An automatic cutting processing system based on aluminum alloy production

Abstract

The present application relates to the technical field of computer-aided design aluminum alloy automatic cutting, in particular to an automatic cutting processing system based on aluminum alloy production, comprising: conveying aluminum alloy to a specified cutting area and acquiring multi-angle images of the surface of the aluminum alloy; extracting features from the multi-angle images of the surface of the aluminum alloy and inputting the extracted features into a pre-trained aluminum alloy cutting parameter calculation model for solving; determining whether the specified cutting area needs to be cut according to the solving result, if not, conveying the aluminum alloy to the next specified cutting area; if yes, transmitting the solving result to a cutting device control system; adjusting the cutting device according to the cutting parameters in the solving result by the cutting device control system, and executing cutting on the aluminum alloy until the cutting is completed.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of automatic cutting of aluminum alloy through computer-aided design, in particular to an automatic cutting processing system based on aluminum alloy production. BACKGROUND

[0002] Aluminum alloy is widely used in aerospace, automobile manufacturing and construction due to its light weight, high strength and corrosion resistance. However, the cutting processing of aluminum alloy has always been a challenge for the manufacturing industry. With the development of industry and intelligent manufacturing, the precision, efficiency and intelligence of aluminum alloy cutting are constantly improving. Traditional aluminum alloy cutting technology mainly relies on manual experience and fixed parameter setting, which has many defects. On the one hand, manual judgment and parameter adjustment are easily affected by subjective factors, making it difficult to ensure the consistency of cutting quality. On the other hand, fixed parameters cannot adapt to the changes in the surface characteristics of aluminum alloy in different batches or different regions, resulting in unstable cutting effect. Traditional aluminum alloy cutting technology cannot adapt to the complex and variable surface characteristics of aluminum alloy, which easily leads to unstable cutting quality of aluminum alloy, material waste and low production efficiency. Therefore, developing an intelligent system that can automatically adjust cutting parameters according to the surface characteristics of aluminum alloy has become a research hotspot to meet the needs of modern manufacturing industry for high-quality and high-efficiency aluminum alloy processing. SUMMARY

[0003] The purpose of the present application is to provide an automatic cutting processing system based on aluminum alloy production, which can dynamically calculate cutting requirements and parameters according to the specific properties of aluminum alloy material through image feature extraction and aluminum alloy cutting parameter calculation model, significantly improving cutting precision and efficiency, and real-time adjustment of cutting parameters in different situations can reduce material loss, achieve lower operating costs and higher quality control, and is easy to integrate with existing production systems, promoting the intelligentization and automation of the overall manufacturing process.

[0004] The present application is realized by the following technical solutions:

[0005] An automatic cutting processing system based on aluminum alloy production, comprising:

[0006] A collection unit that transports aluminum alloy to a designated cutting area and acquires multi-angle images of the aluminum alloy surface;

[0007] A solving unit that extracts features from the multi-angle images of the aluminum alloy surface and inputs the extracted features into a pre-trained aluminum alloy cutting parameter calculation model for solving, determines whether the designated cutting area needs to be cut according to the solving result, if not, transports the aluminum alloy to the next designated cutting area; if yes, transmits the solving result to the cutting device control system;

[0008] The regulating unit adjusts the cutting device according to the cutting parameters in the solution result, and performs cutting on the aluminum alloy until the cutting is completed.

[0009] Optionally, the multi-angle image of the aluminum alloy surface is subjected to feature extraction to obtain surface texture features, surface roughness features, surface edge features, surface corner features and surface color features of the aluminum alloy.

[0010] Optionally, the surface texture features of the aluminum alloy have a calculation formula as follows:

[0011]

[0012] wherein T is the surface texture features of the aluminum alloy, is the number of times that the gray values i and j in the mth angle aluminum alloy surface image appear together at a specific distance and direction, M is the number of the multi-angle aluminum alloy surface images, m is the index of the multi-angle aluminum alloy surface images, and i and j are gray values.

[0013] Optionally, the surface roughness features of the aluminum alloy have a calculation formula as follows:

[0014]

[0015] wherein R is the surface roughness features of the aluminum alloy, M is the number of the multi-angle aluminum alloy surface images, P is the number of neighborhood pixels, is the index of the neighborhood pixels, are the gray values of the neighborhood and center pixels of the mth angle aluminum alloy surface image, respectively, is a threshold function.

