control system and a rust removal method, which has the following beneficial effects by adopting the above scheme:

[0058] 1. The rust removal device does not need to be operated manually to remove rust from the gate, increasing the convenience and safety of rust removal.

[0059] 2. The entire rust removal process is automatic, convenient to operate, increases the efficiency of rust removal, and ensures the rust removal effect.

[0060] 3. It is convenient to remove rust from the complex structure of the gate, and the rust removal effect is better.

[0061] 4. It can accurately calculate to generate the best rust removal path, ensuring the rust removal efficiency and accuracy.

[0062] 5. The rust removal process is carried out in areas, which reduces the difficulty of rust removal and ensures the rust removal effect. BRIEF DESCRIPTION OF DRAWINGS

[0063] The present application will be further described below in conjunction with the drawings and examples:

[0064] Figure 1 is a flowchart of a gate automatic rust removal control system and a rust removal method of the present application. DETAILED DESCRIPTION

[0065] Example 1:

[0066] As shown in the figure, a gate automatic rust removal control system includes a detection unit, a control unit, a moving unit and a rust removal unit, wherein: Figure 1

[0067] Detection unit:

[0068] The detection unit of the present application includes a laser scanning module and a wireless transmission module, which can comprehensively scan the gate and obtain a three-dimensional point cloud dataset of the gate. The laser scanning module uses the principle of laser ranging to emit a laser beam to the surface of the gate and receives the reflected light. By measuring the time of flight or phase change of the laser, the spatial position information of each point on the surface of the gate is accurately calculated, thereby generating a three-dimensional point cloud data. The wireless transmission module is responsible for transmitting the collected three-dimensional point cloud dataset to the control unit in real time, ensuring fast and stable transmission of data for subsequent processing and analysis.

[0069] Control unit:

[0070] The control unit is signal connected with the detection unit, the moving unit and the rust removal unit, and plays a role in coordinating and controlling the work of each unit.

[0071] Based on the three-dimensional point cloud dataset received from the detection unit, the control unit uses a three-dimensional modeling algorithm to establish a three-dimensional model of the gate. The three-dimensional model can intuitively show the surface morphology and structural features of the gate, providing accurate basic data for subsequent rust removal path planning. At the same time, the control unit generates the best rust removal path according to the rust distribution reflected in the three-dimensional model through the built-in intelligent algorithm, to ensure the efficiency and accuracy of the rust removal work.

[0072] In addition, the control unit is also provided with a fault diagnosis module, a warning module and a remote communication module. The fault diagnosis module uses real-time monitoring technology to monitor the working state of the detection unit, the moving unit and the rust removal unit. By comparing and analyzing the normal working parameters and real-time running data of each unit, it can timely judge whether a fault has occurred. Once a fault is detected, the warning module will immediately issue an alarm signal, which can be in the form of sound and light alarm, etc., so that maintenance personnel can quickly locate the fault position and take appropriate measures to minimize system downtime and improve work efficiency. The remote communication module can realize information interaction between the system and external devices or remote control center, which can be used to transmit working signals and data, facilitate operators to remotely monitor and manage the system, and also be conducive to realizing the collaborative work and data sharing among multiple devices.

[0073] Moving unit:

[0074] The moving unit includes a lifting module, a forward and backward moving module, a left and right moving module and a rotating module, which can realize flexible movement of the rust removal unit in three-dimensional space, ensuring that the rust removal unit can accurately follow the rust removal path generated by the control unit to comprehensively and efficiently remove rust from the gate.

[0075] The lifting module, forward / backward movement module, left / right movement module, and rotation module are all driven by motors or hydraulic transmission. The lifting module moves the rust removal unit vertically to accommodate rust removal needs at different heights of the gate. The forward / backward and left / right movement modules control the horizontal movement of the rust removal unit, allowing it to precisely locate the area requiring rust removal. The rotation module enables the rust removal unit to rotate 360 ​​degrees, further enhancing its flexibility and adaptability, and allowing for effective treatment of rust of various complex shapes and angles on the gate surface.

