Aluminum profile extrusion production energy consumption prediction method and system

Abstract

The invention discloses an aluminum profile extrusion production energy consumption prediction method and system. The method comprises the steps that technological parameter schemes for production of various aluminum profile products are designed; aluminum profile production experiments are conducted according to the technological parameter scheme, and the lowest production energy consumption of various existing aluminum profile products is determined; calculating a similarity value between the cross section shape of the to-be-processed product and the cross section shape of the experimental production product; calculating the ratio of the extrusion coefficient of the to-be-processed product to the extrusion coefficient of the most similar experiment production product; and calculating a production energy consumption predicted value of the to-be-processed product by utilizing the production energy consumption value of the most similar aluminum profile product, the similarity value of the to-be-processed product and the most similar experiment production product and the extrusion coefficient ratio. The method can accurately predict the production energy consumption of the new to-be-processed aluminum profile product, can reduce the labor intensity of an enterprise, achieves the optimal energy consumption production of the enterprise, can be used for energy consumption control in the aluminum profile production process, achieves energy conservation and emission reduction of the enterprise and production cost reduction, and is simple, rapid and small in calculation amount.

Description

Technical Field

[0001] The invention belongs to the technical field of energy consumption prediction in aluminum profile extrusion production, relates to an energy consumption prediction method in aluminum profile extrusion production, and also relates to an energy consumption prediction system in aluminum profile extrusion production. Background Art

[0002] Aluminum profiles have been widely used in the fields of construction and decoration due to their excellent material ductility, easy processing and formability. However, the production of aluminum profiles requires not only the preheating of aluminum bars and molds, but also the use of very large extrusion force to extrude the aluminum bars through the corresponding molds to obtain the required shape of the product. This results in the production of aluminum profiles being a high-energy consumption and high-emission production process. At present, energy conservation and emission reduction have become the mainstream trend of social production. In order to reduce energy consumption and emissions in the production process of aluminum profiles, reduce energy consumption, and save production costs, the business community and academia have been looking for ways to reduce energy consumption in the production of aluminum profiles and predict energy consumption in the production of aluminum profiles.

[0003] The Chinese patent application (application number 201911218560.3) discloses an isothermal extrusion process parameter optimization method based on a particle swarm algorithm. In view of the complex and unclear relationship between process parameters and metal deformation resistance, and the difficulty in achieving the optimal process parameter combination with qualified product quality and low production energy consumption as constraints, it is proposed to use a support vector machine to establish a prediction model for process parameters, isothermal extrusion forming energy consumption, and profile outlet surface temperature. Taking the extrusion forming energy consumption and the mean square error of the profile outlet surface temperature as the optimization target, a multi-objective optimization model is constructed, and the particle swarm algorithm is used to solve the multi-objective optimization model, so as to optimize the isothermal extrusion process parameters to achieve an optimization scheme with optimal profile quality and minimum forming energy consumption. This scheme requires a large amount of data and complex models to be implemented. Summary of the invention

[0004] The technical solution adopted by the present invention is: a method and system for predicting energy consumption in aluminum profile extrusion production, which can obtain the production energy consumption of the product before the aluminum profile product is produced, and the predicted value can be used for energy consumption control of aluminum profile production extrusion equipment and control of extrusion process parameters, so as to achieve the purpose of energy conservation and emission reduction in aluminum profile production and reduce production costs, the required quantity is greatly reduced, and the model is simple.

[0005] To solve this problem, the technical solution adopted by the present invention is:

[0006] A method for predicting energy consumption in aluminum profile extrusion production, the method comprising the following steps:

[0007] 1) Use orthogonal experimental method to design the process parameter scheme for the production of various existing aluminum profile products of the enterprise;

[0008] 2) Conduct aluminum profile production experiments according to the process parameter plan to determine the minimum production energy consumption of various existing aluminum profile products;

[0009] 3) Use deep learning to compare the cross-sectional shape of the product to be processed with the cross-sectional shape of the experimental production product, find the experimental production product with the most similar cross-sectional shape to the product to be processed, and calculate the similarity value of the cross-sectional shape of the two products;

[0010] 4) Calculate the extrusion coefficient λ of the product to be processed d The extrusion coefficient λ of the product produced by the most similar experiment b ratio;

[0011] 5) The production energy consumption value of the most similar aluminum profile product, the similarity value between the product to be processed and its most similar experimental production product, and the extrusion coefficient ratio are used to calculate the predicted value of the production energy consumption of the product to be processed.