[0016] Optionally, the surface edge features of the aluminum alloy include:

[0017] The gradients of the mth angle aluminum alloy surface image in the x direction and the y direction are solved to obtain a first gradient and a second gradient;

[0018] The surface edge features of the aluminum alloy are calculated by comprehensively considering the first gradient and the second gradient;

[0019] The calculation formula of the first gradient is as follows:

[0020]

[0021] The calculation formula of the second gradient is as follows:

[0022]

[0023] The calculation formula of the surface edge features of the aluminum alloy calculated by comprehensively considering the first gradient and the second gradient is as follows:

[0024]

[0025] wherein E is the surface edge feature of the aluminum alloy, M is the number of multi-angle images of the aluminum alloy surface, is the two-dimensional array of the aluminum alloy surface image at the mth angle, is the first gradient, is the second gradient.

[0026] Optionally, the surface corner feature of the aluminum alloy has a calculation formula as follows:

[0027]

[0028] wherein C is the surface corner feature of the aluminum alloy, M is the number of multi-angle images of the aluminum alloy surface, and k is an empirical constant, is the determinant, is the trace, i.e., the sum of the main diagonal elements.

[0029] Optionally, the surface color feature of the aluminum alloy has a calculation formula as follows:

[0030]

[0031]

[0032]

[0033] wherein H, S, and V are the comprehensive hue, saturation, and value features of the aluminum alloy, M is the number of multi-angle images of the aluminum alloy surface, and N is the number of pixels of the aluminum alloy surface image at each angle, are the HSV values of the ith pixel in the aluminum alloy surface image at the mth angle, respectively.

[0034] Optionally, the aluminum alloy cutting parameter calculation model has a calculation formula as follows, with the maximum cutting quality as the optimization objective:

[0035]

[0036]

[0037]

[0038]

[0039]

[0040] wherein, is the objective function, is the set of all training parameters in the aluminum alloy cutting parameter calculation model, including , , and N is the total number of samples, i is the sample index, K is the number of cut quality indicators, and k is the index of the cut quality indicator. It is the weight of the k-th cutting quality index. It is the input feature vector of the i-th sample. It is the parameter matrix of the k-th cutting quality index. It is the cutting parameter vector of the i-th sample. It is the dimension of the feature vector. It is the L2 regularization coefficient. It is the L2 norm of the cut parameter vector. This is the weight matrix of the output layer of the aluminum alloy cutting parameter calculation model. This is the output of the last layer of the aluminum alloy cutting parameter calculation model. It is the bias vector of the output layer of the aluminum alloy cutting parameter calculation model. It is the index of the aluminum alloy cutting parameter calculation model layer. It is the first The feature matrix of the aluminum alloy cutting parameter calculation model. It is the first The weight matrix of the calculation model for cutting parameters of multilayer aluminum alloy. It is the adjacency matrix after adding self-joins. yes The degree matrix, It is the input feature matrix, which includes the feature vectors of all samples. These are the surface texture features, surface roughness features, surface edge features, surface corner features, hue values, saturation values, and lightness values ​​in the HSV color space for the i-th sample, respectively. ReLU is the modified linear unit activation function, and tanh is the hyperbolic tangent function.

[0041] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0042] This invention uses image feature extraction and an aluminum alloy cutting parameter calculation model to dynamically calculate cutting requirements and parameters based on the specific properties of the aluminum alloy material, significantly improving cutting accuracy and efficiency. Furthermore, real-time adjustment of cutting parameters under different conditions can reduce material loss, achieving lower operating costs and higher quality control. It is easy to integrate with existing production systems, promoting the intelligence and automation of the overall manufacturing process. Attached Figure Description

[0043] Figure 1A logic diagram of an automatic cutting processing system based on aluminum alloy production is provided. DETAILED DESCRIPTION

[0044] For the purpose, technical solutions and advantages of the present application to be clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, what is described is part of the present application, not the whole. The components of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0045] Referring to Figure 1 as shown, Figure 1 A logic diagram of an automatic cutting processing system based on aluminum alloy production is provided.

