Intelligent management method and system for aluminum profile extrusion conveying production line

Abstract

The invention relates to an intelligent management method and system for an aluminum profile extrusion conveying production line, and the method comprises the following steps: monitoring a multi-station equipment parameter, and obtaining an aluminum profile production process parameter; performing thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain an aluminum profile rheological characteristic vector; performing quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain an aluminum profile quality prediction parameter; when the aluminum profile quality prediction parameters are not in a preset target quality parameter range, cooperative control strategy generation is carried out on the station devices based on the aluminum profile quality prediction parameters, and multi-station cooperative control parameters are obtained; and through the multi-station cooperative control parameters, the production line equipment is driven to carry out closed-loop cooperative control on the aluminum profile, so that the technical problems that the control strategy is lagged and the deviation cannot be corrected in time due to the lack of a quality prediction and feedback regulation mechanism based on real-time data are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of aluminum profiles, and in particular to an intelligent management method and system for an aluminum profile extrusion and conveying production line. Background Art

[0002] In the aluminum extrusion production process, traditional production lines rely heavily on manual experience for equipment adjustment and quality control, making it difficult to meet the modern manufacturing industry's demand for high-precision, high-efficiency, and high-quality products. With the advancement of industrial automation, some production lines have introduced sensors and control systems to achieve partial automation. However, the overall process still lacks real-time perception and intelligent decision-making capabilities for complex processes, resulting in significant fluctuations in product quality and insufficient production stability.

[0003] In recent years, the development of intelligent manufacturing technology has provided new insights for optimizing aluminum extrusion conveyor lines. While research has attempted to integrate sensing technology, data analysis, and automated control, many challenges remain in practical application. For example, existing systems often focus solely on monitoring and controlling a single workstation or local parameters, lacking comprehensive awareness and dynamic control mechanisms for the entire multi-station collaborative operation process. This limits improvements in overall production efficiency and consistent product quality across the entire line.

[0004] Furthermore, the aluminum extrusion process involves complex thermomechanical coupling, and its rheological properties are influenced by multiple factors. Traditional modeling methods struggle to accurately predict product quality trends. Most current systems fail to fully account for these nonlinear relationships and lack quality prediction and feedback mechanisms based on real-time data. This results in lagging control strategies and an inability to promptly correct deviations, which in turn impacts final product yield and production efficiency. Therefore, there is an urgent need to develop an intelligent management approach that can integrate multi-source information and achieve closed-loop control of the entire process to address these issues and promote the transition of aluminum extrusion production to intelligent manufacturing. Summary of the Invention

[0005] The main purpose of the present invention is to provide an intelligent management method for an aluminum profile extrusion conveying production line, which solves the technical problem that the lack of a quality prediction and feedback adjustment mechanism based on real-time data leads to a lag in the control strategy and an inability to correct deviations in a timely manner.

[0006] To achieve the above object, the present invention provides an intelligent management method for an aluminum profile extrusion conveying production line, which is applied to the aluminum profile extrusion conveying production line, wherein the aluminum profile extrusion conveying production line is provided with a multi-station device, and the multi-station device is provided with a distributed sensor array, comprising the following steps: During the aluminum profile extrusion process, the parameters of the multi-station equipment are monitored in real time by a distributed sensor array to obtain the aluminum profile production process parameters; Performing a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain a rheological characteristic vector of the aluminum profile; Performing quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain quality prediction parameters of the aluminum profile; When the aluminum profile quality prediction parameter is not within the preset target quality parameter range, a collaborative control strategy is generated for each of the workstation equipment based on the aluminum profile quality prediction parameter to obtain a multi-workstation collaborative control parameter; By means of the multi-station collaborative control parameters, the production line equipment is driven to perform closed-loop collaborative control on the aluminum profiles, so as to realize a production management process that meets the target process requirements.

[0007] Furthermore, the distributed sensor array is used to monitor the parameters of the multi-station equipment in real time to obtain the parameters of the aluminum profile production process, including: Multi-dimensional physical field signals of the multi-station equipment are collected through the distributed sensor array to obtain the original signals of the multi-station equipment, wherein the original signals include temperature field signals, stress field signals, displacement field signals and vibration field signals; multi-scale wavelet noise reduction processing is performed on the original signals to obtain noise-reduced signals; time-frequency domain feature extraction is performed on the noise-reduced signals to obtain aluminum profile production process parameters.