[0012] Furthermore, the process parameters in the above step 1) include the extrusion speed of the extruded rod, the aluminum rod temperature and the mold temperature.

[0013] Furthermore, the deep learning method in the above step 3) is a convolutional neural network or a generative adversarial network.

[0014] Furthermore, the similarity value in the above step 3) is the percentage of the number of all shape features of the cross section of the product to be processed that are the same as the features of the cross section of its most similar experimental production product to the total number of features of the cross section of its most similar experimental production product.

[0015] Furthermore, the calculation formula for the predicted value of production energy consumption of the product to be processed in the above step 5) is:

[0016]

[0017] Q y —Estimated production energy consumption of the product to be processed;

[0018] γ—similarity value;

[0019] λ d —Extrusion coefficient of the product to be processed;

[0020] λ b —Extrusion coefficient of the product produced by the most similar experiment;

[0021] Q s —The production energy consumption value of the most similar experimental production product;

[0022] Aluminum profile extrusion production energy consumption prediction system, including:

[0023] Process parameter scheme determination module, used to determine the process parameter schemes for the production of various existing aluminum profile products;

[0024] The minimum production energy consumption determination module is used to conduct experiments based on the parameters determined by the process parameter scheme determination module to determine the minimum production energy consumption of various existing aluminum profile products;

[0025] A similarity determination module is used to determine the similarity value between the cross-sectional shape of the product to be processed determined by deep learning and the cross-sectional shape of the experimentally produced product;

[0026] Extrusion coefficient ratio determination module, used to determine the extrusion coefficient λ of the product to be processed d The extrusion coefficient λ of the product produced by the most similar experiment b ratio;

[0027] The prediction module compares the production energy consumption prediction value of the product to be processed based on the production energy consumption value of the most similar aluminum profile product, the similarity value of the product to be processed and its most similar experimental production product, and the extrusion coefficient.

[0028] Beneficial effects of the present invention: Compared with the prior art, the effects of the present invention are as follows:

[0029] 1) The present invention constructs an energy consumption database for aluminum profile product production through experiments (process generation scheme after orthogonal experiment), and then uses a convolutional neural network to find the most similar experimental production products to the product to be processed in the existing experimental production products and calculate their similarity values, and then calculates the extrusion coefficient λ of the product to be processed d The extrusion coefficient λ of the product produced by the most similar experiment b The energy consumption of the product is calculated by the established energy consumption prediction formula. The present invention aims to accurately predict the production energy consumption of new aluminum profile products to be processed by combining database, deep learning and energy consumption calculation model. It can not only reduce the labor intensity of enterprises and lay a good foundation for realizing the optimal energy consumption production plan scheduling of enterprises, but also can be used for energy consumption control in the aluminum profile production process, so as to achieve energy conservation and emission reduction and production cost reduction of enterprises.

[0030] Moreover, compared with the Chinese patent application given in the background technology (application number is 201911218560.3, i.e., the comparative patent), it has the following advantages:

[0031] (1) In terms of process parameter optimization method, the present invention adopts the orthogonal experimental method, which is compared with the particle swarm algorithm used in the patent. Compared with the method in the patent, the method in the present invention is simpler, faster and less computationally intensive;

[0032] (2) In terms of data volume, the present invention only requires a small amount of experimental data, while the comparative patent requires a large amount of data for model training;

[0033] (3) In terms of model, the present invention does not need to construct a complex mathematical model, while the comparative patent needs to construct a multi-objective optimization model with the forming energy consumption and the mean square error of the temperature of the profile outlet surface as the optimization target, and the multi-objective optimization model needs to be solved, which requires relatively large computing resources;

[0034] (4) In terms of calculation parameters, the present invention uses the energy consumption data of existing products and the design parameters of the products (such as cross-sectional shape, extrusion coefficient, etc.), while the comparative patent requires the temperature data and process parameters of the products before and after extrusion;

[0035] (5) In terms of the number of process parameters, the present invention has extrusion speed, aluminum rod temperature, and die temperature, while the comparative patent has blank temperature gradient (both the temperature before and after extrusion are required), blank initial temperature, and extrusion speed. However, die temperature is one of the important parameters of the extrusion process.

