Aluminum profile machining precision optimization method and system

Abstract

The invention discloses an aluminum profile machining precision optimization method and system. The method comprises the following steps: acquiring a target profile of the section of the aluminum profile; actual profile point cloud data of the section of the aluminum profile are collected and preprocessed; calculating a profile tolerance error delta P of the component profile; performing error trend prediction by adopting a long and short term memory network algorithm model LSTM and combining an attention mechanism to obtain a prediction error; according to the prediction error, calculating to obtain a process parameter compensation amount; according to the process parameter compensation amount and a basic process parameter set value, obtaining a finally applied process parameter; complete contour point cloud data are obtained through non-contact online scanning of the optical scanner, the contour error is accurately calculated in combination with B-spline curve fitting and the normal distance, comprehensive collection of contour data and accurate quantification of the error are achieved, the tolerance can be controlled within a smaller range, and the accuracy of the contour data is improved. And the strict requirements of chip radiators, automobile anti-collision beams, precision guide rails and other high-end applications on size precision and shape precision are met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aluminum profile processing, in particular to an aluminum profile processing precision optimization method and system. BACKGROUND

[0002] Aluminum profile extrusion is an efficient process for preparing complex cross-section metal components, and is widely used in key fields such as architecture, transportation, aerospace, and electronic appliances. With the development of industry, the requirements for the dimensional accuracy, shape accuracy, and batch consistency of aluminum profiles are becoming increasingly stringent. However, the current aluminum profile extrusion production has the following defects: (1) The wall thickness tolerance set by the existing national standard is acceptable for conventional applications, but in high-end application scenarios such as chip heat sinks, automobile impact beams, and precision guide rails, especially in the manufacturing of precision electronic components such as chip heat sinks, higher precision requirements are needed, and the tolerance needs to be controlled within a smaller range. However, there is a lack of effective forming control means in the existing technology, making it difficult to achieve higher precision requirements.

[0003] (2) The process parameters of the existing production line are usually fixed after being set and cannot be adjusted in real time according to changes such as die wear and environmental temperature fluctuations, resulting in poor precision and consistency of batch production profiles, high scrap rate, and high production cost.

[0004] (3) Traditional profile detection methods rely on contact gauges such as micrometers and calipers or offline three-coordinate measurement through periodic sampling, which is low in efficiency and limited in sampling points, cannot obtain complete profile information of the profile, and has serious feedback lag; (4) Traditional detection methods are only used for quality detection and cannot be used for real-time control of the production process.

[0005] Therefore, it is necessary to improve the aluminum profile processing technology in the prior art. SUMMARY

[0006] In view of the technical problems pointed out in the above background art, the purpose of the present application is to provide an aluminum profile processing precision optimization method and system.

[0007] To achieve the purpose of the present application, the technical solution provided by the present application is as follows: First aspect The present application provides an aluminum profile processing precision optimization method, comprising the following steps: Step S1: obtaining an aluminum profile cross-section target profile; the aluminum profile cross-section target profile comprises a plurality of basic shape component units; Step S2: collecting aluminum profile cross-section actual profile point cloud data and preprocessing to obtain preprocessed actual profile point cloud data; Step S3: based on the pre-processed actual profile point cloud data, a component fitting profile reflecting a plurality of basic shape component units is constructed; based on the component fitting profile and the aluminum profile section target profile, error values of all data points on the component fitting profile to their corresponding target profile are calculated; based on the error values, a profile tolerance error ΔP of the component profile is obtained; Step S4: steps S2-S3 are repeatedly executed to obtain profile tolerance errors ΔP of a plurality of time component profiles of a preset number; Step S5: based on the profile tolerance errors ΔP of a plurality of time component profiles of a preset number and process parameters, a time sequence feature matrix is constructed; according to the time sequence feature matrix, an error trend prediction is performed using a long short-term memory network algorithm model LSTM combined with an attention mechanism to obtain a predicted error; the process parameters include aluminum rod heating temperature of a processing equipment, extrusion speed of the processing equipment, traction of the processing equipment, die wear index, and processing environment temperature; Step S6: a process parameter compensation amount is calculated according to the predicted error; and a final applied process parameter is obtained according to the process parameter compensation amount and a basic process parameter set value; Step S7: processing is performed according to the final applied process parameter.