[0008] Furthermore, the aluminum profile is subjected to a thermal-mechanical coupling analysis based on the aluminum profile production process parameters to obtain the aluminum profile rheological characteristic vector, including: Reconstructing the thermal-mechanical coupling field of the multi-station equipment using the aluminum profile production process parameters to obtain a multi-station thermal-mechanical coupling field distribution; Constructing a rheological constitutive equation for the aluminum profile based on the multi-station thermal-mechanical coupling field distribution to obtain a rheological constitutive equation group for the aluminum profile; Numerical solution of the rheological field of the aluminum profile is performed by using the rheological constitutive equation group of the aluminum profile to obtain a numerical solution of the rheological field of the aluminum profile; The rheological characteristic index of the aluminum profile is quantified based on the numerical solution of the rheological field of the aluminum profile to obtain the rheological characteristic vector of the aluminum profile.

[0009] Furthermore, the quality correlation mapping of the aluminum profile is performed based on the rheological characteristic vector of the aluminum profile to obtain the quality prediction parameters of the aluminum profile, including: performing quantitative calculation of the non-uniformity deviation of the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain a rheological non-uniformity index of the aluminum profile; Performing surface quality correlation modeling on the aluminum profile using the aluminum profile rheological heterogeneity index to obtain surface morphology prediction features of the aluminum profile, and extracting multi-scale texture features from the surface morphology prediction features of the aluminum profile to obtain surface quality correlation parameters of the aluminum profile; performing a cross-sectional geometric mapping analysis on the aluminum profile based on the aluminum profile surface quality correlation parameter to obtain an aluminum profile cross-sectional deviation prediction vector, and evaluating the aluminum profile cross-sectional quality based on the aluminum profile cross-sectional deviation prediction vector; The aluminum profile quality prediction parameters are obtained by performing a multi-dimensional quality feature fusion calculation on the aluminum profile through the aluminum profile rheological non-uniformity index, the aluminum profile surface quality correlation parameter and the aluminum profile cross-sectional quality.

[0010] Furthermore, the cross-sectional geometric mapping analysis of the aluminum profile is performed based on the aluminum profile surface quality correlation parameters to obtain the aluminum profile cross-sectional deviation prediction vector, including: Reconstructing the local morphology gradient of the aluminum profile based on the surface quality correlation parameters of the aluminum profile, and discretizing the boundary contour of the aluminum profile using the local morphology gradient to obtain contour feature points of the aluminum profile; Performing non-uniform B-spline fitting processing on the aluminum profile profile feature points to obtain an aluminum profile cross-sectional profile reference curve, and obtaining actual measured cross-sectional data based on the aluminum profile cross-sectional profile reference curve; Calculating a geometric deviation field between a preset theoretical cross-sectional topology model of the aluminum profile and the actual measured cross-sectional data to obtain a cross-sectional deviation distribution matrix of the aluminum profile; Based on the aluminum profile cross-section deviation distribution matrix, the aluminum profile is subjected to multi-dimensional deviation coupling modeling to obtain the aluminum profile cross-section deviation coupling coefficient matrix, and the aluminum profile is subjected to global deviation trend prediction through the aluminum profile cross-section deviation coupling coefficient matrix to obtain the aluminum profile cross-section deviation prediction vector.

[0011] Furthermore, the collaborative control strategy for each of the workstation equipment is generated based on the aluminum profile quality prediction parameters to obtain multi-workstation collaborative control parameters, including: Based on the aluminum profile quality prediction parameters, the quality deviation vector of the aluminum profile is analyzed, and based on the quality deviation vector, multi-station traceability mapping is performed to obtain the associated deviation contribution of each station equipment; Sorting the deviation sensitivity of each of the workstation devices according to the associated deviation contribution of each of the workstation devices to obtain a workstation device deviation sensitivity sequence, and allocating control priorities based on the workstation device deviation sensitivity sequence to obtain a collaborative control priority matrix; Calculating the deviation compensation amount of each workstation device based on the quality deviation vector to obtain a deviation compensation instruction, and weight-allocating the deviation compensation instructions based on the collaborative control priority matrix to obtain a collaborative control instruction; The control parameters of each workstation device are dynamically optimized through the collaborative control instructions to obtain multi-workstation collaborative control parameters.

