An intelligent monitoring continuous production line for lightweight foam aluminum in aerospace

Abstract

The present invention relates to the technical field of foam aluminum material preparation, and solves the technical problems that high strength cannot be continuously prepared in the traditional foam aluminum preparation process, the pore structure can be continuously adjusted, and the sample accuracy is low. In particular, it relates to an aerospace lightweight foam aluminum intelligent monitoring continuous production line, including a smelting furnace for obtaining aluminum alloy or pure aluminum liquid at a predetermined temperature, a viscosity-enhancing furnace for performing viscosity-enhancing treatment on the aluminum alloy or pure aluminum liquid at a predetermined temperature and stirring and evenly dispersing the viscosity-enhancing agent, and a foaming furnace for holding the aluminum liquid after viscosity-enhancing, and a roller traction device for cooling and pulling the foam aluminum in a molten state and transferring it to the lateral direction for further shaping and cutting operations. The present invention realizes the functions of reducing energy consumption in the production process of the blowing method, the precise control of the porous structure of the foam aluminum, and the adjustable sample size, and provides effective support for the industrial preparation of high-strength foam aluminum and the expansion of the application range of foam aluminum.

Description

Technical Field

[0001] The invention relates to the technical field of foam aluminum material preparation, and in particular to an intelligent monitoring continuous production line for lightweight foam aluminum for aerospace. Background Art

[0002] Foamed aluminum is a new type of structural functional material that seals a large number of pores in an aluminum or aluminum alloy matrix. It is widely used in aerospace, transportation, building materials, machinery manufacturing, automobiles, etc. In order to further reduce the product size, quality consistency, energy consumption and efficiency in the production process of foamed aluminum, technicians in this field have made unremitting efforts.

[0003] At present, the air blowing foaming method is gradually becoming the mainstream preparation method of industrial foam aluminum due to its low cost and continuous preparation. The main technical principle is to continuously blow gas, such as air, nitrogen, hydrogen, etc., into the molten aluminum or aluminum alloy after viscosity enhancement treatment, cut and disperse the bubbles by stirring, form a large number of evenly dispersed bubbles in the molten aluminum or aluminum alloy, and then cool it to obtain closed-cell foam aluminum material.

[0004] However, in the existing air blowing production process, the consistency of product quality and pore structure cannot be adjusted. The foam aluminum produced in this way usually cannot obtain relatively low porosity and high strength, which limits the application of foam aluminum in the industrial field. On the other hand, after the production line is fixed, the size and pore structure of the foam aluminum samples it produces are uniform and cannot be adjusted, which also increases the cost in the subsequent preparation process of diversified foam aluminum sample needs. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent monitoring continuous production line for aerospace lightweight foam aluminum, which solves the technical problems that high strength cannot be continuously produced in the traditional foam aluminum preparation process, the pore structure cannot be continuously adjusted, and the sample accuracy is low.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace, comprising a melting furnace for obtaining aluminum alloy or pure aluminum liquid at a predetermined temperature, a viscosity-enhancing furnace for performing viscosity-enhancing treatment on the aluminum alloy or pure aluminum liquid at a predetermined temperature and stirring and uniformly dispersing the viscosity-enhancing agent, and a foaming furnace for holding the aluminum liquid after viscosity-enhancing, comprising:

[0007] Roller pulling device, used to cool and pull the molten aluminum foam, and transfer it to the transverse direction for further shaping and cutting operations;

[0008] Thermoplastic extrusion equipment is used to further shape the semi-solid aluminum foam that has been pulled and extrude aluminum foam sheets with fixed dimensions;

[0009] A fast cutting platform is arranged at the exit of the thermoplastic extrusion equipment to cut the foam aluminum sheet after the plasticizing and curing;

[0010] The multi-angle water cooling platform further cools the split aluminum foam sheet and solidifies its internal porous structure;

[0011] The intelligent feedback platform intelligently matches the foam aluminum growth rate data collected by the high-temperature laser displacement sensor with the pore structure, obtains precise control data through the artificial intelligence model, and feeds back the stirring and blowing speed of the blowing port to the CNC platform end, thereby precisely controlling the growth of the foam aluminum pore structure.

