Intelligent derusting method, device, equipment and system for laser cleaning machine

By using intelligent control methods combined with camera, sensor and spectral analyzer in the laser cleaning machine, the comprehensive corrosion degree index is calculated, and the problem of inaccurate laser rust removal in the existing technology is solved, and efficient and accurate rust removal in metal rust areas is achieved. and sufficient consideration of environmental factors.

CN119035178AActive Publication Date: 2024-11-29GUANGDONG XINQUANLI LASER CNC EQUIP CO LTD

Patent Information

Application Number
CN202411404999.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-10
Publication Date
2024-11-29
Estimated Expiration
2044-10-10

AI Technical Summary

Technical Problem

The existing laser rust removal technology lacks accurate judgment and intelligent control of the degree of metal rust, resulting in poor rust removal and prone to excessive rust removal or incomplete rust removal.

Method used

Using the intelligent rust removal control method of laser cleaning machine based on the degree of metal corrosion, we can obtain metal surface images through camera photography, analyze and identify the corrosion area, combine the environmental parameters collected by the sensor and the data detected by the spectral analyzer to calculate the comprehensive rust degree index, and then Determine the parameters of the laser cleaning machine for precise rust removal.

Benefits of technology

It achieves efficient and precise rust removal in metal rust areas, avoids damage to the metal matrix, fully considers the impact of environmental factors on the degree of rust, and improves the pertinence and effectiveness of the rust removal effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119035178A_ABST
    Figure CN119035178A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent rust removal method, device, equipment and system for a laser cleaning machine, and relates to the field of laser rust removal, and the method comprises the steps that a camera is controlled to photograph the surface of a target metal piece to obtain a metal surface image, and the image is analyzed to recognize a corrosion area and determine the corrosion roughness level; environment parameters of a target metal part application scene are collected through a sensor, and the sum of environment influence indexes is calculated; meanwhile, a spectrum analyzer is controlled to detect the corrosion area to obtain spectrum detection data, the corrosion type is analyzed and determined, and a chemical component complexity index is obtained; performing weighted summation on the comprehensive chemical component complexity index, the corrosion roughness level, the corrosion type and the environmental influence index to calculate a comprehensive corrosion degree index; and laser cleaning parameters of the laser cleaning machine are determined according to the comprehensive corrosion degree index, and the laser cleaning machine is controlled to conduct laser rust removal on the corrosion area of the target metal piece. The rust removal effect on metal rust can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of laser rust removal, and in particular to an intelligent rust removal method, device, equipment and system for a laser cleaning machine. Background Art

[0002] In the field of metal surface treatment, traditional metal rust removal methods mainly include mechanical rust removal and chemical rust removal. Mechanical rust removal usually uses sandblasting, shot blasting and other methods to remove rust on the metal surface through physical impact force, but this method is easy to damage the metal surface, and the working environment is harsh, with high noise and dust pollution. Chemical rust removal uses chemical reagents such as acids and alkalis to react with rust to remove rust, but chemical reagents may corrode the metal matrix and also cause environmental pollution problems.

[0003] With the development of technology, some methods of using laser to remove rust from metals have emerged. In the prior art, laser rust removal is usually performed based on experience or preset fixed parameters, lacking accurate judgment and intelligent control of the degree of metal corrosion. Specifically, when removing rust from the target metal parts, the rust condition is generally roughly judged through simple visual observation or rough detection methods, and then the laser cleaning machine is directly used for rust removal, without considering the influence of factors such as the roughness level of rust of the metal parts, the type of rust, and the environmental parameters of the application scenario on the degree of rust.

[0004] Therefore, the existing laser rust removal technology lacks accurate judgment and intelligent control of the degree of metal corrosion, and only relies on experience or fixed parameters for operation, which can easily lead to poor rust removal, excessive rust removal or incomplete rust removal, so the rust removal effect is not ideal. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment and system for intelligent rust removal by a laser cleaning machine, which can effectively improve the rust removal effect on metal corrosion.

[0006] An embodiment of the present invention provides an intelligent rust removal control method for a laser cleaning machine based on the degree of metal corrosion, comprising: Controlling the camera to take a picture of the surface of the target metal part to obtain a metal surface image; Performing image analysis on the metal surface image to identify the rusted area of ​​the target metal part; Performing image analysis on the corroded area to determine the corrosion roughness level of the corroded area; Collecting environmental parameters of the application scenario of the target metal part through a sensor, and calculating the sum of environmental impact indexes affecting the degree of corrosion of the rusted area according to the environmental parameters; Controlling a spectrum analyzer to detect the rusted area of ​​the target metal part to obtain spectrum detection data; Analyzing the spectral detection data to determine the corrosion type of the corrosion area of ​​the target metal part, and analyzing to obtain a chemical composition complexity index of the corrosion area; Calculate the comprehensive corrosion degree index of the rusted area according to the weighted sum of the chemical composition complexity index of the rusted area, the rust roughness grade, the rust type and the environmental impact index affecting the corrosion degree of the rusted area; Determining laser cleaning parameters of a laser cleaning machine according to the comprehensive corrosion degree index; According to the determined laser cleaning parameters, the laser cleaning machine is controlled to perform laser rust removal on the rusted area of ​​the target metal part.

[0007] As an improvement of the above solution, the image analysis of the corroded area to determine the corrosion roughness level of the corroded area includes: Cutting the rusted area in the metal surface image to obtain a rusted area image; A median filtering algorithm is used to perform denoising on the rusted area image, and a histogram equalization algorithm is used to enhance the contrast of the rusted area image to obtain a preprocessed rusted area image; The rust roughness level of the preprocessed rust area image is calculated by the following formula: ; in, is the total number of pixels in the preprocessed rusted area image; is the neighborhood size; It's pixels Gray value of is the average gray value of the rusted area; is the fractal dimension, which is calculated using the box counting method, which involves overlaying the preprocessed rusted area image on grids of different sizes, counting the number of non-empty boxes, and then calculating the fractal dimension through logarithmic regression analysis; and Adjust the parameters through experiments. Specifically, an initial value is given first, and then the matching degree between the calculated rust roughness grade and the actual rust situation is observed, and the parameter value is gradually adjusted until the result that meets the user's needs is obtained; It is the characteristic value of the grayscale gradient used to describe the surface roughness. Specifically, the gradient amplitude of the pixel grayscale value is calculated as a characteristic value. The gradient amplitude is obtained by calculating the grayscale difference between each pixel and its neighboring pixels in the preprocessed rust area image. is the total number of eigenvalues ​​of the grayscale gradient.