[0012] Furthermore, the deviation sensitivity of each of the workstation equipment is sorted by the associated deviation contribution of each of the workstation equipment to obtain a workstation equipment deviation sensitivity sequence, including: Performing a multi-dimensional deviation source decomposition on the aluminum profile quality deviation vector based on the associated deviation contribution of each workstation equipment to obtain a deviation sensitivity matrix of each workstation equipment, and performing singular value decomposition processing on the deviation sensitivity matrix of each workstation equipment to obtain a workstation equipment deviation sensitivity feature vector; Performing non-dominated sorting processing on each of the workstation equipment according to the workstation equipment deviation sensitivity feature vector to obtain a workstation equipment deviation sensitivity sorting index; Based on the workstation equipment deviation sensitivity ranking index, cluster analysis is performed on the deviation sensitivity of each workstation equipment to obtain the workstation equipment deviation sensitivity cluster center, and a hierarchical clustering tree is constructed based on the workstation equipment deviation sensitivity cluster center to obtain a sensitivity hierarchical clustering structure; The deviation sensitivity sequence of each workstation equipment deviation sensitivity ranking index is reconstructed through the sensitivity hierarchical clustering structure to obtain a workstation equipment deviation sensitivity sequence, wherein the workstation equipment deviation sensitivity sequence includes a workstation equipment sequence arranged from high to low according to deviation sensitivity.

[0013] The present invention also provides an intelligent management system for an aluminum profile extrusion conveying production line, which is applied to an aluminum profile extrusion conveying production line. The aluminum profile extrusion conveying production line is provided with a multi-station device, and the multi-station device is provided with a distributed sensor array, including: A monitoring module is used to monitor the parameters of the multi-station equipment in real time through a distributed sensor array during the aluminum profile extrusion process to obtain the aluminum profile production process parameters; An analysis module, configured to perform a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain a rheological characteristic vector of the aluminum profile; A mapping module, configured to perform quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain quality prediction parameters of the aluminum profile; A generation module, configured to generate a collaborative control strategy for each of the workstation devices based on the aluminum profile quality prediction parameters when the aluminum profile quality prediction parameters are not within a preset target quality parameter range, to obtain multi-workstation collaborative control parameters; The control module is used to drive the production line equipment to perform closed-loop collaborative control on the aluminum profile through the multi-station collaborative control parameters, so as to achieve a production management process that meets the target process requirements.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0016] The present invention provides an intelligent management method for an aluminum profile extrusion and conveying production line, comprising the following steps: monitoring the parameters of the multi-station equipment to obtain aluminum profile production process parameters; performing thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain an aluminum profile rheological characteristic vector; performing quality correlation mapping on the aluminum profile based on the aluminum profile rheological characteristic vector to obtain an aluminum profile quality prediction parameter; when the aluminum profile quality prediction parameter is not within a preset target quality parameter range, generating a collaborative control strategy for each of the station equipment based on the aluminum profile quality prediction parameter to obtain a multi-station collaborative control parameter; through the multi-station collaborative control parameter, driving the production line equipment to perform closed-loop collaborative control on the aluminum profile, thereby solving the technical problem of lacking a quality prediction and feedback adjustment mechanism based on real-time data, resulting in a lag in the control strategy and an inability to correct deviations in a timely manner, and realizing the formation of aluminum profile quality prediction parameters by correlating and mapping rheological characteristics with product quality, so that the system can identify potential quality risks in advance during the production process, breaking through the traditional quality control mode that relies on post-detection, and improving the product qualification rate and process stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the steps of an intelligent management method for an aluminum profile extrusion and conveying production line according to one embodiment of the present invention; Figure 2 This is a structural diagram of an intelligent management system for an aluminum profile extrusion conveying production line according to an embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 The invention provides an intelligent management method for an aluminum extrusion conveying production line in one embodiment of the present invention, which is applied to the aluminum extrusion conveying production line. The aluminum extrusion conveying production line is provided with a multi-station device, and the multi-station device is provided with a distributed sensor array, comprising the following steps: Step S1: During the aluminum profile extrusion process, the parameters of the multi-station equipment are monitored in real time by a distributed sensor array to obtain the parameters of the aluminum profile production process.

[0021] Specifically, during the aluminum extrusion process, a distributed sensor array monitors the parameters of multiple workstations in real time to determine the aluminum extrusion process parameters. This step relies on deploying multiple workstations throughout the aluminum extrusion conveyor line, with a distributed sensor array consisting of sensor modules with diverse sensing capabilities installed at each key workstation. These sensors collect real-time data on physical quantities such as temperature, pressure, velocity, and displacement at each workstation during operation, and synchronously transmit this data to a central control system for processing, thereby constructing a comprehensive database of aluminum extrusion process parameters. For example, in the heating station, an infrared temperature sensor continuously monitors the heating temperature of the aluminum ingot; in the extrusion die, a pressure sensor measures the pressure distribution of the material as it flows through the die; and in the drawing and cooling stations, displacement and velocity sensors monitor the motion and cooling uniformity of the aluminum extrusion. Through the collaborative operation of these sensors, the system can fully understand the forming state of the aluminum extrusion at each stage, providing accurate data input for subsequent thermal-mechanical coupling analysis, ensuring the accuracy and real-time performance of the entire intelligent management process.