[0012] Furthermore, a high-temperature blowing device is placed in the foaming furnace for continuously injecting gas into the aluminum liquid to form bubbles. At the same time, a blowing and stirring device equipped with a high-temperature laser displacement sensor is arranged above the foaming furnace. The blowing and stirring device is used to cut the bubbles to form uniform fine foams and to make preliminary adjustments to the pore structure.

[0013] Furthermore, the blowing and stirring device is connected to the blowing port of the high-temperature blowing equipment, and the size and dispersion of the bubbles are adjusted by regulating the rotation speed and the blowing speed.

[0014] Furthermore, the smelting furnace, the viscosity-increasing furnace and the foaming furnace are connected by a rotating folding guide groove for transferring the aluminum liquid, and the aluminum liquid can be poured at a certain angle.

[0015] Furthermore, a stirring device capable of vertically rising and falling is arranged above the viscosity increasing furnace, and the speed of the stirring paddle is adjustable.

[0016] Furthermore, cooling pipes for circulating cooling water are provided in the rollers at both ends of the roller traction device to cool the surface of the foamed aluminum for easy clamping, and the distance between the rollers is adjustable to obtain semi-solid foamed aluminum of different thicknesses.

[0017] Furthermore, the roller traction device is connected to the thermoplastic extrusion equipment via a roller conveying device.

[0018] Furthermore, a drainage port is provided on one side of the foaming furnace to guide the growing foam into one end of the roller traction device.

[0019] By means of the above technical solution, the present invention provides an intelligent monitoring continuous production line for lightweight foam aluminum for aerospace, which has at least the following beneficial effects:

[0020] 1. The present invention realizes the functions of reducing energy consumption in the production process of the blowing method, precisely controlling the porous structure of the foamed aluminum, and adjusting the sample size, etc., which provides effective support for the industrial preparation of high-strength foamed aluminum and expanding the application scope of foamed aluminum.

[0021] 2. The present invention makes up for the shortcomings of low precision in adjusting the pore structure of foamed aluminum, poor mechanical properties, and low uniformity of product quality during the blowing preparation process; at the same time, in the continuous preparation process, by adjusting the distance between the rollers, the blowing speed and the rotation speed, the preparation of foamed aluminum with uniform porosity of various types can be completed on the same equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 This is a spatial schematic diagram of the intelligent monitoring of the foam aluminum production line of the present invention;

[0024] Figure 2 This is a schematic diagram of the intelligent monitoring of the foam aluminum preparation production line of the present invention.

[0025] In the figure: 1. Melting furnace; 2. Viscosity-enhancing furnace; 3. Stirring equipment; 4. Air blowing and stirring device; 5. Foaming furnace; 6. Roller traction device; 7. Thermoplastic extrusion equipment; 8. Rapid cutting platform; 9. Multi-angle water cooling platform. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0027] Please refer to Figure 1-Figure 2 , showing a specific implementation of this embodiment, when the aluminum liquid is prepared by the smelting furnace 1 and the viscosity-increasing furnace 2, it is blown in the foaming furnace 5, and the growth rate of the foam is measured by a high-temperature laser displacement sensor, and the intelligent feedback platform is fed back to the numerical control platform to accurately control the pore structure of the foam aluminum. The foam aluminum sample is further processed by the clamping device of the roller traction device 6 and the thermoplastic extrusion device 7 to obtain the plate with the target pore structure, and the thickness and length of the foam aluminum plate can be adjusted by adjusting the distance between the roller and the hot extrusion equipment. Finally, the foam aluminum plate is divided by the rapid cutting platform 8, and further cooled and solidified by the multi-angle water cooling platform 9.