[0046] In an embodiment, an automatic cutting processing system based on aluminum alloy production comprises:

[0047] A collection unit transports aluminum alloy to a designated cutting area and acquires multi-angle images of the surface of the aluminum alloy;

[0048] A solving unit extracts features from the multi-angle images of the surface of the aluminum alloy and inputs the extracted features into a pre-trained aluminum alloy cutting parameter calculation model for solving. According to the solving result, it is determined whether the designated cutting area needs to be cut. If not, the aluminum alloy is transported to the next designated cutting area. If yes, the solving result is transmitted to a cutting device control system;

[0049] A regulating unit adjusts the cutting device according to the cutting parameters in the solving result, and performs cutting on the aluminum alloy until the cutting is completed.

[0050] The embodiment can be integrated in an intelligent system, which includes an aluminum alloy cutting parameter calculation model, an image acquisition system, a data processing unit, a cutting device control system, an aluminum alloy conveying system, and a human-computer interaction interface. In the application of the embodiment, the aluminum alloy material is conveyed to the designated position through the conveyor belt system, and the aluminum alloy material is ensured to be stable and accurately positioned during the conveying process. After reaching the designated area, the high-resolution camera captures the aluminum alloy surface image from multiple angles to ensure comprehensive coverage. Then, the collected aluminum alloy image is processed for noise reduction, contrast enhancement, and other processes, while the key features are extracted. The extracted key features are input into the trained aluminum alloy cutting parameter calculation model. Based on the output results of the aluminum alloy cutting parameter calculation model, it is determined whether the current position needs to be cut. If not, it returns to the conveying step and moves to the next position. If cutting is required, the accurate cutting parameters are calculated according to the output of the aluminum alloy cutting parameter calculation model, and the calculated parameters are transmitted to the cutting device control system. The control system adjusts the position and settings of the cutting device, starts the cutting device, and performs the actual cutting operation. The cutting process is monitored in real time to ensure safety and accuracy.

[0051] In the implementation process, the aluminum alloy surface multi-angle image is subjected to feature extraction to obtain the surface texture feature, surface roughness feature, surface edge feature, surface corner feature, and surface color feature of the aluminum alloy.

[0052] The surface texture feature of the aluminum alloy has a calculation formula as follows:

[0053]

[0054] wherein T is the surface texture feature of the aluminum alloy, is the number of times that the gray values i and j in the mth angle aluminum alloy surface image appear together at a certain distance and direction, M is the number of aluminum alloy surface multi-angle images, m is the index of the aluminum alloy surface multi-angle image, and i and j are gray values.

[0055] The surface roughness feature of the aluminum alloy has a calculation formula as follows:

[0056]

[0057] wherein R is the surface roughness feature of the aluminum alloy, M is the number of aluminum alloy surface multi-angle images, P is the number of neighborhood pixels, is the index of the neighborhood pixel, are the gray values of the neighborhood and center pixels of the mth angle aluminum alloy surface image, is a threshold function.

[0058] The surface edge feature of the aluminum alloy includes:

[0059] Solving the gradients of the aluminum alloy surface image m at each angle in the x direction and the y direction to obtain a first gradient and a second gradient;

[0060] The surface edge feature of the aluminum alloy is calculated by synthesizing the first gradient and the second gradient;

[0061] The calculation formula of the first gradient is:

[0062]

[0063] The calculation formula of the second gradient is:

[0064]

[0065] The surface edge feature of the aluminum alloy is calculated by synthesizing the first gradient and the second gradient, and the calculation formula is:

[0066]

[0067] Wherein, E is the surface edge feature of the aluminum alloy, M is the number of multi-angle images of the aluminum alloy surface, is the two-dimensional array of the aluminum alloy surface image at the mth angle, is the first gradient, is the second gradient.

[0068] The calculation formula of the surface corner feature of the aluminum alloy is:

[0069]

[0070] Wherein, C is the surface corner feature of the aluminum alloy, M is the number of multi-angle images of the aluminum alloy surface, and k is an empirical constant, is the determinant, is the trace, that is, the sum of the main diagonal elements.