[0022] Step S2: performing a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain a rheological characteristic vector of the aluminum profile.

[0023] Specifically, a thermo-mechanical coupling analysis is performed on the aluminum profile based on the parameters of the aluminum profile production process to obtain the aluminum profile rheological characteristic vector. The implementation of this step depends on obtaining the multi-station equipment parameters monitored in real time by a distributed sensor array, and then introducing these parameters as input variables into the thermo-mechanical coupling analysis model, thereby simulating and analyzing the material response behavior of the aluminum profile under the combined action of high temperature and high pressure. Specifically, the system will combine the temperature data provided by the heating station, the pressure feedback of the mold area, and the speed and displacement information of the traction cooling stage to construct a comprehensive mechanical model covering the temperature field, stress field and strain field. Through numerical calculation or machine learning algorithms, the deformation trend and rheological characteristics of the material under different station conditions are identified, and abstracted into a physically meaningful feature vector - that is, the aluminum profile rheological characteristic vector. For example, in the actual production process, when the initial heating temperature of a batch of aluminum ingots is slightly lower than the standard process requirements, the system can discover the trend of slowing flow velocity and increasing stress concentration at the mold outlet through thermal-mechanical coupling analysis, and then generate a rheological characteristic vector reflecting this abnormal state, providing a key basis for subsequent quality prediction and control strategies, ensuring that the entire intelligent management process has sufficient dynamic adaptability and process insight.

[0024] Step S3: performing quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain quality prediction parameters of the aluminum profile.

[0025] Specifically, based on the rheological characteristic vector of the aluminum profile, the aluminum profile is subjected to quality correlation mapping to obtain the aluminum profile quality prediction parameters. This step is to obtain the rheological characteristic vector generated by the thermal-mechanical coupling analysis, and then establish a mathematical relationship model between the material rheological behavior and the final product quality to convert the abstract material deformation characteristics into quantifiable quality index prediction results. The specific implementation method is to use historical production data and the current real-time collected rheological characteristic vector for feature matching, and combine machine learning or statistical regression methods to build a quality prediction model, so as to identify the key rheological characteristics that affect the dimensional accuracy, surface quality and mechanical properties of the aluminum profile. For example, in actual application, when the system detects that the rheological characteristic vector of the aluminum profile in the mold area during a certain extrusion process shows a high strain rate non-uniformity, the quality correlation mapping model can predict that the batch of profiles may have defects such as wall thickness deviation or surface cracks, and output the corresponding aluminum profile quality prediction parameters as the decision-making basis for the subsequent control strategy, realizing the intelligent transformation process from material behavior analysis to product quality prediction.

[0026] Step S4: When the aluminum profile quality prediction parameter is not within the preset target quality parameter range, a collaborative control strategy is generated for each of the workstation equipment based on the aluminum profile quality prediction parameter to obtain a multi-workstation collaborative control parameter.

[0027] Specifically, when the quality prediction parameters of the aluminum profiles are not within the preset target quality parameter range, a collaborative control strategy is generated for each of the workstation equipment based on the quality prediction parameters of the aluminum profiles to obtain multi-station collaborative control parameters. This step is achieved after the system completes the quality prediction of the current production batch of aluminum profiles. If it is found that its quality prediction parameters deviate from the target range set by the process, the control strategy generation mechanism is triggered, and an intelligent algorithm is used to combine the controllable degrees of freedom and historical response characteristics of each workstation equipment to formulate a multi-station linkage adjustment plan that can effectively correct the deviation. Specifically, the system will reversely map the current quality deviation information to each key process link, analyze the influence weight of heating, extrusion, traction, cooling and other workstations on the final quality, and optimize the operating parameter configuration of each device accordingly to form a set of coordinated control instructions - that is, multi-station collaborative control parameters. For example, during a certain production process, if the quality prediction results show that the aluminum profile has an uneven wall thickness problem, the system can determine that it is caused by uneven material flow in the mold area, and then automatically adjust the temperature distribution of the heating station, adjust the extrusion speed curve, and optimize the air volume control strategy in the cooling stage, so that each station responds in a coordinated manner under closed-loop control, thereby achieving dynamic regulation of product quality and ensuring that the final output meets the target process requirements.