[0008] Second aspect The application provides an aluminum profile machining precision optimization system for executing the aluminum profile machining precision optimization method, comprising the following units: a target profile acquisition unit, a point cloud data acquisition unit, a profile tolerance error acquisition unit, a repeated execution unit, an error prediction unit, a process parameter acquisition unit, and an execution unit. The target profile acquisition unit is configured to acquire an aluminum profile section target profile; the aluminum profile section target profile comprises a plurality of basic shape component units. The point cloud data acquisition unit is configured to collect aluminum profile section actual profile point cloud data and perform preprocessing to obtain pre-processed actual profile point cloud data. The profile tolerance error acquisition unit is configured to construct a component fitting profile reflecting a plurality of basic shape component units based on the pre-processed actual profile point cloud data; calculate error values of all data points on the component fitting profile to their corresponding target profile based on the component fitting profile and the aluminum profile section target profile; and obtain a profile tolerance error ΔP of the component profile based on the error values. The repeated execution unit is configured to repeatedly execute the point cloud data acquisition unit and the profile tolerance error acquisition unit to obtain profile tolerance errors ΔP of a plurality of time component profiles of a preset number. The error prediction unit is configured to construct a time sequence feature matrix based on profile error AP of a plurality of time point component profiles of a preset quantity and process parameters; and perform error trend prediction by using LSTM combined with an attention mechanism according to the time sequence feature matrix, to obtain a predicted error; the process parameters include aluminum bar heating temperature of a processing device, extrusion speed of the processing device, traction of the processing device, die wear index, and processing environment temperature. The process parameter acquisition unit is configured to calculate a process parameter compensation amount according to the predicted error; and obtain a final applied process parameter according to the process parameter compensation amount and a basic process parameter set value. The execution unit is configured to perform processing according to the final applied process parameter.

[0009] Compared with the prior art, the application has the following beneficial effects: (1) The application uses an optical scanner to obtain complete profile point cloud data in a non-contact online scanning manner, combines B-spline curve fitting and normal distance accurate calculation of profile error AP, realizes comprehensive collection of profile data and accurate quantization of errors, can control the tolerance in a smaller range, and meets the stringent requirements of high-end applications such as chip heat sinks, automobile anti-collision beams, and precision guide rails on dimensional accuracy and shape accuracy.

[0010] (2) The error trend prediction model based on LSTM combined with an attention mechanism in the application fuses time sequence features of key process parameters such as aluminum bar heating temperature, extrusion speed, traction, environment temperature, and die wear index, can predict the profile error at a future time point in advance, and solves the problems of fixed process parameters of a traditional production line, inability to cope with real-time changes such as die wear and environmental fluctuations, significantly reduces the precision dispersion of batch products, and improves batch consistency.

[0011] (3) The application uses non-contact online scanning and an abnormal point elimination technology based on statistical distribution characteristics to realize efficient collection and preprocessing of profile data, avoids feedback lag, and at the same time, constructs a closed-loop control process of "detection-error calculation-error prediction-parameter compensation-processing", upgrades the detection function from simple quality inspection to real-time production process control, greatly reduces the waste rate, and reduces production cost. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 The aluminum profile machining precision optimization method flowchart provided by the embodiment of the application; Figure 2 The aluminum profile cross-section actual profile point cloud data schematic diagram in the embodiment of the application; Figure 3 The effect comparison diagram before and after the aluminum profile machining precision optimization. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0014] like Figure 1 As shown in the figure, this embodiment provides a method for optimizing the processing accuracy of aluminum profiles, including the following steps: Step S1: Obtain the target profile of the aluminum profile cross section; the target profile of the aluminum profile cross section includes multiple basic shape component units; It should be noted that in this step, firstly, a unified measurement and evaluation reference coordinate system is established to ensure the consistency and accuracy of the contour evaluation. The target contour of the aluminum profile cross-section is then obtained; this target contour includes multiple basic shape component units, including the outer contour, center hole, corner holes, T-slots, etc.

[0015] Step S2: Collect the actual contour point cloud data of the aluminum profile cross-section and perform preprocessing to obtain the preprocessed actual contour point cloud data; specifically including the following: Step S21: After the aluminum profile has cooled and solidified, an optical scanner is used to perform a non-contact online scan of the aluminum profile cross-section to obtain the actual contour point cloud data of the aluminum profile cross-section; such as Figure 2 As shown.

[0016] It should be noted that the scanning process uses a step length of 0.2-0.5mm for discretization sampling. The sampling step length of 0.2-0.5mm can accurately capture the roundness characteristics of the center hole and corner holes, ensuring accurate representation of complex geometric features.

[0017] Step S22: An outlier detection algorithm based on statistical distribution features is used to automatically identify and remove measurement noise points to obtain preprocessed actual contour point cloud data.

[0018] It should be noted that an outlier detection algorithm based on statistical distribution characteristics is used to automatically identify and remove measurement noise caused by factors such as surface reflection, oxidation residue, and cutting fluid stains, and to verify the integrity of the point cloud data to ensure the accuracy and reliability of subsequent analysis.