[0071] The calculation formula of the surface color feature of the aluminum alloy is:

[0072]

[0073]

[0074]

[0075] Wherein, H, S and V are the comprehensive hue, saturation and lightness features of the aluminum alloy, M is the number of multi-angle images of the aluminum alloy surface, and N is the number of pixels of the aluminum alloy surface image at each angle, are respectively the HSV values of the ith pixel in the aluminum alloy surface image at the mth angle.

[0076] In further implementation of the embodiment, the aluminum alloy cutting parameter calculation model constructed in the embodiment is specifically constructed based on the GCN model, and the construction of the aluminum alloy cutting parameter calculation model is as follows: defining input features ; constructing an adjacency matrix A to represent the relationship between the features, calculating , I is an identity matrix, and a degree matrix is calculated; L GCN layers are defined, and calculation is performed on each layer: , the weight matrix is initialized; the output layer weight and bias are defined, and the cutting parameter is calculated: ; a target function with the optimization objective of maximizing the cutting quality is defined.

[0077] For training of the aluminum alloy cutting parameter calculation model, historical aluminum alloy data is mainly applied, which includes historical aluminum alloy surface feature data and corresponding optimal cutting parameters, and a training set and a validation set are divided. The specific training process is to evaluate the performance of the aluminum alloy cutting parameter calculation model after forward propagation and back propagation in turn, and output the trained aluminum alloy cutting parameter calculation model. It can be understood that this process is the standard training step of the neural network model, and the embodiment will not be described in detail.

[0078] The calculation formula of the target function of the aluminum alloy cutting parameter calculation model is:

[0079]

[0080]

[0081]

[0082]

[0083]

[0084] wherein, is the target function, is the set of all training parameters in the aluminum alloy cutting parameter calculation model, including , , and , N is the total number of samples, i is the sample index, K is the number of cutting quality indexes, k is the index of the cutting quality index, is the weight of the kth cutting quality index, is the input feature vector of the ith sample, is the parameter matrix of the kth cutting quality index, It is the cutting parameter vector of the i-th sample. It is the dimension of the feature vector. It is the L2 regularization coefficient. It is the L2 norm of the cut parameter vector. This is the weight matrix of the output layer of the aluminum alloy cutting parameter calculation model. This is the output of the last layer of the aluminum alloy cutting parameter calculation model. It is the bias vector of the output layer of the aluminum alloy cutting parameter calculation model. It is the index of the aluminum alloy cutting parameter calculation model layer. It is the first The feature matrix of the aluminum alloy cutting parameter calculation model. It is the first The weight matrix of the calculation model for cutting parameters of multilayer aluminum alloy. It is the adjacency matrix after adding self-joins. yes The degree matrix, It is the input feature matrix, which includes the feature vectors of all samples. These are the surface texture features, surface roughness features, surface edge features, surface corner features, hue values, saturation values, and lightness values ​​in the HSV color space for the i-th sample, respectively. ReLU is the modified linear unit activation function, and tanh is the hyperbolic tangent function.

[0085] In practice, the input features include surface texture, roughness, edges, corners, and H, S, and V values ​​in the HSV color space. These input features are processed by the aluminum alloy cutting parameter calculation model to generate cutting parameters. The cutting parameters, together with the input features, are used to calculate the cutting quality score. The objective function defined in this embodiment comprehensively considers the cutting quality score and parameter complexity. By maximizing this function, the model parameters are optimized. It fully considers the characteristics of the aluminum alloy cutting process and the optimization requirements of the machine learning model, providing a theoretical basis for high-quality and high-efficiency aluminum alloy cutting parameter calculation.