[0028] Step S5: Drive the production line equipment to perform closed-loop collaborative control on the aluminum profiles through the multi-station collaborative control parameters to achieve a production management process that meets the target process requirements.

[0029] Specifically, through the multi-station collaborative control parameters, the production line equipment is driven to perform closed-loop collaborative control on the aluminum profiles to achieve a production management process that meets the target process requirements. This step is to generate the multi-station collaborative control parameters and send these parameters to the actuators and control systems of each station in real time, so that key stations such as heating, extrusion, traction, and cooling can operate synchronously according to the optimized process parameters, and continuously collect feedback data during operation and compare it with the set targets, thereby forming a closed-loop control system with dynamic adjustment and continuous optimization. The specific implementation method is to transmit the multi-station collaborative control parameters to the PLC or motion controller of each station through the industrial communication network, drive the inverter, servo motor, temperature control module and other actuators to accurately adjust the equipment status, and combine the real-time monitoring data sent back by the distributed sensor array to continuously revise the control strategy to ensure that the entire aluminum profile extrusion conveying production line always operates within the optimal process window. For example, during a certain production process, the system identified the tendency of surface cracks in aluminum profiles based on quality prediction results, and accordingly generated multi-station collaborative control parameters for adjusting the heating temperature, reducing the extrusion speed, and enhancing the local cooling intensity. The system then automatically controlled the heating station to increase the holding time, instructing the extrusion cylinder to slow down the advancement rate, and started the cooling fan to enhance heat dissipation, ultimately returning the aluminum profile forming quality to within the target range, realizing closed-loop intelligent management of the entire process from data analysis to process control.

[0030] In a specific embodiment, the real-time monitoring of the multi-station equipment parameters by a distributed sensor array to obtain the aluminum profile production process parameters includes: Multi-dimensional physical field signals of the multi-station equipment are collected through the distributed sensor array to obtain the original signals of the multi-station equipment, wherein the original signals include temperature field signals, stress field signals, displacement field signals and vibration field signals; multi-scale wavelet noise reduction processing is performed on the original signals to obtain noise-reduced signals; time-frequency domain feature extraction is performed on the noise-reduced signals to obtain aluminum profile production process parameters.

[0031] Specifically, the distributed sensor array monitors the parameters of the multi-station equipment in real time to obtain aluminum profile production process parameters. This step is achieved by deploying a distributed sensor array composed of multiple types of sensors at each key station in the aluminum profile extrusion conveyor production line. These sensors can collect multi-dimensional physical field signals from the physical environment in which the multi-station equipment is located during operation, thereby obtaining raw signals including temperature field signals, stress field signals, displacement field signals, and vibration field signals. These raw signals reflect the dynamic behavior of each station equipment under actual working conditions and the material response of the aluminum profile during processing. However, due to the influence of electromagnetic interference and mechanical noise in industrial sites, the raw signals often contain a large amount of meaningless noise components. Therefore, multi-scale wavelet noise reduction processing is required to improve signal quality and information availability. Specifically, the system uses wavelet transform technology to decompose the raw signal at multiple scales and designs a threshold function based on the distribution characteristics of the noise at different scales. This effectively suppresses high-frequency noise while retaining the main characteristics of the signal, thereby obtaining a denoised signal. Subsequently, the system further extracts time-frequency domain features from the denoised signal set, using methods such as short-time Fourier transform (STFT) or wavelet packet analysis to jointly characterize the signal's changing patterns from both the time and frequency dimensions, identifying key process features closely related to the aluminum profile forming process. This ultimately generates aluminum profile production process parameters with engineering semantics, such as the stress peak in the mold area, the period of traction speed fluctuation, and the temperature gradient change rate in the cooling section. For example, during a certain production process, the distributed sensor array detected local fluctuations in the temperature field signal of the aluminum ingot at the heating station. After wavelet denoising, the system identified energy anomalies in specific frequency bands and, combined with the changing trend of the displacement field signal, determined that this was a material flow instability phenomenon caused by uneven heating. The system then extracted production process parameters reflecting this state, providing high-fidelity data input for subsequent thermal-mechanical coupling analysis, ensuring that the data foundation of the entire intelligent management process has good accuracy and real-time performance.