[0019] Step S3: Based on the preprocessed actual contour point cloud data, construct a component fitting contour that reflects multiple basic shape component units; based on the component fitting contour and the target contour of the aluminum profile section, calculate the error value from all data points on the component fitting contour to their corresponding target contour; based on the error value, obtain the contour accuracy error ΔP of the component contour; specifically including the following: Step S3.1: Use the B-spline curve fitting formula to fit the preprocessed actual contour point cloud data to construct a component fitting contour that reflects multiple basic shape component units; Step S3.2: Based on the component fitting profile and the aluminum profile cross-section target profile, calculate the normal distance from all data points on the component fitting profile to their corresponding target profile, and the obtained normal distance is the error value; The formula for calculating the normal distance is as follows: ; in, This represents the normal distance to the i-th data point on the component's fitted contour; ) indicates the component fitting profile on the th i The coordinates of each data point; ) represents the first contour on the target contour that matches the component's fitted contour. i The coordinates of the points corresponding to each data point; Indicates the component fitting profile on the first i At the nth data point, the direction of the fitted contour normal is parallel to the nth data point. i The angle between the directions of the lines connecting each data point to the corresponding point on the target contour; Indicates the component fitting profile on the first i Euclidean distance from each data point to the corresponding point on the target contour; Step S3.3: Based on the error value, obtain the contour error ΔP of the component contour. The calculation formula is as follows: ; in, Indicates the profile error of the component outline; tm This represents the total number of fitted data points on the component outline that participated in the calculation. Indicates the first i The absolute value of the normal distance to each data point.

[0020] Step S4: Repeat steps S2-S3 to obtain the contour error ΔP of the component contour at multiple time points for a preset number of moments; Step S5: constructing a time sequence feature matrix based on the profile error ΔP of the component profile at a preset number of time points and the process parameters; performing error trend prediction by using a long short-term memory network algorithm model LSTM combined with an attention mechanism according to the time sequence feature matrix, to obtain a predicted error; the process parameters include aluminum bar heating temperature of a processing device, extrusion speed of the processing device, traction of the processing device, mold wear index, processing environment temperature; specifically including the following: Step S5.1: performing time sequence alignment based on the profile error ΔP of the component profile at a preset number of time points and the field collected process parameters, to construct a time sequence feature matrix ; ; Wherein, is a profile error sequence from the current time t to the historical time k; is a profile error sequence from the current time t to the historical time k+1; is the aluminum bar heating temperature; is the extrusion speed; is the traction; is the environment temperature; is the mold wear index; is the profile error sequence at the current time t; Step S5.2: processing by using a long short-term memory network algorithm model LSTM according to the time sequence feature matrix, including: Step S5.2.1: forgetting gate processing, specifically as follows: ; Wherein, is the forgetting gate output, indicating the activation value of the forgetting gate at the current time t , and the value range is between [0, 1]; is a Sigmoid activation function; is a forgetting gate weight matrix; is a splicing vector, is the hidden state of the previous time; is a forgetting gate bias term; Step S5.2.2: input gate processing, specifically as follows: ; Wherein, is the input gate output, indicating the activation value of the input gate at the current time t, and the value range is between [0, 1]; is an input gate weight matrix; is an input gate bias term; Step S5.2.3: output gate processing, specifically as follows: ; in, The output value is the value of the output gate at the current time t, and its value ranges from [0,1]. This is the output gate weight matrix; This is the output gate bias term; Step S5.2.4: Calculation of cell state and hidden state, as detailed below: ; in, The candidate cell state represents the new information to be added to memory at the current time t. The candidate state weight matrix; Candidate state bias terms; ; in, Let be the cell state at the current time t, and the cell state at the current time t is long-term memory; This represents the cell state at the previous moment; This is element-wise multiplication; ; in, Let be the hidden state at the current time t, and let be the short-term memory / output. Step S5.3: Calculate the attention mechanism weights, including: ; in, This represents the hidden state of historical time k at the current time t. The attention weights assigned range from [0,1]. At a certain point in history; T1 is the length of the time series; To measure the difference between the current time t and historical times k Attention energy scores indicating their correlation or importance; An attention energy score that measures the relevance or importance of the current time t to a historical time j; where, This is the attention vector; This is the historical state weight matrix; This is the current state weight matrix; It is in a state of historical concealment; The current hidden state is T, where T is the matrix transpose. Step S5.4: Calculate the prediction error; ; in, For prediction error, the predicted future time. profile error of the contour; T 1 is the length of time series.

[0021] Step S6: According to the prediction error, the process parameter compensation amount is calculated; according to the process parameter compensation amount and the basic process parameter set value, the final applied process parameter is obtained; specifically including the following: Step S6.1: An optimization objective function is constructed with the minimization of the prediction error as the only objective, specifically as follows: ; Wherein, is the optimization objective, minimizing the absolute value of the prediction error; Decision variable: ; Set the constraint condition: ; ; ; ; ; Wherein, is the minimum threshold of the aluminum bar heating temperature, is the maximum threshold of the aluminum bar heating temperature; is the minimum threshold of the extrusion speed, is the maximum threshold of the extrusion speed; is the minimum threshold of the traction force, is the maximum threshold of the traction force; is the minimum threshold of the environmental temperature, is the maximum threshold of the environmental temperature; is the minimum threshold of the die wear index, is the maximum threshold of the die wear index; 、 、 、 、 Indicates 5 constraint conditions; Step S6.2: For the objective function constructed in step S6.1, the adaptive gradient descent algorithm is used to solve the process parameters, and the formula is as follows: ; Wherein, is the process parameter when the iteration number is n ; is the process parameter when the iteration number is n+1 ; is the learning rate; is the objective function in step S6.1 The gradient at the point is implicitly satisfied by the constraints of step S6.1 through the iterative process of gradient descent. Among them, the learning rate Adaptive learning rate adjustment is performed to obtain : ; in, The initial learning rate; The attenuation coefficient; Step S6.3: Real-time compensation of process parameters based on PID control, as detailed below: ; in, For the first The amount of compensation at any given moment; , , These are the proportional, integral, and differential coefficients, respectively. Let be the error at time t; For target contour error; This represents the actual profile error at the current time t. This represents the error at time t-1; Indicates from the initial time j =1 to the current time in the accumulated error sequence of time n j One error value; Final applied process parameters The formula is as follows: ; in, These are the basic process parameter settings. .