[0008] As an improvement of the above solution, the analyzing the spectral detection data to determine the corrosion type of the rusted area of ​​the target metal part includes: Extracting features from the spectrum detection data to obtain peak features, band features, and slope features of the spectrum data; The peak feature, the band feature and the slope feature are fused, and the fused spectral feature is calculated by the following feature fusion formula: ;in, is the vector of peak features, and the vector set of peak features is , Indicates A vector of peak features; is the vector of band features, and the vector set of band features is , Indicates A vector of band features; is the vector of slope characteristics, and the vector set of slope characteristics is , Indicates A vector of slope characteristics; are weight coefficients, the sum of which is 1; is the bias term; They are respectively nonlinear transformation functions of the vector of peak features, the vector of band features, and the vector of slope features; The Hadamard product of the peak, band, and slope feature vectors is used to capture the interactive information between different features by element-by-element multiplication; The fused spectral features are input into a corrosion type classification model of a convolutional neural network, and the corrosion type of the corroded area of ​​the target metal part is output.

[0009] As an improvement of the above solution, the weighted summation according to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust type and the environmental impact index affecting the rust degree of the rusted area includes: Determining the degree of corrosion impact of the corrosion type according to the corrosion type of the corrosion area; According to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust impact degree of the rust type and the sum of the environmental impact indexes affecting the rust degree of the rusted area, the comprehensive rust degree index of the rusted area is calculated by the following formula: ; in, are weight coefficients, the sum of which is 1; is the rust roughness grade of the rusted area; It is the preset adjustment index for the rust roughness level; is the degree of rust influence of the rust type; It is a preset adjustment index for the degree of rust influence of the rust type, which is used to adjust its influence weight in the comprehensive rust degree index according to the actual situation; is the chemical composition complexity index of the rusted area; It is a preset adjustment index of the chemical composition complexity index to adapt to different metal materials and corrosion environments; is the sum of the environmental impact indices affecting the degree of corrosion in the corroded area; is the number of environmental parameters; It is An environmental parameter environmental impact index of the degree of corrosion of the corrosion area.

[0010] Another embodiment of the present invention provides an intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion, including: A first control module is used to control the camera to take a picture of the surface of the target metal part to obtain a metal surface image; A first analysis module, configured to perform image analysis on the metal surface image to identify the rusted area of ​​the target metal part; A second analysis module is used to perform image analysis on the rusted area to determine the rust roughness level of the rusted area; A second control module is used to collect environmental parameters of the application scenario of the target metal part through a sensor, and calculate the sum of environmental impact indexes affecting the degree of corrosion of the rusted area according to the environmental parameters; A third control module is used to control the spectrum analyzer to detect the rusted area of ​​the target metal part to obtain spectrum detection data; A third analysis module is used to analyze the spectral detection data, determine the corrosion type of the rusted area of ​​the target metal part, and analyze and obtain the chemical composition complexity index of the rusted area; A calculation module, used to calculate a comprehensive corrosion degree index of the corrosion area according to a weighted sum of the chemical composition complexity index of the corrosion area, the corrosion roughness grade, the corrosion type and an environmental impact index affecting the corrosion degree of the corrosion area; A determination module, used to determine the laser cleaning parameters of the laser cleaning machine according to the comprehensive corrosion degree index; The fourth control module is used to control the laser cleaning machine to perform laser rust removal on the rusted area of ​​the target metal part according to the determined laser cleaning parameters.

[0011] As an improvement of the above solution, the second analysis module is specifically used for: Cutting the rusted area in the metal surface image to obtain a rusted area image; A median filtering algorithm is used to perform denoising on the rusted area image, and a histogram equalization algorithm is used to enhance the contrast of the rusted area image to obtain a preprocessed rusted area image; The rust roughness level of the preprocessed rust area image is calculated by the following formula: ; in, is the total number of pixels in the preprocessed rusted area image; is the neighborhood size; It's pixels Gray value of is the average gray value of the rusted area; is the fractal dimension, which is calculated using the box counting method, which involves overlaying the preprocessed rusted area image on grids of different sizes, counting the number of non-empty boxes, and then calculating the fractal dimension through logarithmic regression analysis; and Adjust the parameters through experiments. Specifically, an initial value is given first, and then the matching degree between the calculated rust roughness grade and the actual rust situation is observed, and the parameter value is gradually adjusted until the result that meets the user's needs is obtained; It is the characteristic value of the grayscale gradient used to describe the surface roughness. Specifically, the gradient amplitude of the pixel grayscale value is calculated as a characteristic value. The gradient amplitude is obtained by calculating the grayscale difference between each pixel and its neighboring pixels in the preprocessed rust area image. is the total number of eigenvalues ​​of the grayscale gradient.

[0012] As an improvement of the above solution, the third analysis module is specifically used for: Extracting features from the spectrum detection data to obtain peak features, band features, and slope features of the spectrum data; The peak feature, the band feature and the slope feature are fused, and the fused spectral feature is calculated by the following feature fusion formula: ;in, is the vector of peak features, and the vector set of peak features is , Indicates A vector of peak features; is the vector of band features, and the vector set of band features is , Indicates A vector of band features; is the vector of slope characteristics, and the vector set of slope characteristics is , Indicates A vector of slope characteristics; are weight coefficients, the sum of which is 1; is the bias term; They are respectively nonlinear transformation functions of the vector of peak features, the vector of band features, and the vector of slope features; The Hadamard product of the peak, band, and slope feature vectors is used to capture the interactive information between different features by element-by-element multiplication; The fused spectral features are input into a corrosion type classification model of a convolutional neural network, and the corrosion type of the corroded area of ​​the target metal part is output.

[0013] As an improvement of the above solution, the calculation module is specifically used for: Determining the degree of corrosion impact of the corrosion type according to the corrosion type of the corrosion area; According to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust impact degree of the rust type and the sum of the environmental impact indexes affecting the rust degree of the rusted area, the comprehensive rust degree index of the rusted area is calculated by the following formula: ; in, are weight coefficients, the sum of which is 1; is the rust roughness grade of the rusted area; It is the preset adjustment index for the rust roughness level; is the degree of rust influence of the rust type; It is a preset adjustment index for the degree of rust influence of the rust type, which is used to adjust its influence weight in the comprehensive rust degree index according to the actual situation; is the chemical composition complexity index of the rusted area; It is a preset adjustment index of the chemical composition complexity index to adapt to different metal materials and corrosion environments; is the sum of the environmental impact indices affecting the degree of corrosion in the corroded area; is the number of environmental parameters; It is An environmental parameter environmental impact index of the degree of corrosion of the corrosion area.

[0014] Another embodiment of the present invention provides an intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the intelligent rust removal control method for a laser cleaning machine based on the degree of metal corrosion described in the above-mentioned embodiment of the invention is implemented.

[0015] Another embodiment of the present invention provides an intelligent rust removal control system for a laser cleaning machine based on the degree of metal corrosion, comprising a camera, a spectrum analyzer, and the intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion described in the above-mentioned embodiment of the invention; the intelligent rust removal control device for a laser cleaning machine is communicatively connected to the camera and is communicatively connected to the spectrum analyzer.