[0028] This embodiment proposes an intelligent monitoring continuous production line for lightweight foam aluminum in aerospace, which realizes the functions of reducing energy consumption in the production process of blowing method, accurately controlling the porous structure of foam aluminum, and adjusting the sample size, etc., and provides effective support for the industrial preparation of high-strength foam aluminum and expanding the application range of foam aluminum. The production line includes a smelting furnace 1 for obtaining aluminum alloy or pure aluminum liquid at a predetermined temperature, a viscosity-enhancing furnace 2 for performing viscosity-enhancing treatment on the aluminum alloy or pure aluminum liquid at a predetermined temperature and stirring and uniformly dispersing the viscosity-enhancing agent, and a foaming furnace 5 for holding the aluminum liquid after viscosity-enhancing. A high-temperature blowing device for continuously injecting gas into the aluminum liquid to form bubbles is placed in the foaming furnace 5, and a blowing stirring device 4 loaded with a high-temperature laser displacement sensor is arranged above the foaming furnace 5, and the blowing stirring device 4 is used to cut bubbles to form uniform fine foams and to make preliminary adjustments to the pore structure. The foaming furnace 5 performs air blowing and foaming treatment on the aluminum liquid after temperature control and viscosity enhancement in the viscosity enhancement furnace 2. The aluminum liquid is transferred to the foaming furnace 5 by the same pouring method, and then the air blowing and stirring device 4 is lowered to a suitable position to perform air blowing and stirring operations. The high-temperature laser displacement sensor located at the top of the air blowing and stirring device 4 is used for real-time monitoring and feedback of the growth rate of bubbles.

[0029] The smelting furnace 1, the viscosity-enhancing furnace 2 and the foaming furnace 5 are connected by a rotating folding guide groove for transferring aluminum liquid, and the aluminum liquid can be tilted at a certain angle to pour it, thereby reducing the steps of manual operation and reducing energy consumption. A stirring device 3 that can be lifted and lowered vertically is arranged above the viscosity-enhancing furnace 2, and the speed of the stirring paddle is adjustable, which can facilitate the transfer of aluminum liquid from the viscosity-enhancing furnace 2 to the foaming furnace 5. At the same time, the viscosity-enhancing furnace 2 is used to perform viscosity-enhancing and temperature-control operations on the aluminum liquid after smelting. The aluminum liquid is transferred from the smelting furnace 1 to the viscosity-enhancing furnace 2 through the rotating folding guide groove through the pouring operation, and then the viscosity-enhancing agent is added, usually aluminum oxide or calcium oxide, silicon carbide particles, and the stirring device 3 is operated. The stirring paddle that can be raised and lowered and has an adjustable speed is lowered to a suitable position to perform a stirring and viscosity-enhancing operation, and at the same time, the viscosity-enhancing agent is dispersed to make the aluminum liquid uniformly viscosity-enhanced.

[0030] The blowing and stirring device 4 is connected to the blowing port of the high-temperature blowing equipment. The size and dispersion of the bubbles are adjusted by regulating the rotation speed and the blowing speed. A drainage port is provided on one side of the foaming furnace 5 to guide the growing foam into one end of the roller traction device 6. The drainage port has a certain guide angle, which is used for the roller traction device 6 to clamp the molten foam aluminum.

[0031] The roller traction device 6 is used to cool and pull the foamed aluminum in the molten state, and transfer it to the transverse direction for further shaping and cutting operations. The rollers at both ends of the roller traction device 6 are provided with cooling pipes for circulating cooling water to cool the surface of the foamed aluminum for easy clamping, and the distance between each roller can be adjusted to obtain semi-solid foamed aluminum of different thicknesses.

[0032] Thermoplastic extrusion equipment 7 is used to further shape the semi-solid aluminum foam that is pulled, and extrude aluminum foam sheets with fixed sizes. A fast cutting platform 8 is arranged at the exit of the thermoplastic extrusion equipment 7, and a multi-angle water cooling platform 9 is used to divide the aluminum foam sheets after shaping and solidification, and further cool and solidify the porous structure inside the divided aluminum foam sheets, wherein the roller traction device 6 is connected to the thermoplastic extrusion equipment 7 through a roller conveying device. The semi-solid aluminum foam is conveyed to the thermoplastic extrusion equipment 7 by the roller conveying device for further shaping, and an aluminum foam sheet with fixed sizes is extruded, so that a target size of aluminum foam sheet sample is obtained at one time, and then the aluminum foam sheet sample is divided by the fast cutting platform 8, and then the aluminum foam sheet sample is quickly cooled by the multi-angle water cooling platform 9 immediately to solidify the porous structure inside the aluminum foam sheet.