[0076] Rust removal unit:

[0077] The rust removal unit comprises a rust removal module and an image recording module. The rust removal module employs existing rust removal technologies, such as sandblasting and laser rust removal, to remove rust from the gate surface. During the rust removal process, the image recording module records the process and images after rust removal in real time and sends the image signals to the control unit. Upon receiving the image signals, the control unit uses image recognition and analysis technology to assess the rust removal effect based on the actual condition of the gate surface as reflected in the images. If any remaining rust is found, the control unit will promptly adjust the rust removal path and parameters, driving the rust removal unit again for secondary rust removal until the desired rust removal effect is achieved.

[0078] Example 2:

[0079] A method for removing rust from a gate includes the following steps:

[0080] S1. Perform a full scan of the gate to obtain the gate surface morphology and generate a 3D point cloud dataset.

[0081] S2. Process the 3D point cloud dataset to determine the specific locations and dimensions requiring rust removal;

[0082] S3. Calculate and obtain the optimal rust removal path based on the specific location and size information of the rust removal;

[0083] S4. The rust removal unit is driven by the moving unit to remove rust from the gate along the rust removal path;

[0084] During the rust removal process, the rust-removed area is scanned to generate a new 3D point cloud dataset;

[0085] S5. Process the 3D point cloud dataset to obtain the location and size of the area requiring secondary rust removal;

[0086] S6. Calculate and obtain the optimal rust removal path based on the position and size information in S5;

[0087] S7. Repeat S4-S6 until the rust is completely removed.

[0088] In the preferred solution, in S1 and S4, a laser scanner is used to scan the target gate comprehensively;

[0089] Scan 2-5 times to generate 2-5 sets of three-dimensional point cloud data sets A n = {P1, P2, P3...P i}, A n represents the nth set of three-dimensional point cloud data, P i represents the point of the three-dimensional point cloud data set;

[0090] Process the three-dimensional point cloud data set A n , compare P i (x i , y i , z i ), P i (x i , y i , z i ) are the coordinate values of P i ;

[0091] For the same P i (x i , y i , z i ) at the same position, count A 0 , for different P i (x i , y i , z i ) at the same position, take the most frequent P i (x i , y i , z i ) count A 0 , or take the average value count A 0 , finally get complete A 0 .

[0092] In the preferred solution, in S2 and S5:

[0093] S21, denoising processing is performed on the three-dimensional point cloud data set, for each point P i (x i , y i , z i ) in the point cloud set, the coordinate value of the filtered point is calculated as follows:

[0094]

[0095] Where N(i) represents the neighborhood point set of point P i , ω(p i , p j ) represents the weight value of the point Pi and P j The weight function is determined by the spatial distance and the angle between the normal vectors:

[0096]

[0097] Where, σ d and σ n The parameters representing the control distance and normal vector weights are ||p, respectively. i -p j || 2 Representative point P i and P j The square of the spatial distance, <n i n j > 2 Representative point P i and P j The square of the angle between the normal vectors;

[0098] v22. Use Gaussian filtering to further smooth the data for point P. i Its Gaussian-filtered coordinates are:

[0099]

[0100] Among them, G(p i p j () represents the Gaussian kernel function:

[0101]

[0102] Where ′ represents the standard deviation of the Gaussian kernel.

[0103] S23. Calculate the local features of each point in the processed 3D point cloud dataset;

[0104] Local features include the normal vector n of each point. i and curvature k i ;

[0105] Calculate the normal vector for each point: using a method based on principal component analysis (PCA); for point P i Given the neighborhood point set N(i), construct the covariance matrix C:

[0106]

[0107] in, The mean of the points in the neighborhood is used to perform eigenvalue decomposition on the covariance matrix C. The eigenvector corresponding to the smallest eigenvalue is the point P. i normal vector n i .

[0108] Curvature calculation: A method based on normal vector transformation is used for point P. i Within its neighborhood, select two mutually perpendicular directions u and v (which can be obtained by performing a cross product on the normal vector, etc.), and calculate the partial derivatives of the normal vector in these two directions:

[0109]

[0110] Among them, point P i curvature k i for:

[0111]

[0112] S24. Use the calculated local features as input to construct a random forest model;

[0113] From the preprocessed 3D point cloud data, a certain proportion (e.g., 20-70%) of points are randomly selected as training samples. For each training sample point, its coordinates (x, y, z) and normal vector n are extracted. i and curvature k i As an eigenvector X:

[0114] Decision tree construction: In the feature vector of the training samples, a subset of features is randomly selected (for example, the number of features to be selected is determined by the feature selection parameters of random forest), such as selecting m features to form a new feature subset.