[0016] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: First, the camera is controlled to take a photo of the surface of the target metal part to obtain a metal surface image, and the image is analyzed to identify the rust area and determine the rust roughness level; then the sensor is used to collect the environmental parameters of the target metal part application scenario, and the sum of the environmental impact index is calculated; at the same time, the spectrum analyzer is controlled to detect the rust area to obtain spectral detection data, and the rust type is analyzed to determine the chemical composition complexity index; then the chemical composition complexity index, the rust roughness level, the rust type and the environmental impact index are weighted and summed to calculate the comprehensive rust degree index; then the laser cleaning parameters of the laser cleaning machine are determined according to the comprehensive rust degree index, and finally the laser cleaning machine is controlled to perform laser rust removal on the rusted area of ​​the target metal part. The embodiment of the present invention effectively solves the problem that the existing laser rust removal technology lacks accurate judgment and intelligent control of the metal rust degree, determines the comprehensive rust degree index through multi-dimensional analysis, and then accurately sets the laser cleaning parameters to achieve efficient and accurate rust removal of the rusted area of ​​the target metal part, while avoiding damage to the metal matrix caused by excessive rust removal or incomplete rust removal, and fully considers the influence of environmental factors on the rust degree. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of an intelligent rust removal control method of a laser cleaning machine based on the degree of metal corrosion provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of an intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of an intelligent rust removal control device of a laser cleaning machine based on the degree of metal corrosion provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of an intelligent rust removal control system of a laser cleaning machine based on the degree of metal corrosion provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 , is a flow chart of a method for intelligent rust removal of a laser cleaning machine based on the degree of metal corrosion provided by an embodiment of the present invention. The method for intelligent rust removal of a laser cleaning machine based on the degree of metal corrosion comprises steps S10 to S18: S10, controlling the camera to take a picture of the surface of the target metal part to obtain a metal surface image; S11, performing image analysis on the metal surface image to identify the rusted area of ​​the target metal part; S12, performing image analysis on the corroded area to determine the corrosion roughness level of the corroded area; S13, collecting environmental parameters of the application scenario of the target metal part through a sensor, and calculating the sum of environmental impact indexes affecting the degree of corrosion of the rusted area according to the environmental parameters; S14, controlling a spectrum analyzer to detect the rusted area of ​​the target metal part to obtain spectrum detection data; S15, analyzing the spectral detection data to determine the corrosion type of the corrosion area of ​​the target metal part, and analyzing to obtain a chemical composition complexity index of the corrosion area; S16, calculating a comprehensive corrosion degree index of the corrosion area according to a weighted sum of the chemical composition complexity index of the corrosion area, the corrosion roughness grade, the corrosion type, and an environmental impact index affecting the corrosion degree of the corrosion area; S17, determining laser cleaning parameters of a laser cleaning machine according to the comprehensive corrosion degree index; S18, according to the determined laser cleaning parameters, controlling the laser cleaning machine to perform laser rust removal on the rusted area of ​​the target metal part.

[0020] In an embodiment of the present invention, firstly, a camera is controlled to take a photo of the surface of a target metal part to obtain a metal surface image, and the image is analyzed to identify the rust area and determine the rust roughness level; then, a sensor is used to collect environmental parameters of the target metal part application scenario, and the sum of environmental impact indexes is calculated; at the same time, a spectrum analyzer is controlled to detect the rust area to obtain spectrum detection data, and the rust type is analyzed to determine the chemical composition complexity index; then, the chemical composition complexity index, the rust roughness level, the rust type, and the sum of the environmental impact index are comprehensively calculated to obtain a comprehensive rust degree index; then, according to the comprehensive rust degree index, the laser cleaning parameters of the laser cleaning machine are determined, and finally, the laser cleaning machine is controlled to perform laser rust removal on the rusted area of ​​the target metal part. The embodiment of the present invention effectively solves the problem that the existing laser rust removal technology lacks accurate judgment and intelligent control of the metal rust degree, determines the comprehensive rust degree index through multi-dimensional analysis, and then accurately sets the laser cleaning parameters to achieve efficient and accurate rust removal of the rusted area of ​​the target metal part, while avoiding damage to the metal matrix caused by excessive rust removal or incomplete rust removal, and fully considering the influence of environmental factors on the rust degree.

[0021] It is understandable that existing image analysis can be used to perform image analysis on the metal surface image to identify the rusted area of ​​the target metal part.

[0022] As an example, through a large number of experiments and data analysis, the laser cleaning parameter combinations corresponding to different comprehensive corrosion index ranges are determined. For example, the comprehensive corrosion index is divided into three levels: low, medium, and high, corresponding to different laser power, scanning speed, pulse frequency and other parameters. For a low comprehensive corrosion index, a lower laser power (such as 500W), a higher scanning speed (such as 1000mm / s), and a higher pulse frequency (such as 50kHz) may be selected. This is because areas with low corrosion require less energy input, and a higher scanning speed can improve rust removal efficiency and avoid overtreatment. For a medium comprehensive corrosion index, a moderate laser power (such as 1000W), a moderate scanning speed (such as 500mm / s), and a moderate pulse frequency (such as 30kHz) can be selected. This can minimize damage to the metal surface while ensuring the rust removal effect. For a high comprehensive corrosion index, a higher laser power (such as 1500W), a lower scanning speed (such as 200mm / s), and a lower pulse frequency (such as 20kHz) may be selected. Areas with high rust levels require greater energy input to effectively remove rust, but lower scanning speeds ensure that the laser can fully act on the rusted area and improve the quality of rust removal. After calculating the comprehensive rust level index of the target metal part's rusted area, the laser cleaning parameters suitable for the rust level are determined by querying a pre-established correspondence table or using an algorithm model.

[0023] In addition, the process of controlling the laser cleaning machine for rust removal can be: 1. Equipment settings: Set the laser cleaning machine's laser power, scanning speed, pulse frequency and other parameters to the determined laser cleaning parameters. Ensure that the laser cleaning machine's optical system, control system and cooling system are in normal working condition. Adjust the laser cleaning machine's working distance and focus position so that the laser can accurately focus on the rusted area to achieve the best rust removal effect.

[0024] 2. Rust removal operation: Start the laser cleaning machine and perform laser rust removal on the rusted area of ​​the target metal part. During the rust removal process, the laser beam is irradiated on the rusted area, and the rust is vaporized, decomposed or falls off through instantaneous high temperature, thereby achieving the purpose of rust removal. The laser cleaning machine can use continuous scanning or point scanning, and select the appropriate scanning mode according to the shape and size of the rusted area. For example, for large-area rusted areas, the continuous scanning mode can be used to improve the rust removal efficiency; for rusted areas with complex shapes or small areas, the point scanning mode can be used to ensure that the laser can accurately act on each rusted point.