[0033] The intelligent feedback platform intelligently matches the foam aluminum growth rate data collected by the high-temperature laser displacement sensor with the pore structure, obtains precise control data through the artificial intelligence model, and feeds back the stirring and blowing speed of the blowing port to the CNC platform end, thereby precisely controlling the growth of the foam aluminum pore structure.

[0034] In this embodiment, the function of the smelting furnace 1 is to melt pure aluminum or aluminum alloy to obtain aluminum liquid, and the viscosity-increasing furnace 2 is used to receive the aluminum liquid in the molten state in the smelting furnace 1, add a stabilizer after stabilizing the temperature, and stir the aluminum liquid in combination with the liftable stirring device 3 to make the aluminum liquid fully and evenly viscosity-increasing; the aluminum liquid after viscosity-increasing is poured into the foaming furnace 5, and the blowing and stirring device 4 with a high-temperature laser displacement sensor is submerged into the aluminum liquid to perform blowing and foaming operations; the subsequent high-temperature laser displacement sensor is used to monitor the growth rate of the foam, and feedback adjust the blowing and stirring speeds to preliminarily adjust the porous structure of the foamed aluminum; after the foam grows to a certain stage, the roller traction device 6 clamps the foam for preliminary plasticity and introduces it into the thermoplastic extrusion device 7 to further process the sample to form the target foamed aluminum plate size; the outlet of the thermoplastic extrusion device 7 is equipped with a fast cutting platform 8 to further process the size of the plate, and then the foamed aluminum plate is brought into the multi-angle water cooling platform 9 through a conveyor belt to further cool and solidify the pore structure.

[0035] Among them, in the intelligent stage, the real-time data collected by the high-temperature laser displacement sensor is fed back to the terminal device, and the relationship between the growth rate of foam aluminum and the control parameter rotation speed and blowing speed is obtained by combining the artificial intelligence model. The precise matching relationship between the growth rate and the porous structure of the final sample is further constructed, thereby obtaining the process of adjusting the porous structure by the growth rate. The porous structure of the foam aluminum is directly and accurately adjusted through the terminal CNC platform, and the precise preparation design of the optimized pore structure is realized by intelligent monitoring. This can more accurately obtain the porous structure of the air blowing foaming method, eliminate defective structures from a theoretical point of view, and improve the mechanical properties of the porous structure of the foam aluminum.

[0036] During the sequential transfer of aluminum liquid among the smelting furnace 1, the viscosity increasing furnace 2 and the foaming furnace 5, the spatial position of the furnaces is placed, and the drainage equipment of the rotating folding guide trough is used to shorten the spatial distance and time of the aluminum liquid transfer, reduce the energy consumption and the manpower and material consumption in the transfer process, and thus reduce the preparation cost.

[0037] When the aluminum liquid foams in the foaming furnace 5, the foams are squeezed against each other and accumulated to the drainage port, and the drainage is carried out through the sloped drainage port. Combined with the roller traction device 6, the foam aluminum in the molten state is continuously pulled and shaped. The width of this part is adjustable, which is convenient for the subsequent preparation of foam aluminum plate samples with different porosity requirements and width requirements on the same equipment. The roller-rolled hollow belt on the roller traction device 6 has a cooling water pipe, which is convenient for the rapid cooling of the foam aluminum surface during entrainment, thereby solidifying the molten foam aluminum surface, thereby achieving the effect of convenient clamping.