[0115] Based on these feature subsets, the best splitting features and splitting points are selected using criteria such as information gain and Gini index. The samples are continuously divided into child nodes until the stopping conditions are met (such as the number of samples in a node being less than a certain threshold, or the depth of the tree reaching a preset value).

[0116] Repeat the decision tree construction process described above to generate multiple decision trees, preferably 50-150, to form a random forest model. During training, each decision tree is trained based on a different subset of random features and a subset of training samples to improve the model's generalization ability.

[0117] S25. Obtain the location and size of the rust removal area based on the random forest model.

[0118] The feature vector of the test sample is input into the trained random forest model. Each decision tree classifies and predicts the sample to obtain a prediction result, preferably a category label of whether rust removal is required, where 0 indicates that rust removal is not required and 1 indicates that rust removal is required.

[0119] For each sample point, the prediction results of all decision trees are combined, and the final prediction category is determined by majority voting. If the majority decision tree predicts that the point needs rust removal, the point is marked as the location that needs rust removal, thereby determining the rust removal location and size of the entire gate surface.

[0120] In the preferred embodiment, in steps S3 and S6, the gate surface is divided into multiple small areas B1, B2, B3…B, based on the required location and size information for rust removal. n Then, the optimal rust removal path is obtained based on the ant colony optimization algorithm;

[0121] Each small region is configured with a corresponding pheromone concentration τ. ij The probability of an ant moving from region i to region j when searching for a path is:

[0122]

[0123] Where α and β represent parameters that control the relative importance of pheromones and heuristic information, respectively. d ij The distance from region i to j is represented by "allowed". k This represents the set of regions that ant k can currently choose from; after completing one traversal, the ant updates the pheromones along the path using the following formula:

[0124]

[0125] Where ρ represents the pheromone volatility coefficient. The pheromone increment left by ant k on path ij during this traversal is calculated using the following formula:

[0126]

[0127] Where Q represents a constant, L k This represents the total path length traversed by ant k in this iteration. Through multiple iterations, the optimal rust removal path is finally found, which passes through all areas requiring rust removal and has the shortest total path length and highest efficiency. At the same time, considering the motion characteristics and constraints of the moving unit, the path is smoothed and optimized to ensure that the moving unit can move smoothly and efficiently along the path.

[0128] In the divided area B n The process includes the following steps:

[0129] S31. Divide the gate surface into several consecutive square regions, and designate the last region as B;

[0130] S32. Starting from the first region, let's call it B. m, and set the rust area set in the current area as {b1, b2, b3…b n};

[0131] wherein b n represents the rust area in the current area;

[0132] S33, when , calculate the next area B m+1 ;

[0133] When , b x is included in the next area B m+1 , until , calculate the next area B m+1 ;

[0134] Let B m =B n ;

[0135] wherein b x represents the rust area included in B m+1 , and b0 represents the maximum rust area allowed to exist in the same area;

[0136] S34, let B m+1 =B m , and the rust area set in the area is {b1, b2, b3…b n}, which includes the rust area included in the last area;

[0137] S35, repeat S33-S34 until B m =B.

[0138] By the above partial division of a plurality of small areas B1, B2, B3…B n , in S33-S35, B n is marked one by one from B1.

[0139] The above embodiments are only preferred technical solutions of the present application, and should not be regarded as a limitation of the present application. The protection scope of the present application should be based on the technical solutions claimed in the claims, including the equivalent replacement solutions of the technical features claimed in the claims. That is, within this range, equivalent replacement improvements are also within the protection scope of the present application.