[0025] 3. Real-time monitoring and adjustment: During the laser rust removal process, the working status and rust removal effect of the laser cleaning machine can be monitored in real time through sensors. For example, a temperature sensor can be used to monitor the temperature change of the metal surface to avoid damage to the metal substrate due to excessive temperature; an optical sensor can be used to monitor the surface quality after rust removal to ensure that the rust removal effect meets the requirements. If the rust removal effect is not ideal or an abnormal situation occurs, the laser cleaning parameters can be adjusted in time or the rust removal operation can be stopped for inspection and adjustment. For example, if the rust removal is not thorough, the laser power can be appropriately increased or the scanning speed can be reduced; if the metal surface is found to be overheated, the laser power can be reduced or the scanning speed can be increased.

[0026] Assume that the target metal part is a part of a large steel structure bridge. The comprehensive rust index of a certain rusted area is calculated to be medium through the previous steps. According to the pre-established correspondence, the laser cleaning parameters of 1000W laser power, 500mm / s scanning speed and 30kHz pulse frequency are selected. When performing laser rust removal, set the parameters of the laser cleaning machine to the above values, and adjust the working distance and focus position. After starting the laser cleaning machine, the rusted area is scanned continuously. During the rust removal process, the temperature sensor monitors the temperature of the metal surface in real time. When the temperature is close to the critical value, the laser power is appropriately reduced or the scanning speed is increased to prevent the metal substrate from overheating. At the same time, the optical sensor monitors the surface quality after rust removal. When residual rust is found, the laser power is appropriately increased or the scanning speed is reduced to improve the rust removal effect.

[0027] Through the above process, the laser cleaning parameters can be accurately determined according to the comprehensive rust degree index, and the laser cleaning machine can be controlled to perform efficient and precise laser rust removal on the rusted area of ​​the target metal part.

[0028] As an improvement of the above solution, the image analysis of the corroded area to determine the corrosion roughness level of the corroded area includes: Cutting the rusted area in the metal surface image to obtain a rusted area image; A median filtering algorithm is used to perform denoising on the rusted area image, and a histogram equalization algorithm is used to enhance the contrast of the rusted area image to obtain a preprocessed rusted area image; The rust roughness level of the preprocessed rust area image is calculated by the following formula: ; in, is the total number of pixels in the preprocessed rusted area image; is the neighborhood size; It's pixels Gray value of is the average gray value of the rusted area; is the fractal dimension, which is calculated using the box counting method, which involves overlaying the preprocessed rusted area image on grids of different sizes, counting the number of non-empty boxes, and then calculating the fractal dimension through logarithmic regression analysis; and Adjust the parameters through experiments. Specifically, an initial value is given first, and then the matching degree between the calculated rust roughness grade and the actual rust situation is observed, and the parameter value is gradually adjusted until the result that meets the user's needs is obtained; It is the characteristic value of the grayscale gradient used to describe the surface roughness. Specifically, the gradient amplitude of the pixel grayscale value is calculated as a characteristic value. The gradient amplitude is obtained by calculating the grayscale difference between each pixel and its neighboring pixels in the preprocessed rust area image. is the total number of eigenvalues ​​of the grayscale gradient.

[0029] In the embodiment of the present invention, not only the traditional total number of pixels, neighborhood size, pixel grayscale value and average grayscale value are considered, but also the fractal dimension, adjustment parameters and grayscale gradient eigenvalues ​​are introduced. This comprehensive consideration of multiple factors can more comprehensively and accurately describe the surface roughness of the rusted area. At the same time, the introduction of fractal dimension can better reflect the complexity and irregularity of the surface of the rusted area. The fractal dimension is calculated by the box counting method, which provides a new perspective and method for the evaluation of the rust roughness level. In addition, the addition of grayscale gradient eigenvalues ​​enriches the description of surface roughness. The gradient amplitude of the calculated pixel grayscale value is used as the eigenvalue to capture the grayscale changes of the pixel in the rusted area image and its neighborhood pixels, and further reflect the roughness of the surface. Therefore, the embodiment of the present invention provides an important basis for determining the comprehensive rust degree index by accurately calculating the rust roughness level. Because the accuracy of the comprehensive rust degree index directly affects the setting of the laser cleaning parameters of the laser cleaning machine. By accurately calculating the rust roughness level, the laser cleaning parameters can be set more accurately, the accuracy of rust removal can be improved, and excessive rust removal or incomplete rust removal can be avoided.

[0030] As an improvement of the above solution, the analyzing the spectral detection data to determine the corrosion type of the rusted area of ​​the target metal part includes: Extracting features from the spectrum detection data to obtain peak features, band features, and slope features of the spectrum data; The peak feature, the band feature and the slope feature are fused, and the fused spectral feature is calculated by the following feature fusion formula: ;in, is the vector of peak features, and the vector set of peak features is , Indicates A vector of peak features; is the vector of band features, and the vector set of band features is , Indicates A vector of band features; is the vector of slope characteristics, and the vector set of slope characteristics is , Indicates A vector of slope characteristics; are weight coefficients, the sum of which is 1; is the bias term; They are respectively nonlinear transformation functions of the vector of peak features, the vector of band features, and the vector of slope features; The Hadamard product of the peak, band, and slope feature vectors is used to capture the interactive information between different features by element-by-element multiplication; The fused spectral features are input into a corrosion type classification model of a convolutional neural network, and the corrosion type of the corroded area of ​​the target metal part is output.

[0031] In an embodiment of the present invention, firstly, the spectral detection data of the rusted area of ​​the target metal part is feature extracted to obtain peak features, band features and slope features. Then, these features are fused through a specific feature fusion formula, in which weight coefficients, bias terms, nonlinear transformation functions and Hadamard product operations are introduced to capture the interactive information between different features. Finally, the fused spectral features are input into the rust type classification model of the convolutional neural network to determine the rust type of the rusted area. Specifically, the embodiment of the present invention comprehensively considers the peak features, band features and slope features, analyzes the spectral data from multiple angles, and improves the accuracy of the judgment of the rust type; at the same time, when performing feature fusion, not only the weights of different feature vectors are considered, but also the feature expression ability is improved through nonlinear transformation functions, and the Hadamard product operation is used to capture the interactive information between features, so that the fused features are more representative (the Hadamard product operation multiplies the elements one by one, effectively captures the interactive relationship between the peak, band and slope features, and provides more information for the judgment of the rust type.). Moreover, the nonlinear transformation function processes different feature vectors, which can extract higher-level feature representations and enhance the distinguishability of features. In summary, the embodiment of the present invention can accurately determine the rust type of the rusted area of ​​the target metal part through precise feature extraction, innovative feature fusion and classification model using convolutional neural network. It provides an important basis for the calculation of the comprehensive rust degree index, thereby realizing the precise setting of the parameters of the laser cleaning machine, improving the rust removal efficiency and quality, avoiding the problem of poor rust removal effect caused by inaccurate judgment of the rust type, and giving full play to the advantages of convolutional neural network, improving the intelligence level of the entire rust removal process.