[0032] In a specific embodiment, the performing of a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain the aluminum profile rheological characteristic vector includes: Reconstructing the thermal-mechanical coupling field of the multi-station equipment using the aluminum profile production process parameters to obtain a multi-station thermal-mechanical coupling field distribution; Constructing a rheological constitutive equation for the aluminum profile based on the multi-station thermal-mechanical coupling field distribution to obtain a rheological constitutive equation group for the aluminum profile; Numerical solution of the rheological field of the aluminum profile is performed by using the rheological constitutive equation group of the aluminum profile to obtain a numerical solution of the rheological field of the aluminum profile; The rheological characteristic index of the aluminum profile is quantified based on the numerical solution of the rheological field of the aluminum profile to obtain the rheological characteristic vector of the aluminum profile.

[0033] Specifically, the aluminum profile is subjected to a thermal-mechanical coupling analysis based on the aluminum profile production process parameters to obtain the aluminum profile rheological characteristic vector. This step is implemented as follows: first, the aluminum profile production process parameters extracted in the aforementioned steps, including key physical information such as temperature field signals, stress field signals, displacement field signals, and vibration field signals, are used to reconstruct the thermal-mechanical interaction environment experienced by the multi-station equipment during actual operation with high precision, thereby obtaining a multi-station thermal-mechanical coupling field distribution that reflects the forming state of the material at each station. This thermal-mechanical coupling field distribution not only includes the temperature gradient, stress distribution, and strain evolution that the aluminum profile is subjected to at different stations such as heating, extrusion, traction, and cooling, but also provides basic physical field support for the subsequent establishment of material constitutive relations. On this basis, the system further constructs a set of rheological constitutive equations for aluminum profiles suitable for current process conditions based on this multi-station thermal-mechanical coupling field distribution and the characteristics of the plastic deformation behavior of aluminum profiles under high temperature and high pressure conditions. These equations typically include models such as the Perzyna model or the Johnson-Cook model, which describe the viscoplastic flow of materials. They link externally applied thermal and mechanical boundary conditions with the internal microstructural evolution of the material, accurately characterizing the nonlinear deformation response of aluminum profiles under complex processing conditions. The system then solves the aforementioned rheological constitutive equations for the aluminum profile using finite element simulation techniques or numerical solution algorithms, such as the Newton-Raphson iteration method, to obtain numerical solutions for the rheological field of the aluminum profile at all times and spatial locations throughout the extrusion process. These numerical solutions discretize the dynamic changes in the velocity, stress, and strain rate fields within key regions such as the die inlet, extrusion channel, and exit sizing zone, providing a theoretical basis for a deeper understanding of material flow patterns. For example, during a production run, the system detected a localized temperature drop in the die region through collected temperature field data, while stress field signals indicated elevated principal stress peaks in this region. The resulting rheological constitutive equations, after numerical solution, revealed a significant tendency for shear band formation in this region, indicating a potential risk of quality defects. Finally, based on the numerical solution of the aluminum profile's rheological field obtained above, combined with engineering experience and quality control standards, the system quantifies key rheological properties, including maximum equivalent strain, strain rate sensitivity, flow nonuniformity, and stress concentration factor. Ultimately, these properties are integrated into a set of characteristic vectors with clear physical meaning—the aluminum profile's rheological characteristic vector. This vector not only reflects the aluminum profile's overall deformation capacity and stability under current process conditions but also provides accurate data support for subsequent quality prediction and control strategy generation.For example, in the aforementioned case, the system identified that the flow unevenness of the material at the mold outlet exceeded the set threshold through further analysis of the numerical solution of the rheological field, and output it as a significant component in the rheological characteristic vector to drive the subsequent quality association mapping module, thereby realizing the construction of an intelligent closed-loop link from physical modeling to quality prediction, ensuring that the entire aluminum profile extrusion conveying production line has a high degree of self-perception, self-decision-making and self-adaptation capabilities.

[0034] In a specific embodiment, performing quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain the aluminum profile quality prediction parameter includes: performing quantitative calculation of the non-uniformity deviation of the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain a rheological non-uniformity index of the aluminum profile; Performing surface quality correlation modeling on the aluminum profile using the aluminum profile rheological heterogeneity index to obtain surface morphology prediction features of the aluminum profile, and extracting multi-scale texture features from the surface morphology prediction features of the aluminum profile to obtain surface quality correlation parameters of the aluminum profile; performing a cross-sectional geometric mapping analysis on the aluminum profile based on the aluminum profile surface quality correlation parameter to obtain an aluminum profile cross-sectional deviation prediction vector, and evaluating the aluminum profile cross-sectional quality based on the aluminum profile cross-sectional deviation prediction vector; The aluminum profile quality prediction parameters are obtained by performing a multi-dimensional quality feature fusion calculation on the aluminum profile through the aluminum profile rheological non-uniformity index, the aluminum profile surface quality correlation parameter and the aluminum profile cross-sectional quality.