[0086] The above are merely preferred embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An automated cutting and processing system based on aluminum alloy production, characterized in that, include: The acquisition unit transports the aluminum alloy to the designated cutting area and acquires multi-angle images of the aluminum alloy surface; The solving unit extracts features from multi-angle images of the aluminum alloy surface and inputs the extracted features into a pre-trained aluminum alloy cutting parameter calculation model for solving. Based on the solution results, it determines whether the specified cutting area needs to be cut. If not, it sends the aluminum alloy to the next specified cutting area. If so, the solution result will be transmitted to the cutting device control system; The control unit adjusts the cutting device according to the cutting parameters in the solution results, and performs cutting on the aluminum alloy until the cutting is completed. The aluminum alloy cutting parameter calculation model specifically aims to maximize cutting quality, and its calculation formula is as follows: in, It is the objective function. It is the set of all training parameters in the aluminum alloy cutting parameter calculation model, including , , and N is the total number of samples, i is the sample index, K is the number of cut quality indicators, and k is the index of the cut quality indicator. It is the weight of the k-th cutting quality index. It is the input feature vector of the i-th sample. It is the parameter matrix of the k-th cutting quality index. It is the cutting parameter vector of the i-th sample. It is the dimension of the feature vector. It is the L2 regularization coefficient. It is the L2 norm of the cut parameter vector. This is the weight matrix of the output layer of the aluminum alloy cutting parameter calculation model. This is the output of the last layer of the aluminum alloy cutting parameter calculation model. It is the bias vector of the output layer of the aluminum alloy cutting parameter calculation model. It is the index of the aluminum alloy cutting parameter calculation model layer. It is the first The feature matrix of the aluminum alloy cutting parameter calculation model. It is the first The weight matrix of the calculation model for cutting parameters of multilayer aluminum alloy. It is the adjacency matrix after adding self-joins. yes The degree matrix, It is the input feature matrix, which includes the feature vectors of all samples. These are the surface texture features, surface roughness features, surface edge features, surface corner features, hue values, saturation values, and lightness values ​​in the HSV color space for the i-th sample, respectively. ReLU is the modified linear unit activation function, and tanh is the hyperbolic tangent function.

2. The automatic cutting and processing system based on aluminum alloy production according to claim 1, characterized in that, The process involves extracting features from multi-angle images of the aluminum alloy surface to obtain surface texture features, surface roughness features, surface edge features, surface corner features, and surface color features.

3. The automatic cutting and processing system based on aluminum alloy production according to claim 2, characterized in that, The surface texture characteristics of the aluminum alloy are calculated using the following formula: Where T represents the surface texture characteristics of the aluminum alloy. It represents the number of times grayscale values ​​i and j appear together at a specific distance and direction in the m-th angle image of the aluminum alloy surface. M is the number of multi-angle images of the aluminum alloy surface, m is the index of the multi-angle image of the aluminum alloy surface, and i and j are the grayscale values.

4. The automatic cutting and processing system based on aluminum alloy production according to claim 3, characterized in that, The surface roughness characteristics of the aluminum alloy are calculated using the following formula: Where R represents the surface roughness feature of the aluminum alloy, M represents the number of multi-angle images of the aluminum alloy surface, and P represents the number of neighboring pixels. The index of the neighboring pixels. These are the grayscale values ​​of the neighborhood and center pixel of the aluminum alloy surface image at the m-th angle, respectively. This is a threshold function.

5. The automatic cutting and processing system based on aluminum alloy production according to claim 4, characterized in that, The surface edge features of the aluminum alloy include: Solve for the gradients of the aluminum alloy surface image m at various angles in the x and y directions to obtain the first gradient and the second gradient; The surface edge features of the aluminum alloy are calculated by combining the first and second gradients. The formula for calculating the first gradient is: The formula for calculating the second gradient is: The formula for calculating the surface edge features of aluminum alloys by combining the first and second gradients is as follows: Where E represents the surface edge features of the aluminum alloy, and M represents the number of multi-angle images of the aluminum alloy surface. It is a two-dimensional array of aluminum alloy surface images at the m-th angle. For the first gradient, This is the second gradient.

6. The automatic cutting and processing system based on aluminum alloy production according to claim 5, characterized in that, The surface corner features of the aluminum alloy are calculated using the following formula: Where C represents the surface corner features of the aluminum alloy, M represents the number of multi-angle images of the aluminum alloy surface, and k is an empirical constant. It is a determinant. It is the trace, that is, the sum of the elements on the main diagonal.

7. The automatic cutting and processing system based on aluminum alloy production according to claim 6, characterized in that, The surface color characteristics of the aluminum alloy are calculated using the following formula: Where H, S, and V represent the overall hue, saturation, and brightness characteristics of the aluminum alloy, respectively; M is the number of multi-angle images of the aluminum alloy surface; and N is the number of pixels in each angle image of the aluminum alloy surface. These are the HSV values ​​of the i-th pixel in the aluminum alloy surface image at the m-th angle.

Images