[0036] 2) The orthogonal experimental method is used to determine the process parameter scheme. The advantages are: 1) It can reduce the number of experiments. The orthogonal experimental method can obtain sufficient data with a fewer number of experiments through a carefully designed experimental scheme, thereby reducing the overall number of production experiments. This method can effectively save time and cost, especially in the production of aluminum profiles, where comprehensive experiments may require a large amount of raw materials and time. For example, through the orthogonal experimental method, the impact of multiple process parameters can be evaluated with fewer experiments without sacrificing the quality of the results; 2) Improve the efficiency of the experiment: The orthogonal experimental method selects representative test points to make the test results more universal and generalizable, thereby improving the efficiency of the experiment. This method can quickly identify the key factors that affect product quality and help producers find the optimal combination of process parameters more quickly; 3) Reduce experimental costs: Due to the reduction in the number of experiments, the corresponding raw material, energy and labor costs will also be reduced. 4) Orthogonal test method can clearly reveal the influence of various factors on product performance, making the results easier to explain and promote. This clear factor impact analysis helps producers understand how process parameters affect the quality of the final product and make process improvements accordingly; 5) Optimize process parameters: Through the orthogonal test method, process parameters such as extrusion speed, aluminum bar temperature, mold temperature, etc. can be systematically analyzed and optimized to improve the product quality of aluminum profiles. For example, the orthogonal test method can be used to determine the optimal extrusion process parameters to obtain the required mechanical properties and microstructure; 6) Strong adaptability: The orthogonal test method can adapt to a variety of different test conditions and requirements, including multi-factor and multi-level situations, which makes it highly flexible and adaptable in aluminum profile production;

[0037] 3) Deep learning models can automatically learn and extract features from raw data, reducing manual intervention and improving the efficiency and accuracy of feature extraction; Deep learning models, especially deep neural networks, have rich hierarchical structures and can express complex feature mapping relationships, enabling them to process high-dimensional data and extract useful information from them; Deep learning models show good robustness in dealing with noise and outliers, which makes them have better performance when processing data in practical applications;

[0038] 4) The present invention uses an orthogonal experimental method to determine the process parameter scheme, a deep learning method to determine the similarity value, and an extrusion coefficient ratio to collaboratively determine the production energy consumption prediction, which is more scientific, reasonable, and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a method for predicting energy consumption of aluminum profile extrusion production;

[0040] Figure 2 This is a structural schematic diagram of an energy consumption prediction system for aluminum profile extrusion production. DETAILED DESCRIPTION

[0041] The present invention is further described below in conjunction with specific embodiments.

[0042] Example 1: Figure 1 As shown, a method for predicting energy consumption of aluminum profile extrusion production comprises the following steps:

[0043] 1) Use orthogonal experimental method to design the process parameter scheme for the production of various existing aluminum profile products of the enterprise; the process parameters include the extrusion speed of the extrusion rod, the aluminum rod temperature and the mold temperature

[0044] A 3-factor, 10-level experimental scheme for process parameters such as extrusion speed, aluminum bar temperature, and die temperature of the extruded rod;

[0045] 2) Conduct aluminum profile production experiments according to the process parameter plan to determine the minimum production energy consumption of various existing aluminum profile products;

[0046] The determination method is: compare the processing energy consumption of all process parameter groups of aluminum profile products of the same specification and model in the experimental plan, and the product with the smallest energy consumption value is the lowest production energy consumption of the specification and model.

[0047] 3) Use a convolutional neural network or a generative adversarial network to compare the cross-sectional shape of the product to be processed with the cross-sectional shape of the experimental production product, find the experimental production product with the most similar cross-sectional shape to the product to be processed, and calculate the similarity value of the cross-sectional shapes of the two products;

[0048] The similarity value is the percentage of the number of identical shape features of the cross section of the product to be processed and the features of the cross section of the most similar experimental production product to the total number of features of the cross section of the most similar experimental production product (similar to the facial contour recognition in the face recognition in the prior art);

[0049] 4) Calculate the ratio of the extrusion coefficient λd of the product to be processed to the extrusion coefficient λb of the most similar experimental production product;

[0050] 5) Calculate the predicted value of production energy consumption of the product to be processed by using the production energy consumption value of the most similar aluminum profile product, the similarity value of the product to be processed and its most similar experimental production product, and the extrusion coefficient ratio;

[0051] The calculation formula for the predicted value of production energy consumption of the product to be processed is:

[0052]

[0053] Q y —Estimated production energy consumption of the product to be processed;

[0054] γ—similarity value;

[0055] λ d —Extrusion coefficient of the product to be processed;

[0056] λ b —Extrusion coefficient of the product produced by the most similar experiment;

[0057] Qs—The production energy consumption value of the most similar experimental production product.