[0022] Step S7: Process according to the final applied process parameters.

[0023] like Figure 3 The figure shows a comparison of the effects of aluminum profile processing accuracy optimization before and after. As shown, before optimization, the profile error ΔP remained at a high level, exhibiting stable fluctuations. After applying the optimized process parameters, the profile error ΔP gradually converged and stabilized near the target error. Figure 3 The method is visually demonstrated to significantly improve machining accuracy.

[0024] In addition, this embodiment provides an aluminum profile processing accuracy optimization system for executing the aluminum profile processing accuracy optimization method, including the following units: target contour acquisition unit, point cloud data acquisition unit, contour error acquisition unit, repetitive execution unit, error prediction unit, process parameter acquisition unit, and execution unit; The target profile acquisition unit is configured to acquire an aluminum profile section target profile, and the aluminum profile section target profile comprises a plurality of basic shape component units. The point cloud data acquisition unit is configured to collect aluminum profile section actual profile point cloud data and pre-process the aluminum profile section actual profile point cloud data to obtain pre-processed actual profile point cloud data. The profile error acquisition unit is configured to construct a component fitting profile reflecting the plurality of basic shape component units based on the pre-processed actual profile point cloud data, calculate error values of all data points on the component fitting profile to corresponding target profiles based on the component fitting profile and the aluminum profile section target profile, and obtain a profile error ΔP of the component profile based on the error values. The repeated execution unit is configured to repeatedly execute the point cloud data acquisition unit and the profile error acquisition unit to obtain profile errors ΔP of component profiles at a preset number of moments. The error prediction unit is configured to construct a time sequence feature matrix based on the profile errors ΔP of the component profiles at the preset number of moments and process parameters, and perform error trend prediction using LSTM combined with an attention mechanism based on the time sequence feature matrix to obtain a predicted error, wherein the process parameters include aluminum rod heating temperature of a processing device, extrusion speed of the processing device, traction of the processing device, die wear index, and processing environment temperature. The process parameter acquisition unit is configured to calculate a process parameter compensation amount based on the predicted error, and obtain a final applied process parameter based on the process parameter compensation amount and a basic process parameter set value. The execution unit is configured to perform processing based on the final applied process parameter.

[0025] The point cloud data acquisition unit is specifically configured to perform the following steps: Step S21: After the aluminum profile is cooled and shaped, an optical scanner is used to perform non-contact online scanning on the aluminum profile section to obtain aluminum profile section actual profile point cloud data. Step S22: An abnormal point detection algorithm based on statistical distribution characteristics is used to automatically identify and remove measurement noise points to obtain pre-processed actual profile point cloud data.

[0026] The profile error acquisition unit is specifically configured to perform the following steps: Step S3.1: A B-spline curve fitting formula is used to fit the pre-processed actual profile point cloud data to construct a component fitting profile reflecting the plurality of basic shape component units. Step S3.2: Normal distances of all data points on the component fitting profile to corresponding target profiles are calculated based on the component fitting profile and the aluminum profile section target profile, and the normal distances obtained are error values. The formula for calculating the normal distance is as follows: ; in, This represents the normal distance to the i-th data point on the component's fitted contour; ) indicates the component fitting profile on the th i The coordinates of each data point; ) represents the first contour on the target contour that matches the component's fitted contour. i The coordinates of the points corresponding to each data point; Indicates the component fitting profile on the first i At the nth data point, the direction of the fitted contour normal is parallel to the nth data point. i The angle between the directions of the lines connecting each data point to the corresponding point on the target contour; Indicates the component fitting profile on the first i Euclidean distance from each data point to the corresponding point on the target contour; Step S3.3: Based on the error value, obtain the contour error ΔP of the component contour. The calculation formula is as follows: ; in, Indicates the profile error of the component outline; tm This represents the total number of fitted data points on the component outline that participated in the calculation. Indicates the first i The absolute value of the normal distance to each data point.