[0038] Furthermore, the molten aluminum foam is initially plasticized by clamping and then pulled into the thermoplastic extrusion device 7 for heating and extrusion. The heating process in this step is to prevent over-solidification, which causes the internal pore structure to be destroyed during the extrusion process. The aluminum foam sheet is finally formed by the thermoplastic extrusion device 7 to obtain a sample of the target size, and the aluminum foam sheet is further segmented and processed by the rapid cutting platform 8 at the outlet position.

[0039] Finally, the foam aluminum sheet is pulled to the multi-angle water cooling platform 9 by a conveyor belt, and the pore structure inside the foam aluminum sheet is further solidified by the multi-angle water cooling platform 9 to obtain the final foam aluminum sheet. Different cooling methods can also be used to correspondingly change the growth of the pore structure inside the foam aluminum sheet, thereby obtaining a foam aluminum sheet with enhanced mechanical properties.

[0040] In this embodiment, a method for generating precise control data of an air blowing and stirring device is also provided, comprising the following steps:

[0041] S1. Acquire the growth rate data of aluminum foam collected by the high-temperature laser displacement sensor, and acquire the stirring speed data and blowing speed data corresponding to the growth rate data of aluminum foam, and form real-time data. In this embodiment, the real-time growth rate data of aluminum foam can be obtained by the high-temperature laser displacement sensor, and the stirring speed and blowing speed corresponding to the growth rate of aluminum foam can also be obtained by other sensors.

[0042] S2, standardize the real-time data and construct an artificial intelligence model for precise control of the growth of the foam aluminum pore structure, the artificial intelligence model consists of a first prediction model for predicting the precise relationship between the growth rate and the pore structure parameters, and a second prediction model for predicting the growth morphology of the foam aluminum pore structure according to the growth rate of the foam aluminum. In step S2, the specific process includes the following steps:

[0043] S21. Convert the eigenvalues ​​in the real-time data into standard normal distribution data with a mean of 0 and a standard deviation of 1. The purpose of standardization is to convert the eigenvalues ​​into a standard normal distribution with a mean of 0 and a standard deviation of 1. This process is critical to the performance and stability of many machine learning algorithms, especially those that rely on distance metrics or gradient descent optimization. The standardization processing formula is:

[0044] ;

[0045] in, is the original feature in the real-time data; is the mean of the characteristic values ​​in the real-time data; is the standard deviation of the eigenvalues ​​in the real-time data;

[0046] S22, obtaining the pore structure parameters of the foam aluminum sample by CT scanning, and constructing sample data together with the growth rate obtained by the high-temperature laser displacement sensor, the pore structure parameters including porosity, sphericity, anisotropy, and solid material fraction;

[0047] S23, constructing a first prediction model for predicting the precise relationship between the growth rate and the pore structure parameters according to the sample data, and constructing a second prediction model for predicting the growth morphology of the pore structure of the foam aluminum according to the growth rate of the foam aluminum. In this embodiment, the first prediction model adopts a support vector regression (SVR) model and uses a radial basis function (RBF) as a kernel function. For a general regression problem, given a training sample , the goal of this embodiment is to learn a function , so that its predicted value is consistent with the true value As close as possible, the SVR model is constructed by determining the parameters and to achieve this goal.

[0048] In traditional regression models, only when the predicted value With the true value The loss is zero only when the values ​​are exactly the same. However, the SVR model introduces a tolerance , allowing for predicted values With the true value Specifically, when the predicted value With the true value The absolute value of the difference is less than When the absolute value of the difference is greater than The loss is calculated only when A width of If the training sample falls within this interval, the prediction is considered accurate. The degree of relaxation on both sides of the interval can be different;

[0049] Among them, the formula of RBF kernel function is:

[0050] ;

[0051] In the formula, is the original feature in the real-time data; For Different samples; It is an adjustable parameter.

[0052] For the second prediction model, in the task of predicting growth rate, a multi-layer perceptron (MLP) regression model is used, which can capture nonlinear relationships and is suitable for more complex regression problems. Similarly, in order to ensure the stability and efficiency of model training.