[0032] As an improvement of the above solution, the sum of the environmental impact indexes according to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust type and the rust degree of the rusted area includes: Determining the degree of corrosion impact of the corrosion type according to the corrosion type of the corrosion area; According to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust impact degree of the rust type and the sum of the environmental impact indexes affecting the rust degree of the rusted area, the comprehensive rust degree index of the rusted area is calculated by the following formula: ; in, are weight coefficients, the sum of which is 1; is the rust roughness grade of the rusted area; It is the preset adjustment index for the rust roughness level; is the degree of rust influence of the rust type; It is a preset adjustment index for the degree of rust influence of the rust type, which is used to adjust its influence weight in the comprehensive rust degree index according to the actual situation; is the chemical composition complexity index of the rusted area; It is a preset adjustment index of the chemical composition complexity index to adapt to different metal materials and corrosion environments; is the sum of the environmental impact indices affecting the degree of corrosion in the corroded area; is the number of environmental parameters; It is An environmental parameter environmental impact index of the degree of corrosion of the corrosion area.

[0033] In an embodiment of the present invention, first, the degree of corrosion influence of the corrosion type is determined according to the corrosion type of the target metal part corrosion area. This step helps to quantify the contribution of different corrosion types to the overall corrosion degree in a more specific manner. Then, a comprehensive corrosion degree index is calculated by comprehensively considering multiple key factors. These include the corrosion roughness level, which reflects the roughness of the surface of the corrosion area; the corrosion influence level of the corrosion type, which clarifies the specific role of different corrosion types; the chemical composition complexity index, which reflects the impact of the diversity of chemical composition in the corrosion area on corrosion; and the sum of the environmental impact index, which takes into account the effect of environmental parameters on corrosion in the application scenario of the target metal part. Therefore, the embodiment of the present invention comprehensively integrates the impact of multiple aspects such as corrosion roughness level, corrosion type, chemical composition complexity and environmental parameters on the degree of corrosion. Compared with traditional methods, it no longer relies solely on a single factor for evaluation, but is comprehensively considered from multiple angles, making the evaluation results more accurate and comprehensive. For example, not only the physical characteristics of the rusted area (rust roughness level) are considered, but also the influence of chemical factors (complexity of chemical composition) and external environmental factors (environmental parameters) on rust are deeply analyzed, and the specific influence degree of the rust type is combined to provide more abundant information for a comprehensive understanding of the rust condition. In addition, the degree of rust influence is determined according to the type of rust, which provides more specific considerations for comprehensive evaluation. Different types of rust may have different corrosion mechanisms and development speeds. By determining the degree of rust influence of the rust type, the overall rust situation can be evaluated more specifically. For example, for different types such as oxidative rust and electrochemical rust, the degree of damage and development trend to metal parts may be different. By determining the respective degree of rust influence, different weights can be given in the comprehensive evaluation. In summary, the embodiment of the present invention provides an accurate basis for determining the laser cleaning parameters of the laser cleaning machine by accurately calculating the comprehensive rust degree index. Specifically, it can achieve a comprehensive and accurate evaluation of the rusted area, avoiding the limitations of a single factor evaluation. For example, in traditional methods, if only the rust roughness level is considered, the influence of rust type, chemical composition and environmental factors may be ignored, resulting in inaccurate laser cleaning parameter settings, thereby affecting the rust removal effect. However, by comprehensively considering multiple factors, this technical solution can more accurately determine the power, scanning speed, pulse frequency and other parameters of the laser cleaning machine, thereby improving the pertinence and effectiveness of rust removal. At the same time, it can be flexibly adjusted according to different actual conditions, which improves the adaptability and practicality of the technical solution. For example, under different metal materials, rust environments and application requirements, the weight coefficient and preset adjustment index can be adjusted to make the calculation of the comprehensive rust degree index more in line with the actual situation, thereby better guiding the laser rust removal operation.

[0034] It is understandable that preset adjustment indexes are set for different factors, such as the preset adjustment index for the rust roughness level, the preset adjustment index for the rust influence degree of the rust type, and the preset adjustment index for the chemical composition complexity index. These adjustment indexes can flexibly adjust the influence weight of each factor in the comprehensive index according to the actual situation to adapt to different metal materials and corrosion environments. For example, for some special metal materials, the influence of chemical composition complexity on rust may be more significant. At this time, the value can be increased to increase the weight of the chemical composition complexity index in the comprehensive rust degree index. The value of the adjustment index can be determined by analyzing a large number of actual cases and experimental verification to ensure that the real influence of each factor on the rust degree can be accurately reflected in different situations.

[0035] It should be noted that It is the sum of the environmental impact indexes that affect the degree of corrosion in the rusted area, so that the influence of environmental factors on the degree of corrosion is considered in more detail. For example, environmental parameters may include humidity, temperature, pH, etc. Different environmental parameters may have different degrees of influence on corrosion. By calculating the environmental impact index of each environmental parameter separately and summing them, the comprehensive effect of environmental factors on corrosion can be more accurately reflected. For example, assuming that the target metal part is an outdoor iron facility, consider the three environmental parameters of humidity, temperature and salinity. Humidity can be measured by a humidity sensor. For example, when the relative humidity is below 50%, it has little effect on corrosion, and the environmental impact index is 0.2; 50%-70% is 0.4; above 70% is 0.6. The temperature is measured by a temperature sensor. The environmental impact index is 0.1 at 0-25°C, 0.3 at 25°C-35°C, and 0.5 above 35°C. Salinity can be determined by detecting the salt content in the surrounding soil or air. The environmental impact index is 0.1 for low salinity, 0.3 for medium salinity, and 0.5 for high salinity. Assuming that the relative humidity is 65%, the temperature is 32°C, and the salinity is medium at a certain moment, the humidity environmental impact index is 0.4, the temperature environmental impact index is 0.3, and the salinity environmental impact index is 0.3. There are three environmental parameters, that is, n=3, then the total environmental impact index E=0.4+0.3+0.3=1, which reflects the comprehensive impact of these environmental parameters on the degree of corrosion in the rusted area of ​​the iron facility.