[0027] Specifically, the error prediction unit is used to perform the following steps: Step S5.1: Based on the contour error ΔP of the component contour at multiple time points and the process parameters collected on-site, perform time-series alignment to construct a time-series feature matrix. ; ; in, This is the contour error sequence from the current time t to the historical time k; This is the contour error sequence from the current time t to the historical time k+1; The heating temperature of the aluminum rod; This refers to the extrusion speed; For traction force; The ambient temperature; The mold wear index; Step S5.2: Based on the aforementioned temporal feature matrix, process it using the Long Short-Term Memory (LSTM) network algorithm model, including: Step S5.2.1: Forget gate processing, as follows: ; in, The output of the forget gate indicates the current time. t The activation value of the forget gate is between [0,1]. Use the Sigmoid activation function; This is the forget gate weight matrix; To concatenate vectors, It is the hidden state from the previous moment; Forget gate bias term; Step S5.2.2: Input gate processing, as follows: ; in, The input gate output represents the activation value of the input gate at the current time t, and its value ranges from [0,1]. The input gate weight matrix; Forget gate bias term; Step S5.2.3: Output gate processing, as detailed below: ; in, The output value is the value of the output gate at the current time t, and its value ranges from [0,1]. This is the output gate weight matrix; This is the output gate bias term; Step S5.2.4: Calculation of cell state and hidden state, as detailed below: ; in, The candidate cell state represents the new information to be added to memory at the current time t. The candidate state weight matrix; Candidate state bias terms; ; in, Let be the cell state at the current time t, and the cell state at the current time t is long-term memory; This represents the cell state at the previous moment; This is element-wise multiplication; ; in, Let be the hidden state at the current time t, and let be the short-term memory / output. Step S5.3: Calculate the attention mechanism weights, including: ; in, denotes the hidden state of the history time k at the current time t assigned attention weight, ranging from 0 to 1; history time; T1 is the length of the time series; is the attention energy score measuring the relevance or importance between the current time t and the history time k ; is the attention energy score measuring the relevance or importance between the current time t and the history time j; where, is the attention vector; is the history state weight matrix; is the current state weight matrix; is the history hidden state; is the current hidden state, T is the matrix transpose; Step S5.4: Calculate the prediction error; ; where, is the prediction error, the profile error of the predicted future time ; T 1 is the length of the time series.

[0028] Wherein, the process parameter acquisition unit is specifically used for executing the following steps: Step S6.1: Construct an optimization objective function with the minimization of the prediction error as the only objective, specifically as follows: ; where, is the optimization objective, minimizing the absolute value of the prediction error; decision variable: ; Set the constraint condition: ; ; ; ; ; where, is the minimum threshold of the aluminum rod heating temperature, is the maximum threshold of the aluminum rod heating temperature; is the minimum threshold of the extrusion speed, is the maximum threshold of the extrusion speed; is the minimum threshold of the traction force, is the maximum threshold of the traction force; is the minimum threshold of the ambient temperature, is the ambient temperature maximum threshold value; is the minimum threshold value of the die wear index, is the maximum threshold value of the die wear index; , , , , represents five constraint conditions; Step S6.2: For the objective function constructed in step S6.1, the process parameters are solved by using an adaptive gradient descent algorithm, and the formula is as follows: ; wherein, is the process parameter at the iteration number n ; is the process parameter at the iteration number n+1 ; is the learning rate; is the gradient of the objective function in step S6.1 at , and the constraint conditions of step S6.1 are implicitly satisfied through the iterative process of gradient descent; wherein, the adaptive learning rate adjustment is performed on the learning rate to obtain : ; wherein, is the initial learning rate; is the decay coefficient; Step S6.3: Real-time compensation of process parameters based on PID control, specifically as follows: ; wherein, is the compensation amount at the moment; , , are proportional, integral, and differential coefficients, respectively; is the error at the t moment; is the target profile error; is the actual profile error at the current moment t; represents the error at the t-1 moment; represents the j th error value in the cumulative error sequence from the initial moment j =1 to the current moment; The final applied process parameter , the formula is as follows: ; wherein, setting values for basic process parameters, .

[0029] Finally, it should be noted that the above-described embodiments are merely intended to illustrate and explain the present application, and are not intended to limit the present application to the scope of the described embodiments. Furthermore, those skilled in the art can understand that the present application is not limited to the above-described embodiments, and that more various modifications and changes can be made according to the teachings of the present application, and that these modifications and changes all fall within the scope of the present application.