[0058] Example 2: Figure 2 As shown, a system for predicting energy consumption of aluminum profile extrusion production includes:

[0059] Process parameter scheme determination module, used to determine the process parameter schemes for the production of various existing aluminum profile products;

[0060] The minimum production energy consumption determination module is used to conduct experiments based on the parameters determined by the process parameter scheme determination module to determine the minimum production energy consumption of various existing aluminum profile products;

[0061] A similarity determination module is used to determine the similarity value between the cross-sectional shape of the product to be processed determined by deep learning and the cross-sectional shape of the experimentally produced product;

[0062] Extrusion coefficient ratio determination module, used to determine the extrusion coefficient λ of the product to be processed d The extrusion coefficient λ of the product produced by the most similar experiment b ratio;

[0063] The prediction module compares the production energy consumption prediction value of the product to be processed based on the production energy consumption value of the most similar aluminum profile product, the similarity value of the product to be processed and its most similar experimental production product, and the extrusion coefficient.

Claims

1. A method for predicting energy consumption in aluminum profile extrusion production, characterized in that: The method comprises the following steps: 1) Use orthogonal experimental method to design process parameter solutions for the production of various existing aluminum profile products; 2) Conduct aluminum profile production experiments according to the process parameter plan to determine the minimum production energy consumption of various existing aluminum profile products; 3) Use deep learning to compare the cross-sectional shape of the product to be processed with the cross-sectional shape of the experimental production product, find the experimental production product with the most similar cross-sectional shape to the product to be processed, and calculate the similarity value of the cross-sectional shape of the two products; 4) Calculate the extrusion coefficient λ of the product to be processed d The extrusion coefficient λ of the product produced by the most similar experiment b ratio; 5) The production energy consumption forecast value of the product to be processed is calculated using the production energy consumption value of the most similar aluminum profile product, the similarity value between the product to be processed and its most similar experimental production product, and the extrusion coefficient ratio.

2. The method for predicting energy consumption of aluminum profile extrusion production according to claim 1, characterized in that: The process parameters in step 1) include the extrusion speed of the extruded rod, the aluminum rod temperature and the mold temperature.

3. The method for predicting energy consumption of aluminum profile extrusion production according to claim 2, characterized in that: The orthogonal experimental scheme in step 1) is a 3-factor, 10-level experimental scheme.

4. The method for predicting energy consumption of aluminum profile extrusion production according to claim 2, characterized in that: In step 3), the deep learning method is a convolutional neural network or a generative adversarial network.

5. The method for predicting energy consumption of aluminum profile extrusion production according to claim 3, characterized in that: The similarity value in step 3) is the percentage of the number of all shape features of the cross section of the product to be processed that are identical to the features of the cross section of its most similar experimental production product to the total number of features of the cross section of its most similar experimental production product.

6. The method for predicting energy consumption of aluminum profile extrusion production according to claim 3, characterized in that: The calculation formula for the predicted value of production energy consumption of the product to be processed in step 5) is: （1） —Estimated production energy consumption of the product to be processed; —similarity value; —Extrusion coefficient of the product to be processed; —Extrusion coefficient of the product produced by the most similar experiment; Q s —The production energy consumption value of the most similar experimental production product.

7. Aluminum profile extrusion production energy consumption prediction system, characterized by: include, Process parameter scheme determination module, used to determine the process parameter schemes for the production of various existing aluminum profile products; The minimum production energy consumption determination module is used to conduct experiments based on the parameters determined by the process parameter scheme determination module to determine the minimum production energy consumption of various existing aluminum profile products; A similarity determination module is used to determine the similarity value between the cross-sectional shape of the product to be processed determined by deep learning and the cross-sectional shape of the experimentally produced product; Extrusion coefficient ratio determination module, used to determine the extrusion coefficient of the product to be processed Extrusion coefficient of the product produced with the most similar experiment ratio; The prediction module compares the production energy consumption prediction value of the product to be processed based on the production energy consumption value of the most similar aluminum profile product, the similarity value of the product to be processed and its most similar experimental production product, and the extrusion coefficient.

Images