[0035] Specifically, the aluminum profile is subjected to quality correlation mapping based on the aluminum profile rheological characteristic vector to obtain the aluminum profile quality prediction parameter. This step is implemented as follows: first, the system uses the aluminum profile rheological characteristic vector obtained above as a comprehensive representation of the internal deformation behavior of the material during the extrusion molding process, and quantitatively calculates the non-uniformity deviation through mathematical modeling, identifying the flow inconsistency and stress distribution differences exhibited by the material in different spatial regions or time stages, thereby deriving an aluminum profile rheological non-uniformity index that reflects the overall molding stability. This index is an important basis for measuring whether local defects may occur in the material and can provide key input for the subsequent prediction of surface quality and cross-sectional geometric accuracy. On this basis, the system further uses the aluminum profile rheological non-uniformity index, combined with historical data and process experience, to construct an aluminum profile surface quality correlation modeling mechanism, simulates the surface cracks, orange peel patterns, scratches and other micro-morphological change trends caused by uneven flow of the material at the mold outlet and cooling and shaping stages, and generates aluminum profile surface morphology prediction features accordingly. In order to capture more detailed information about surface quality, the system also extracts multi-scale texture features from the predicted features, using image analysis techniques such as wavelet packet decomposition, Gabor filtering, or gray-level co-occurrence matrix (GLCM) to identify key parameters such as surface roughness, texture directionality, and spot density from the macro to micro levels. This ultimately forms engineering-operable aluminum profile surface quality correlation parameters, providing intuitive data support for product quality assessment. At the same time, based on the above-mentioned aluminum profile surface quality correlation parameters, the system further conducts cross-sectional geometric mapping analysis, models the spatial correspondence between the strain concentration area during the rheological process and the geometric shape of the final profile cross section, identifies possible wall thickness deviation, angular distortion, contour distortion, and other problems, and outputs an aluminum profile cross-sectional deviation prediction vector that describes these deviation trends. Subsequently, the system combines the set process tolerance range to perform a quality grade assessment on the cross-sectional deviation prediction vector to determine whether the current production batch meets the target cross-sectional accuracy requirements, thereby completing a closed-loop prediction of the structural dimensional stability of the aluminum profile. Finally, after obtaining the aluminum profile rheological heterogeneity index, aluminum profile surface quality correlation parameters, and aluminum profile cross-section quality assessment results, the system uses a multi-dimensional quality feature fusion calculation algorithm, employing weighted fusion, principal component analysis (PCA), or deep neural networks to uniformly model and normalize quality indicators from different physical levels, forming a set of aluminum profile quality prediction parameters that can comprehensively reflect the overall quality status of the aluminum profile. This parameter set not only includes a quantitative description of explicit quality characteristics such as surface defects and geometric accuracy, but also implicitly contains information on the trend of the material's internal structural stability and mechanical properties, providing a scientific decision-making basis for the subsequent generation of control strategies.For example, during an actual production process, the distributed sensor array detected large fluctuations in the temperature field in the mold area, resulting in the rheological characteristic vector showing an uneven strain rate distribution. The system then calculated a higher rheological non-uniformity index for the aluminum profile. The subsequent quality association mapping model identified that slight orange peel texture may appear on the surface of the aluminum profile in this state, and confirmed that it belonged to a medium roughness level through texture feature extraction. At the same time, the cross-sectional geometric mapping analysis pointed out that the wall thickness deviation in some areas was close to the upper threshold. Finally, the system output a set of aluminum profile quality prediction parameters through multi-dimensional quality feature fusion calculation, clearly indicating that the current batch has a slight quality risk, triggering the collaborative control module to fine-tune the heating temperature and optimize the cooling wind speed to ensure that the final product meets the target process requirements, thus realizing intelligent closed-loop management of the entire process from material behavior perception to quality prediction to process control.