Claims

1. A method for optimizing the processing accuracy of aluminum profiles, characterized in that, Includes the following steps: Step S1: Obtain the target profile of the aluminum profile cross section; the target profile of the aluminum profile cross section includes multiple basic shape component units; Step S2: Collect the actual contour point cloud data of the aluminum profile cross section and perform preprocessing to obtain the preprocessed actual contour point cloud data; Step S3: Based on the preprocessed actual contour point cloud data, construct a component fitting contour that reflects multiple basic shape component units; based on the component fitting contour and the target contour of the aluminum profile section, calculate the error value from all data points on the component fitting contour to their corresponding target contour; based on the error value, obtain the contour error ΔP of the component contour. Step S4: Repeat steps S2-S3 to obtain the contour error ΔP of the component contour at multiple time points for a preset number of moments; Step S5: Construct a timing feature matrix based on the contour error ΔP of the component contour at multiple time points and process parameters of a preset number of time points; Based on the temporal feature matrix, the Long Short-Term Memory (LSTM) network algorithm model combined with an attention mechanism is used to predict the error trend and obtain the prediction error; the process parameters include the heating temperature of the aluminum rod in the processing equipment, the extrusion speed of the processing equipment, the traction force of the processing equipment, the die wear index, and the ambient temperature of the processing environment; Step S6: Calculate the process parameter compensation amount based on the prediction error; obtain the final applied process parameters based on the process parameter compensation amount and the basic process parameter setting value. Step S7: Process according to the final applied process parameters.

2. The method for optimizing the processing accuracy of aluminum profiles according to claim 1, characterized in that, Step S2 specifically includes the following: Step S21: After the aluminum profile is cooled and shaped, an optical scanner is used to perform a non-contact online scan of the aluminum profile cross section to obtain the actual contour point cloud data of the aluminum profile cross section; Step S22: Employ an outlier detection algorithm based on statistical distribution characteristics to automatically identify and remove measurement noise points. The preprocessed actual contour point cloud data is obtained.

3. The method for optimizing the processing accuracy of aluminum profiles according to claim 2, characterized in that, Step S3 specifically includes the following: Step S3.1: Use the B-spline curve fitting formula to fit the preprocessed actual contour point cloud data to construct a component fitting contour that reflects multiple basic shape component units; Step S3.2: Based on the component fitting profile and the aluminum profile cross-section target profile, calculate the normal distance from all data points on the component fitting profile to their corresponding target profile, and the obtained normal distance is the error value; The formula for calculating the normal distance is as follows: ； in, This represents the normal distance to the i-th data point on the component's fitted contour; ) indicates the component fitting profile on the th i The coordinates of each data point; ) represents the first contour on the target contour that matches the component's fitted contour. i The coordinates of the points corresponding to each data point; Indicates the component fitting profile on the first i At the nth data point, the direction of the fitted contour normal is parallel to the nth data point. i The angle between the directions of the lines connecting each data point to the corresponding point on the target contour; Indicates the component fitting profile on the first i Euclidean distance from each data point to the corresponding point on the target contour; Step S3.3: Based on the error value, obtain the contour error ΔP of the component contour. The calculation formula is as follows: ； in, Indicates the profile error of the component outline; tm This represents the total number of fitted data points on the component outline that participated in the calculation. Indicates the first i The absolute value of the normal distance to each data point.

4. The method for optimizing the processing accuracy of aluminum profiles according to claim 3, characterized in that, Step S5 specifically includes the following: Step S5.1: Based on the contour error ΔP of the component contour at multiple time points and the process parameters collected on-site, perform time-series alignment to construct a time-series feature matrix. ; ； in, This is the contour error sequence from the current time t to the historical time k; This is the contour error sequence from the current time t to the historical time k+1; The heating temperature of the aluminum rod; This refers to the extrusion speed; For traction force; The ambient temperature; The mold wear index; This is the contour error sequence from the current time t; Step S5.2: Based on the aforementioned temporal feature matrix, process it using the Long Short-Term Memory (LSTM) network algorithm model, including: Step S5.2.1: Forget gate processing, as follows: ； in, The output of the forget gate indicates the current time. t The activation value of the forget gate is between [0,1]. Use the Sigmoid activation function; This is the forget gate weight matrix; To concatenate vectors, It is the hidden state from the previous moment; Forget gate bias term; Step S5.2.2: Input gate processing, as follows: ； in, The input gate output represents the activation value of the input gate at the current time t, and its value ranges from [0,1]. The input gate weight matrix; Forget gate bias term; Step S5.2.3: Output gate processing, as detailed below: ； in, The output value is the value of the output gate at the current time t, and its value ranges from [0,1]. This is the output gate weight matrix; This is the output gate bias term; Step S5.2.4: Calculation of cell state and hidden state, as detailed below: ； in, The candidate cell state represents the new information to be added to memory at the current time t. The candidate state weight matrix; Candidate state bias terms; ； in, Let be the cell state at the current time t, and the cell state at the current time t is long-term memory; This represents the cell state at the previous moment; This is element-wise multiplication; ； in, Let be the hidden state at the current time t, and let be the short-term memory / output. Step S5.3: Calculate the attention mechanism weights, including: ； in, This represents the hidden state of historical time k at the current time t. The attention weights assigned range from [0,1]. At a certain point in history; T1 is the length of the time series; To measure the difference between the current time t and historical times k Attention energy scores indicating their correlation or importance; An attention energy score that measures the relevance or importance of the current time t to a historical time j; where, This is the attention vector; This is the historical state weight matrix; This is the current state weight matrix; It is in a state of historical concealment; The current hidden state is T, where T is the matrix transpose. Step S5.4: Calculate the prediction error; ； in, For prediction error, the predicted future time. Contour error; T 1 represents the length of the time series.