[0036] As an example, the existing principal component analysis algorithm can be used to extract the spectral features of the spectral detection data, and the chemical composition complexity index of the rusted area can be obtained by assigning values ​​according to the importance of the spectral features. For example, assume that there is a series of spectral detection data of the rusted area of ​​the target metal parts, and each data point contains spectral intensity values ​​at multiple wavelengths. First, these data are preprocessed, including removing outliers and performing normalization. For example, the spectral intensity value can be normalized to the interval [0,1] for subsequent analysis. The spectral features of the spectral detection data are extracted by the principal component analysis (PCA) algorithm: for the preprocessed spectral data matrix (assuming that the number of rows of the matrix is ​​the number of samples and the number of columns is the number of wavelengths), its covariance matrix is ​​calculated. The covariance matrix reflects the correlation between different wavelengths. The covariance matrix is ​​subjected to eigenvalue decomposition to obtain eigenvalues ​​and corresponding eigenvectors. The eigenvalue represents the variance in the direction of the corresponding eigenvector. The eigenvectors are arranged in descending order of eigenvalues. Usually, the first few eigenvectors with larger eigenvalues ​​are selected as principal components, and these principal components can explain most of the data variance. Assume that the first k principal components are selected, and project the original data onto these k principal components to obtain the spectral data after dimension reduction. In addition, the importance of the principal component is determined according to the size of its eigenvalue. The larger the eigenvalue, the greater the contribution of the corresponding principal component in explaining the data variance, and therefore it can be given a higher importance. For example, the eigenvalues ​​can be normalized so that their sum is 1. Then, the proportion of each eigenvalue to the sum of the total eigenvalues ​​can be used as the importance weight of the corresponding principal component. Calculate the chemical composition complexity index: For the spectral data of each sample after dimension reduction, a weighted sum is taken according to the importance weights of the principal components to obtain a comprehensive value. This comprehensive value can be used as the chemical composition complexity index of the sample. Assume that the spectral data after dimension reduction is ,in The sample is in The projection value on the principal component, the importance weight of the principal component is , then the chemical composition complexity index It can be calculated as: .

[0037] See also Figure 2 , is a schematic diagram of a structure of an intelligent rust removal control device for a laser cleaning machine based on the degree of metal rust provided by an embodiment of the present invention. The intelligent rust removal control device for a laser cleaning machine based on the degree of metal rust comprises: The first control module 10 is used to control the camera to take a picture of the surface of the target metal part to obtain a metal surface image; A first analysis module 11 is used to perform image analysis on the metal surface image to identify the rusted area of ​​the target metal part; A second analysis module 12 is used to perform image analysis on the rusted area to determine the rust roughness level of the rusted area; A second control module 13 is used to collect environmental parameters of the application scenario of the target metal part through a sensor, and calculate the sum of environmental impact indexes affecting the degree of corrosion of the rusted area according to the environmental parameters; A third control module 14 is used to control the spectrum analyzer to detect the rusted area of ​​the target metal part to obtain spectrum detection data; A third analysis module 15 is used to analyze the spectral detection data, determine the corrosion type of the rusted area of ​​the target metal part, and analyze and obtain the chemical composition complexity index of the rusted area; A calculation module 16 is used to calculate a comprehensive corrosion degree index of the corrosion area according to a weighted sum of the chemical composition complexity index of the corrosion area, the corrosion roughness grade, the corrosion type and an environmental impact index affecting the corrosion degree of the corrosion area; A determination module 17, for determining laser cleaning parameters of a laser cleaning machine according to the comprehensive corrosion degree index; The fourth control module 18 is used to control the laser cleaning machine to perform laser rust removal on the rusted area of ​​the target metal part according to the determined laser cleaning parameters.

[0038] In an embodiment of the present invention, firstly, a camera is controlled to take a photo of the surface of a target metal part to obtain a metal surface image, and the image is analyzed to identify the rust area and determine the rust roughness level; then, a sensor is used to collect environmental parameters of the target metal part application scenario, and the sum of environmental impact indexes is calculated; at the same time, a spectrum analyzer is controlled to detect the rust area to obtain spectrum detection data, and the rust type is analyzed to determine the chemical composition complexity index; then, the chemical composition complexity index, the rust roughness level, the rust type, and the sum of the environmental impact index are comprehensively calculated to obtain a comprehensive rust degree index; then, according to the comprehensive rust degree index, the laser cleaning parameters of the laser cleaning machine are determined, and finally, the laser cleaning machine is controlled to perform laser rust removal on the rusted area of ​​the target metal part. The embodiment of the present invention effectively solves the problem that the existing laser rust removal technology lacks accurate judgment and intelligent control of the metal rust degree, determines the comprehensive rust degree index through multi-dimensional analysis, and then accurately sets the laser cleaning parameters to achieve efficient and accurate rust removal of the rusted area of ​​the target metal part, while avoiding damage to the metal matrix caused by excessive rust removal or incomplete rust removal, and fully considering the influence of environmental factors on the rust degree.

[0039] As an improvement of the above solution, the second analysis module is specifically used for: Cutting the rusted area in the metal surface image to obtain a rusted area image; A median filtering algorithm is used to perform denoising on the rusted area image, and a histogram equalization algorithm is used to enhance the contrast of the rusted area image, so as to obtain a preprocessed rusted area image; The rust roughness level of the preprocessed rust area image is calculated by the following formula: ; in, is the total number of pixels in the preprocessed rusted area image; is the neighborhood size; It's pixels Gray value of is the average gray value of the rusted area; is the fractal dimension, which is calculated using the box counting method, which involves overlaying the preprocessed rusted area image on grids of different sizes, counting the number of non-empty boxes, and then calculating the fractal dimension through logarithmic regression analysis; and Adjust the parameters through experiments. Specifically, an initial value is given first, and then the matching degree between the calculated rust roughness grade and the actual rust situation is observed, and the parameter value is gradually adjusted until the result that meets the user's needs is obtained; It is the characteristic value of the grayscale gradient used to describe the surface roughness. Specifically, the gradient amplitude of the pixel grayscale value is calculated as a characteristic value. The gradient amplitude is obtained by calculating the grayscale difference between each pixel and its neighboring pixels in the preprocessed rust area image. is the total number of eigenvalues ​​of the grayscale gradient.

[0040] As an improvement of the above solution, the third analysis module is specifically used for: Extracting features from the spectrum detection data to obtain peak features, band features, and slope features of the spectrum data; The peak feature, the band feature and the slope feature are fused, and the fused spectral feature is calculated by the following feature fusion formula: ;in, is the vector of peak features, and the vector set of peak features is , Indicates A vector of peak features; is the vector of band features, and the vector set of band features is , Indicates A vector of band features; is the vector of slope characteristics, and the vector set of slope characteristics is , Indicates A vector of slope characteristics; are weight coefficients, the sum of which is 1; is the bias term; They are respectively nonlinear transformation functions of the vector of peak features, the vector of band features, and the vector of slope features; The Hadamard product of the peak, band, and slope feature vectors is used to capture the interactive information between different features by element-by-element multiplication; The fused spectral features are input into a corrosion type classification model of a convolutional neural network, and the corrosion type of the corroded area of ​​the target metal part is output.

[0041] As an improvement of the above solution, the calculation module is specifically used for: Determining the degree of corrosion impact of the corrosion type according to the corrosion type of the corrosion area; According to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust impact degree of the rust type and the sum of the environmental impact indexes affecting the rust degree of the rusted area, the comprehensive rust degree index of the rusted area is calculated by the following formula: ; in, are weight coefficients, the sum of which is 1; is the rust roughness grade of the rusted area; It is the preset adjustment index for the rust roughness level; is the degree of rust influence of the rust type; It is a preset adjustment index for the degree of rust influence of the rust type, which is used to adjust its influence weight in the comprehensive rust degree index according to the actual situation; is the chemical composition complexity index of the rusted area; It is a preset adjustment index of the chemical composition complexity index to adapt to different metal materials and corrosion environments; is the sum of the environmental impact indices affecting the degree of corrosion in the corroded area; is the number of environmental parameters; It is An environmental parameter environmental impact index of the degree of corrosion of the corrosion area.