[0053] In order to construct the second prediction model, this embodiment uses a multilayer perceptron regressor (MLPRegressor). Multilayer perceptron is a feedforward neural network that includes an input layer, one or more hidden layers, and an output layer. The nodes in each layer are fully connected to the nodes in the next layer, and the input is mapped to the output through a nonlinear activation function. The training process of the MLP regressor minimizes the prediction error through the back propagation algorithm. The process is mainly divided into two stages. The first stage is the forward propagation of the signal, from the input layer through the hidden layer, and finally to the output layer; the second stage is the back propagation of the error, from the output layer to the hidden layer, and finally to the input layer, and the weights and biases from the hidden layer to the output layer, and the weights and biases from the input layer to the hidden layer are adjusted in turn.

[0054] Specifically, this embodiment selects a network structure with two hidden layers, each of which contains 50 neurons. The model optimization process adopts the stochastic gradient descent method, and the maximum number of iterations (1000 times) and the random seed (42) are set to ensure the repeatability and stability of the model training.

[0055] Through the above steps, this embodiment can successfully construct and evaluate a multilayer perceptron regression model for predicting growth rate based on blowing speed and stirring speed. The model can effectively capture the complex nonlinear relationship between input features and target variables and provide high-precision prediction results.

[0056] S24. Use standard normal distribution data to train the first prediction model and the second prediction model respectively and evaluate and verify to obtain an artificial intelligence model. In order to evaluate the performance of the first prediction model, this embodiment uses k-fold cross-validation. During the cross-validation process, the data set is randomly divided into k subsets, and k-1 subsets are used for training each time, and the remaining 1 subset is used for verification (k=5 in the experiment). This method can effectively evaluate the generalization ability of the first prediction model and avoid the deviation of the evaluation results caused by the data division method. The cross-validation scoring indicator uses the negative mean square error (neg_mean_squared_error), and its formula is:

[0057] ;

[0058] Where n is the number of samples; is the true value; is the predicted value.

[0059] This approach enables the construction of a robust regression model that accurately relates the growth rate to porosity, sphericity, solid material fraction, and anisotropy parameters.

[0060] The k-fold cross-validation strategy is also used for the second prediction model to fully understand the performance of the second prediction model on different data partitions and ensure its reliability and stability in practical applications.

[0061] S3. Feedback the precise control data to the CNC platform to control the stirring speed and blowing speed of the blowing port in the blowing stirring device.

[0062] In the stirring and blowing process, this embodiment adopts the method of controlling variables to collect the control of the growth rate of the foam aluminum sample by the stirring speed and the blowing speed respectively, obtains the growth rate of the foam aluminum through the laser displacement sensor, and establishes real-time data together with the corresponding stirring speed data and blowing speed data, and finally constructs an artificial intelligence model according to the deep learning method to obtain precise control data for the growth rate of the foam aluminum. In addition, the obtained foam aluminum sample is scanned by CT to obtain pore structure parameters such as porosity, sphericity, anisotropy, solid material fraction and other pore structure parameters, and then constructs sample data together with the growth rate, and constructs a model in combination with the deep learning method to obtain the precise relationship between them. The precise relationship is fed back to the CNC platform end, and the stirring and blowing speeds of the blowing port are combined to precisely control the growth of the foam aluminum pore structure.

[0063] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0064] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace, comprising a melting furnace (1) for obtaining aluminum alloy or pure aluminum liquid at a predetermined temperature, a viscosity-enhancing furnace (2) for performing viscosity-enhancing treatment on the aluminum alloy or pure aluminum liquid at a predetermined temperature and stirring and uniformly dispersing a viscosity-enhancing agent, and a foaming furnace (5) for containing the aluminum liquid after viscosity-enhancing, characterized in that: include: A high-temperature air blowing device for continuously injecting gas into the aluminum liquid to form bubbles is placed in the foaming furnace (5), and a blowing stirring device (4) equipped with a high-temperature laser displacement sensor is arranged above the foaming furnace (5). The blowing stirring device (4) is used to cut the bubbles to form uniform fine foams and to perform preliminary adjustment on the pore structure; A roller pulling device (6) is used to cool and pull the foamed aluminum in a molten state and transfer it to a transverse direction for further shaping and cutting operations; Thermoplastic extrusion equipment (7) is used to further shape the drawn semi-solid aluminum foam to extrude an aluminum foam sheet with a fixed size; A fast cutting platform (8) is arranged at the exit of the thermoplastic extrusion device (7) and is used to cut the foamed aluminum sheet after molding and curing; A multi-angle water cooling platform (9) is used to further cool the split aluminum foam sheet to solidify the porous structure inside it; The intelligent feedback platform intelligently matches the foam aluminum growth rate data collected by the high-temperature laser displacement sensor with the pore structure, obtains precise control data through the artificial intelligence model, and feeds back to the CNC platform end as the stirring and blowing speed of the blowing port, which is used to accurately control the growth of the foam aluminum pore structure.