5. The method for optimizing the processing accuracy of aluminum profiles according to claim 4, characterized in that, Step S6 specifically includes the following: Step S6.1: Construct an optimization objective function with the sole objective of minimizing the prediction error, as follows: ； in, To optimize the objective, minimize the absolute value of the prediction error; Decision variables: ; Set constraints: ； ； ； ； ； in, This represents the minimum threshold temperature for heating the aluminum rod. This represents the maximum threshold temperature for heating the aluminum rod. The minimum threshold for extrusion speed, The maximum threshold for extrusion speed; The minimum threshold for traction force. This represents the maximum threshold value for traction force. The minimum threshold for ambient temperature. The maximum threshold for ambient temperature; The minimum threshold for mold wear index, The maximum threshold for mold wear index; , , , , This indicates 5 constraints; Step S6.2: For the objective function constructed in step S6.1, the process parameters are solved using the adaptive gradient descent algorithm, as shown in the following formula: ； in, Number of iterations n Process parameters at that time; Number of iterations n+1 Process parameters at that time; The learning rate; For the objective function in step S6.1 The gradient at the point is implicitly satisfied by the constraints of step S6.1 through the iterative process of gradient descent. Among them, the learning rate Adaptive learning rate adjustment is performed to obtain : ； in, The initial learning rate; The attenuation coefficient; Step S6.3: Real-time compensation of process parameters based on PID control, as detailed below: ； in, For the first The amount of compensation at any given moment; , , These are the proportional, integral, and differential coefficients, respectively. Let be the error at time t; For target contour error; This represents the actual profile error at the current time t. This represents the error at time t-1; Indicates from the initial time j =1 to the current time in the accumulated error sequence of time n j One error value; Final applied process parameters The formula is as follows: ； in, These are the basic process parameter settings. .

6. An aluminum profile processing accuracy optimization system, used to execute the aluminum profile processing accuracy optimization method as described in any one of claims 1-5, characterized in that, It includes the following units: target contour acquisition unit, point cloud data acquisition unit, contour error acquisition unit, repetitive execution unit, error prediction unit, process parameter acquisition unit, and execution unit; The target contour acquisition unit is used to acquire the target contour of the aluminum profile cross section; the target contour of the aluminum profile cross section includes multiple basic shape component units; The point cloud data acquisition unit is used to collect the actual contour point cloud data of the aluminum profile cross section and perform preprocessing to obtain the preprocessed actual contour point cloud data. The contour error acquisition unit is used to construct a component fitting contour that reflects multiple basic shape component units based on the preprocessed actual contour point cloud data; calculate the error value from all data points on the component fitting contour to their corresponding target contour based on the component fitting contour and the target contour of the aluminum profile section; and obtain the contour error ΔP of the component contour based on the error value. The repeat execution unit is used to repeatedly execute the point cloud data acquisition unit and the contour error acquisition unit to obtain the contour error ΔP of the component contour at multiple time points of a preset number of time periods. The error prediction unit is used to construct a time-series feature matrix based on the contour error ΔP of the component contour at multiple time points and process parameters of a preset number of time points. Based on the time-series feature matrix, LSTM combined with an attention mechanism is used to predict the error trend and obtain the prediction error; the process parameters include the heating temperature of the aluminum rod in the processing equipment, the extrusion speed of the processing equipment, the traction force of the processing equipment, the die wear index, and the ambient temperature of the processing environment. The process parameter acquisition unit is used to calculate the process parameter compensation amount based on the prediction error. Based on the compensation amount of the process parameters and the set value of the basic process parameters, the final applied process parameters are obtained; The execution unit is used to perform processing according to the final applied process parameters.

7. The aluminum profile processing accuracy optimization system according to claim 6, characterized in that, The point cloud data acquisition unit is specifically used to perform the following steps: Step S21: After the aluminum profile is cooled and shaped, an optical scanner is used to perform a non-contact online scan of the aluminum profile cross section to obtain the actual contour point cloud data of the aluminum profile cross section; Step S22: Employ an outlier detection algorithm based on statistical distribution characteristics to automatically identify and remove measurement noise points. The preprocessed actual contour point cloud data is obtained.