[0042] It can be understood that the solution contents of the relevant embodiments of the intelligent rust removal control device of the laser cleaning machine based on the degree of metal corrosion can correspond to the relevant embodiments of the intelligent rust removal control method of the laser cleaning machine based on the degree of metal corrosion mentioned above, which will not be repeated here.

[0043] See also Figure 3, is a schematic diagram of an intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion provided by an embodiment of the present invention. The intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion of this embodiment includes: a processor 100, a memory 101, and a computer program stored in the memory and executable on the processor, such as an intelligent rust removal control program for a laser cleaning machine based on the degree of metal corrosion. When the processor executes the computer program, the steps in the above-mentioned embodiments of the intelligent rust removal control method for a laser cleaning machine based on the degree of metal corrosion are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented. See Figure 4 , is a schematic diagram of an intelligent rust removal control system for a laser cleaning machine based on the degree of metal rust provided by an embodiment of the present invention. The intelligent rust removal control system for a laser cleaning machine based on the degree of metal rust comprises a camera 1, a spectrum analyzer 2, and an intelligent rust removal control device 3 for a laser cleaning machine based on the degree of metal rust described in the above-mentioned embodiment of the invention; the intelligent rust removal control device 3 for a laser cleaning machine is connected to the camera 1 in communication, and is connected to the spectrum analyzer 2 in communication.

[0044] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the intelligent rust removal control device for laser cleaning machine based on metal rust degree.

[0045] The intelligent rust removal control device for the laser cleaning machine based on the degree of metal corrosion can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The intelligent rust removal control device for the laser cleaning machine based on the degree of metal corrosion may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the schematic diagram is only an example of the intelligent rust removal control device for the laser cleaning machine based on the degree of metal corrosion, and does not constitute a limitation on the intelligent rust removal control device for the laser cleaning machine based on the degree of metal corrosion. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the intelligent rust removal control device for the laser cleaning machine based on the degree of metal corrosion may also include input and output devices, network access devices, buses, etc.

[0046] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the intelligent rust removal control device for laser cleaning machine based on the degree of metal rust, and uses various interfaces and lines to connect the various parts of the intelligent rust removal control device for laser cleaning machine based on the degree of metal rust.

[0047] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the intelligent rust removal control device of the laser cleaning machine based on the degree of metal corrosion by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0048] Wherein, if the module / unit integrated in the intelligent rust removal control device of the laser cleaning machine based on the degree of metal corrosion is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0049] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0050] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An intelligent rust removal control method for a laser cleaning machine based on the degree of metal corrosion, characterized in that: include: Controlling the camera to take a picture of the surface of the target metal part to obtain a metal surface image; Performing image analysis on the metal surface image to identify the rusted area of ​​the target metal part; Performing image analysis on the corroded area to determine the corrosion roughness level of the corroded area; Collecting environmental parameters of the application scenario of the target metal part through a sensor, and calculating the sum of environmental impact indexes affecting the degree of corrosion of the rusted area according to the environmental parameters; Controlling a spectrum analyzer to detect the rusted area of ​​the target metal part to obtain spectrum detection data; Analyzing the spectral detection data to determine the corrosion type of the corrosion area of ​​the target metal part, and analyzing to obtain a chemical composition complexity index of the corrosion area; Calculate the comprehensive corrosion degree index of the rusted area according to the weighted sum of the chemical composition complexity index of the rusted area, the rust roughness grade, the rust type and the environmental impact index affecting the corrosion degree of the rusted area; Determining laser cleaning parameters of a laser cleaning machine according to the comprehensive corrosion degree index; According to the determined laser cleaning parameters, the laser cleaning machine is controlled to perform laser rust removal on the rusted area of ​​the target metal part.

2. The intelligent rust removal control method of a laser cleaning machine based on the degree of metal corrosion according to claim 1, characterized in that: The performing image analysis on the corroded area to determine the corrosion roughness level of the corroded area includes: Cutting the rusted area in the metal surface image to obtain a rusted area image; A median filtering algorithm is used to perform denoising on the rusted area image, and a histogram equalization algorithm is used to enhance the contrast of the rusted area image, so as to obtain a preprocessed rusted area image; The rust roughness level of the preprocessed rust area image is calculated by the following formula: ; in, is the total number of pixels in the preprocessed rusted area image; is the neighborhood size; It's pixels Gray value of is the average gray value of the rusted area; is the fractal dimension, which is calculated using the box counting method, which involves overlaying the preprocessed rusted area image on grids of different sizes, counting the number of non-empty boxes, and then calculating the fractal dimension through logarithmic regression analysis; and Adjust the parameters through experiments. Specifically, an initial value is given first, and then the matching degree between the calculated rust roughness grade and the actual rust situation is observed, and the parameter value is gradually adjusted until the result that meets the user's needs is obtained; It is the characteristic value of the grayscale gradient used to describe the surface roughness. Specifically, the gradient amplitude of the pixel grayscale value is calculated as a characteristic value. The gradient amplitude is obtained by calculating the grayscale difference between each pixel and its neighboring pixels in the preprocessed rust area image. is the total number of eigenvalues ​​of the grayscale gradient.

3. The intelligent rust removal control method of a laser cleaning machine based on the degree of metal corrosion according to claim 1, characterized in that: The analyzing the spectral detection data to determine the corrosion type of the rusted area of ​​the target metal part includes: Extracting features from the spectrum detection data to obtain peak features, band features, and slope features of the spectrum data; The peak feature, the band feature and the slope feature are fused, and the fused spectral feature is calculated by the following feature fusion formula: ;in, is the vector of peak features, and the vector set of peak features is , Indicates A vector of peak features; is the vector of band features, and the vector set of band features is , Indicates A vector of band features; is the vector of slope characteristics, and the vector set of slope characteristics is , Indicates A vector of slope characteristics; are weight coefficients, the sum of which is 1; is the bias term; They are respectively nonlinear transformation functions of the vector of peak features, the vector of band features, and the vector of slope features; The Hadamard product of the peak, band, and slope feature vectors is used to capture the interactive information between different features by element-by-element multiplication; The fused spectral features are input into a corrosion type classification model of a convolutional neural network, and the corrosion type of the corroded area of ​​the target metal part is output.