2. The intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace according to claim 1 is characterized in that: The blowing and stirring device (4) is connected to the blowing port of the high-temperature blowing equipment, and the size and dispersion of the bubbles are adjusted by regulating the rotation speed and the blowing speed.

3. The intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace according to claim 1 is characterized in that: The smelting furnace (1), the viscosity-increasing furnace (2) and the foaming furnace (5) are connected by a rotating folding guide groove for transferring aluminum liquid, and the aluminum liquid can be poured at a certain angle.

4. The intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace according to claim 1 is characterized in that: A stirring device (3) capable of vertically rising and falling is arranged above the viscosity increasing furnace (2), and the rotation speed of the stirring paddle is adjustable.

5. The intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace according to claim 1 is characterized in that: The rollers at both ends of the roller traction device (6) are provided with cooling pipes for circulating cooling water, so as to cool the surface of the foamed aluminum to facilitate clamping, and the distance between the rollers can be adjusted to obtain semi-solid foamed aluminum of different thicknesses.

6. The intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace according to claim 1 is characterized in that: The roller traction device (6) is connected to the thermoplastic extrusion equipment (7) via a roller conveying device.

7. The intelligent monitoring continuous production line for lightweight foamed aluminum for aerospace according to claim 1 is characterized in that: A drainage port is provided on one side of the foaming furnace (5) for guiding the growing foam to enter one end of the roller traction device (6).

8. A method for generating precise control data of an air blowing and stirring device in a production line according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1, obtaining the foam aluminum growth rate data collected by the high-temperature laser displacement sensor, and obtaining the stirring speed data and the blowing speed data corresponding to the foam aluminum growth rate data, and forming real-time data; S2. Standardizing the real-time data and constructing an artificial intelligence model for accurately controlling the growth of the pore structure of aluminum foam, wherein the artificial intelligence model is composed of a first prediction model for predicting the precise relationship between the growth rate and the pore structure parameters, and a second prediction model for predicting the growth morphology of the pore structure of aluminum foam according to the growth rate of aluminum foam; S3. Feedback the precise control data to the CNC platform to control the stirring speed and blowing speed of the blowing port in the blowing stirring device.

9. The generation method according to claim 8, characterized in that: In step S2, the specific process includes the following steps: S21. Convert the eigenvalues ​​in the real-time data into standard normal distribution data with a mean of 0 and a standard deviation of 1. The standardization processing formula is: Among them, x is the original feature in the real-time data; μ is the mean of the feature value in the real-time data; σ is the standard deviation of the feature value in the real-time data; S22, obtaining the pore structure parameters of the foam aluminum sample by CT scanning, and constructing sample data together with the growth rate obtained by the high-temperature laser displacement sensor, the pore structure parameters including porosity, sphericity, anisotropy, and solid material fraction; S23, constructing a first prediction model for predicting the precise relationship between the growth rate and the pore structure parameters according to the sample data, and constructing a second prediction model for predicting the growth morphology of the pore structure of the foamed aluminum according to the growth rate of the foamed aluminum; S24. Use standard normal distribution data to train the first prediction model and the second prediction model respectively and evaluate and verify them to obtain an artificial intelligence model.

Images