Claims

1. A method for rust removal from gates, characterized by: Includes the following steps: S1. Perform a full scan of the gate to obtain the gate surface morphology and generate a 3D point cloud dataset. S2. Process the 3D point cloud dataset to determine the specific locations and dimensions requiring rust removal; S3. Calculate and obtain the optimal rust removal path based on the specific location and size information of the rust removal; S4. The rust removal unit is driven by the moving unit to remove rust from the gate along the rust removal path; During the rust removal process, the rust-removed area is scanned to generate a new 3D point cloud dataset; S5. Process the 3D point cloud dataset to obtain the location and size of the area requiring secondary rust removal; S6. Calculate and obtain the optimal rust removal path based on the position and size information in S5; S7. Repeat S4-S6 until the rust is completely removed; In S2 and S5: S21. Denoise the 3D point cloud dataset. For each point in the point cloud dataset... The formula for calculating the filtered coordinate values ​​is as follows: ； in, Representative point The neighborhood point set, Representative base point and The weight function is determined by the spatial distance and the angle between the normal vectors; S22. Use Gaussian filtering to further smooth the data; S23. Calculate the local features of each point in the processed 3D point cloud dataset; S24. Use the calculated local features as input to construct a random forest model; S25. Obtain the location and size of the rust removal area based on the random forest model; In S23, local features include the normal vector of each point. and curvature ; In S3 and S6, the gate surface is divided into multiple small areas based on the required location and size information for rust removal. Then, the optimal rust removal path is obtained based on the ant colony optimization algorithm; In dividing the area The process includes the following steps: S31. Divide the gate surface into several consecutive square regions, and designate the last region as B; S32, Starting from the first region, set as And let the set of rusted areas in the current region be . ; in This represents the rusted area within the current region; S33, when Then calculate the next region. ; when Then Transferred to the next area until Then calculate the next region. ; set up ; in Representatives included rusty areas This represents the maximum allowable area of ​​rust within the same region. S34, Let = The rusted areas within the region are grouped as follows This includes the rusted area that was previously marked out; S35. Repeat S33-S34 until... ; The above section divides the area into multiple smaller regions. In S33-S35, Depend on Start marking them one by one.

2. The gate rust removal method according to claim 1, characterized in that: in In S1 and S4, a laser scanner is used to perform a full scan of the target gate; Scan 2-5 times to generate 2-5 sets of 3D point cloud datasets. , Represents the nth set of 3D point cloud datasets. Points representing a 3D point cloud dataset; 3D point cloud dataset Process and compare , for The coordinate values; For the same location , included For the same location, different Take the one that appears most frequently. Included Or calculate the average and include it. Finally, the complete .

3. An automatic rust removal control system for gates, characterized in that: A gate rust removal method according to any one of claims 1-2 includes a detection unit, a control unit, a moving unit, and a rust removal unit; The detection unit, moving unit, and rust removal unit are all connected to the control unit via signals. The detection unit is used to acquire the three-dimensional point cloud dataset of the gate; The control unit is used to control the detection unit, the moving unit, and the rust removal unit, and to build a 3D model and generate a rust removal path based on the 3D point cloud dataset; The moving unit is used to drive the rust removal unit to move along the rust removal path; The rust removal unit is used for rust removal.

4. The automatic rust removal control system for gates according to claim 3, characterized in that: The detection unit includes a laser scanning module and a wireless transmission module, and the signal transmission module is connected to the detection unit.

5. The automatic rust removal control system for gates according to claim 3, characterized in that: The moving unit includes a lifting module, a forward and backward moving module, a left and right moving module, and a rotating module; The lifting module is used to drive the rust removal unit to lift up and down; the forward and backward movement module is used to drive the rust removal unit to move forward and backward; the left and right movement module is used to drive the rust removal unit to move left and right; and the rotation module is used to drive the rust removal unit to rotate 360 ​​degrees.

6. The automatic rust removal control system for gates according to claim 3, characterized in that: The rust removal unit includes a rust removal module and an image recording module; The image recording module is used to record the rust removal process and images after rust removal, and sends the image signals to the control unit. The control unit receives the image signals and judges the rust removal effect based on the image signals.

7. The automatic rust removal control system for gates according to claim 3, characterized in that: The control unit is equipped with a fault diagnosis module, an early warning module, and a remote communication module; The fault diagnosis module is used to monitor the working status of the detection unit, moving unit and rust removal unit in real time, and compare and analyze whether a fault has occurred. The early warning module is used to issue alarm signals so that maintenance personnel can quickly locate and resolve problems; The remote communication module is used to transmit working signals and data.

Images