4. The intelligent rust removal control method of a laser cleaning machine based on the degree of metal corrosion according to claim 1, characterized in that: The weighted summation according to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust type and the environmental impact index affecting the rust degree of the rusted area includes: Determining the degree of corrosion impact of the corrosion type according to the corrosion type of the corrosion area; According to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust impact degree of the rust type and the sum of the environmental impact indexes affecting the rust degree of the rusted area, the comprehensive rust degree index of the rusted area is calculated by the following formula: ; in, are weight coefficients, the sum of which is 1; is the rust roughness grade of the rusted area; It is the preset adjustment index for the rust roughness level; is the degree of rust influence of the rust type; It is a preset adjustment index for the degree of rust influence of the rust type, which is used to adjust its influence weight in the comprehensive rust degree index according to the actual situation; is the chemical composition complexity index of the rusted area; It is a preset adjustment index of the chemical composition complexity index to adapt to different metal materials and corrosion environments; is the sum of the environmental impact indices affecting the degree of corrosion in the corroded area; is the number of environmental parameters; It is An environmental parameter environmental impact index of the degree of corrosion of the corrosion area.

5. An intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion, characterized in that: include: A first control module is used to control the camera to take a picture of the surface of the target metal part to obtain a metal surface image; A first analysis module, configured to perform image analysis on the metal surface image to identify the rusted area of ​​the target metal part; A second analysis module is used to perform image analysis on the rusted area to determine the rust roughness level of the rusted area; A second control module is used to collect environmental parameters of the application scenario of the target metal part through a sensor, and calculate the sum of environmental impact indexes affecting the degree of corrosion of the rusted area according to the environmental parameters; A third control module is used to control the spectrum analyzer to detect the rusted area of ​​the target metal part to obtain spectrum detection data; A third analysis module is used to analyze the spectral detection data, determine the corrosion type of the rusted area of ​​the target metal part, and analyze and obtain the chemical composition complexity index of the rusted area; A calculation module, used to calculate a comprehensive corrosion degree index of the corrosion area according to a weighted sum of the chemical composition complexity index of the corrosion area, the corrosion roughness grade, the corrosion type and an environmental impact index affecting the corrosion degree of the corrosion area; A determination module, used to determine the laser cleaning parameters of the laser cleaning machine according to the comprehensive corrosion degree index; The fourth control module is used to control the laser cleaning machine to perform laser rust removal on the rusted area of ​​the target metal part according to the determined laser cleaning parameters.

6. The intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion according to claim 5, characterized in that: The second analysis module is specifically used for: Cutting the rusted area in the metal surface image to obtain a rusted area image; A median filtering algorithm is used to perform denoising on the rusted area image, and a histogram equalization algorithm is used to enhance the contrast of the rusted area image, so as to obtain a preprocessed rusted area image; The rust roughness level of the preprocessed rust area image is calculated by the following formula: ; in, is the total number of pixels in the preprocessed rusted area image; is the neighborhood size; It's pixels Gray value of is the average gray value of the rusted area; is the fractal dimension, which is calculated using the box counting method, which involves overlaying the preprocessed rusted area image on grids of different sizes, counting the number of non-empty boxes, and then calculating the fractal dimension through logarithmic regression analysis; and Adjust the parameters through experiments. Specifically, an initial value is given first, and then the matching degree between the calculated rust roughness grade and the actual rust situation is observed, and the parameter value is gradually adjusted until the result that meets the user's needs is obtained; It is the characteristic value of the grayscale gradient used to describe the surface roughness. Specifically, the gradient amplitude of the pixel grayscale value is calculated as a characteristic value. The gradient amplitude is obtained by calculating the grayscale difference between each pixel and its neighboring pixels in the preprocessed rust area image. is the total number of eigenvalues ​​of the grayscale gradient.

7. The intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion as claimed in claim 5, characterized in that: The third analysis module is specifically used for: Extracting features from the spectrum detection data to obtain peak features, band features, and slope features of the spectrum data; The peak feature, the band feature and the slope feature are fused, and the fused spectral feature is calculated by the following feature fusion formula: ;in, is the vector of peak features, and the vector set of peak features is , Indicates A vector of peak features; is the vector of band features, and the vector set of band features is , Indicates A vector of band features; is the vector of slope characteristics, and the vector set of slope characteristics is , Indicates A vector of slope characteristics; are weight coefficients, the sum of which is 1; is the bias term; They are respectively nonlinear transformation functions of the vector of peak features, the vector of band features, and the vector of slope features; The Hadamard product of the peak, band, and slope feature vectors is used to capture the interactive information between different features by element-by-element multiplication; The fused spectral features are input into a corrosion type classification model of a convolutional neural network, and the corrosion type of the corroded area of ​​the target metal part is output.

8. The intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion as claimed in claim 5, characterized in that: The calculation module is specifically used for: Determining the degree of corrosion impact of the corrosion type according to the corrosion type of the corrosion area; According to the chemical composition complexity index of the rusted area, the rust roughness grade, the rust impact degree of the rust type and the sum of the environmental impact indexes affecting the rust degree of the rusted area, the comprehensive rust degree index of the rusted area is calculated by the following formula: ; in, are weight coefficients, the sum of which is 1; is the rust roughness grade of the rusted area; It is the preset adjustment index for the rust roughness level; is the degree of rust influence of the rust type; It is a preset adjustment index for the degree of rust influence of the rust type, which is used to adjust its influence weight in the comprehensive rust degree index according to the actual situation; is the chemical composition complexity index of the rusted area; It is a preset adjustment index of the chemical composition complexity index to adapt to different metal materials and corrosion environments; is the sum of the environmental impact indices affecting the degree of corrosion in the corroded area; is the number of environmental parameters; It is An environmental parameter environmental impact index of the degree of corrosion of the corrosion area.

9. An intelligent rust removal control device for a laser cleaning machine based on the degree of metal corrosion, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the intelligent rust removal control method of a laser cleaning machine based on the degree of metal corrosion as described in any one of claims 1 to 4.

10. An intelligent rust removal control system for a laser cleaning machine based on the degree of metal corrosion, characterized in that: It includes a camera, a spectrum analyzer and the intelligent rust removal control device of a laser cleaning machine based on the degree of metal corrosion as described in claim 9; the intelligent rust removal control device of the laser cleaning machine is communicatively connected to the camera and is communicatively connected to the spectrum analyzer.

Citation Information

Patent Citations

  • Method for evaluating corrosion degree of reinforcement of concrete member

    CN110310258A

  • Pulse laser rust removal method, equipment, storage medium and device

    CN115430917A

  • Rust layer analysis method based on terahertz time-domain spectroscopy

    CN116879152A

  • Steel structure durability evaluation method, system and device

    CN117760952A

  • Line hardware corrosion defect detection method and system based on cloud-edge collaboration, and medium

    CN117788436A

Cited By

  • Laser cleaning method for surface of metal part

    CN119838959A

  • Rust cleaning method and rust cleaning system for surface of electrical equipment

    CN120644420A

  • Window cleaning robot and method for laser decontamination

    CN120884215A

  • Intelligent laser self-adaptive rust removal system and method based on machine vision

    CN121060900A