8. The aluminum profile processing accuracy optimization system according to claim 7, characterized in that, The contour error acquisition unit is specifically used to perform the following steps: Step S3.1: Use the B-spline curve fitting formula to fit the preprocessed actual contour point cloud data to construct a component fitting contour that reflects multiple basic shape component units; Step S3.2: Based on the component fitting profile and the aluminum profile cross-section target profile, calculate the normal distance from all data points on the component fitting profile to their corresponding target profile, and the obtained normal distance is the error value; The formula for calculating the normal distance is as follows: ； in, This represents the normal distance to the i-th data point on the component's fitted contour; ) indicates the component fitting profile on the th i The coordinates of each data point; ) represents the first contour on the target contour that matches the component's fitted contour. i The coordinates of the points corresponding to each data point; Indicates the component fitting profile on the first i At the nth data point, the direction of the fitted contour normal is parallel to the nth data point. i The angle between the directions of the lines connecting each data point to the corresponding point on the target contour; Indicates the component fitting profile on the first i Euclidean distance from each data point to the corresponding point on the target contour; Step S3.3: Based on the error value, obtain the contour error ΔP of the component contour. The calculation formula is as follows: ； in, Indicates the profile error of the component outline; tm This represents the total number of fitted data points on the component outline that participated in the calculation. Indicates the first i The absolute value of the normal distance to each data point.

9. The aluminum profile processing accuracy optimization system according to claim 8, characterized in that, The error prediction unit is specifically used to perform the following steps: Step S5.1: Based on the contour error ΔP of the component contour at multiple time points and the process parameters collected on-site, perform time-series alignment to construct a time-series feature matrix. ; ； in, This is the contour error sequence from the current time t to the historical time k; This is the contour error sequence from the current time t to the historical time k+1; The heating temperature of the aluminum rod; This refers to the extrusion speed; For traction force; The ambient temperature; The mold wear index; Step S5.2: Based on the aforementioned temporal feature matrix, process it using the Long Short-Term Memory (LSTM) network algorithm model, including: Step S5.2.1: Forget gate processing, as follows: ； in, The output of the forget gate indicates the current time. t The activation value of the forget gate is between [0,1]. Use the Sigmoid activation function; This is the forget gate weight matrix; To concatenate vectors, It is the hidden state from the previous moment; Forget gate bias term; Step S5.2.2: Input gate processing, as follows: ； in, The input gate output represents the activation value of the input gate at the current time t, and its value ranges from [0,1]. The input gate weight matrix; Forget gate bias term; Step S5.2.3: Output gate processing, as detailed below: ； in, The output value is the value of the output gate at the current time t, and its value ranges from [0,1]. This is the output gate weight matrix; This is the output gate bias term; Step S5.2.4: Calculation of cell state and hidden state, as detailed below: ； in, The candidate cell state represents the new information to be added to memory at the current time t. The candidate state weight matrix; Candidate state bias terms; ； in, Let be the cell state at the current time t, and the cell state at the current time t is long-term memory; This represents the cell state at the previous moment; This is element-wise multiplication; ； in, Let be the hidden state at the current time t, and let be the short-term memory / output. Step S5.3: Calculate the attention mechanism weights, including: ； in, This represents the hidden state of historical time k at the current time t. The attention weights assigned range from [0,1]. At a certain point in history; T1 is the length of the time series; To measure the difference between the current time t and historical times k Attention energy scores indicating their correlation or importance; An attention energy score that measures the relevance or importance of the current time t to a historical time j; where, This is the attention vector; This is the historical state weight matrix; This is the current state weight matrix; It is in a state of historical concealment; The current hidden state is T, where T is the matrix transpose. Step S5.4: Calculate the prediction error; ； in, For prediction error, the predicted future time. Contour error; T 1 represents the length of the time series.

10. The aluminum profile processing accuracy optimization system according to claim 9, characterized in that, The process parameter acquisition unit is specifically used to perform the following steps: Step S6.1: Construct an optimization objective function with the sole objective of minimizing the prediction error, as follows: ； in, To optimize the objective, minimize the absolute value of the prediction error; Decision variables: ; Set constraints: ； ； ； ； ； in, This represents the minimum threshold temperature for heating the aluminum rod. This represents the maximum threshold temperature for heating the aluminum rod. The minimum threshold for extrusion speed, The maximum threshold for extrusion speed; The minimum threshold for traction force. This represents the maximum threshold value for traction force. The minimum threshold for ambient temperature. The maximum threshold for ambient temperature; The minimum threshold for mold wear index, The maximum threshold for mold wear index; , , , , This indicates 5 constraints; Step S6.2: For the objective function constructed in step S6.1, the process parameters are solved using the adaptive gradient descent algorithm, as shown in the following formula: ； in, Number of iterations n Process parameters at that time; Number of iterations n+1 Process parameters at that time; The learning rate; For the objective function in step S6.1 The gradient at the point is implicitly satisfied by the constraints of step S6.1 through the iterative process of gradient descent. Among them, the learning rate Adaptive learning rate adjustment is performed to obtain : ； in, The initial learning rate; The attenuation coefficient; Step S6.3: Real-time compensation of process parameters based on PID control, as detailed below: ； in, For the first The amount of compensation at any given moment; , , These are the proportional, integral, and differential coefficients, respectively. Let be the error at time t; For target contour error; This represents the actual profile error at the current time t. This represents the error at time t-1; Indicates from the initial time j =1 to the current time in the accumulated error sequence of time n j One error value; Final applied process parameters The formula is as follows: ； in, These are the basic process parameter settings. .

Images