[0036] In a specific embodiment, performing cross-sectional geometric mapping analysis on the aluminum profile based on the aluminum profile surface quality correlation parameters to obtain the aluminum profile cross-sectional deviation prediction vector includes: Reconstructing the local morphology gradient of the aluminum profile based on the surface quality correlation parameters of the aluminum profile, and discretizing the boundary contour of the aluminum profile using the local morphology gradient to obtain contour feature points of the aluminum profile; Performing non-uniform B-spline fitting processing on the aluminum profile profile feature points to obtain an aluminum profile cross-sectional profile reference curve, and obtaining actual measured cross-sectional data based on the aluminum profile cross-sectional profile reference curve; Calculating a geometric deviation field between a preset theoretical cross-sectional topology model of the aluminum profile and the actual measured cross-sectional data to obtain a cross-sectional deviation distribution matrix of the aluminum profile; Based on the aluminum profile cross-section deviation distribution matrix, the aluminum profile is subjected to multi-dimensional deviation coupling modeling to obtain the aluminum profile cross-section deviation coupling coefficient matrix, and the aluminum profile is subjected to global deviation trend prediction through the aluminum profile cross-section deviation coupling coefficient matrix to obtain the aluminum profile cross-section deviation prediction vector.

[0037] Specifically, the aluminum profile is subjected to cross-sectional geometric mapping analysis based on the surface quality associated parameters of the aluminum profile to obtain a prediction vector for the cross-sectional deviation of the aluminum profile. This step is implemented as follows: the system first uses the surface quality associated parameters of the aluminum profile as input. These parameters are derived from the quality association mapping model constructed based on the rheological characteristic vector of the aluminum profile in the previous link, which can reflect the surface texture changes, local roughness increase, or micro-crack tendency caused by factors such as uneven internal stress distribution and flow velocity differences during the extrusion molding process. On this basis, the system further reconstructs the local morphology gradient of the aluminum profile based on the surface quality associated parameters of the aluminum profile, that is, converts the surface quality state into a three-dimensional morphology change trend with spatial continuity, identifies areas with significant height mutations or curvature anomalies, and divides several key contour feature areas accordingly. Subsequently, the system discretizes the overall boundary contour of the aluminum profile using local morphology gradient information, that is, it selects multiple representative points on the contour line as aluminum profile contour feature points. These points not only cover the main turning points of the outer edge of the profile, but also include local deformation areas caused by surface defects, thereby ensuring subsequent fitting accuracy and engineering practicality. In order to make these discretized contour feature points more in line with the requirements for cross-sectional shape in actual production, the system further performs non-uniform B-spline fitting on them to generate an aluminum profile cross-sectional contour reference curve that retains the details of the original data and has mathematical smoothness. This reference curve serves as a true expression of the cross-sectional morphology of the current batch of aluminum profiles and can be used for comparative analysis with standard design models. Immediately afterwards, the system matches the preset aluminum profile theoretical cross-sectional topology model with the above-mentioned aluminum profile cross-sectional contour reference curve point by point, calculates the geometric deviation values ​​of the two at corresponding spatial positions, and organizes these deviation values ​​into a two-dimensional matrix structure according to the angle or coordinate order to form an aluminum profile cross-sectional deviation distribution matrix. Each element in this matrix represents the difference between the actual measured value and the theoretical value at a specific location, reflecting the degree of dimensional deviation in each area of ​​the entire cross-section, and providing basic data support for subsequent deviation coupling modeling. On this basis, the system conducts multi-dimensional deviation coupling modeling based on the aluminum profile cross-section deviation distribution matrix, comprehensively considering the mutual influence between multiple geometric dimensions such as wall thickness, angle, curvature, and flatness, and constructs an aluminum profile cross-section deviation coupling coefficient matrix that can describe the coordinated change law between various deviation factors. This matrix extracts key coupling factors through methods such as principal component analysis (PCA) or partial least squares regression (PLS), identifies the deviation combination pattern that has the greatest impact on the overall cross-section quality, and is used to predict the global deviation trend that may occur in future rounds of production. Ultimately, it outputs a set of aluminum profile cross-section deviation prediction vectors with time series prediction capabilities.For example, during a certain production process, the distributed sensor array detected large temperature fluctuations at the mold outlet, resulting in abnormal texture directional indicators in the aluminum profile surface quality-related parameters. The system reconstructed the local morphology gradient based on this and found that the contour had slight wavy fluctuations; then, the cross-sectional contour reference curve obtained by non-uniform B-spline fitting was compared with the theoretical model, showing that the wall thickness deviation in multiple areas exceeded the process tolerance; further deviation coupling modeling revealed that the deviation was mainly caused by the combined effect of extrusion speed fluctuations and uneven cooling. The aluminum profile cross-sectional deviation prediction vector generated by the system accurately predicted the angular distortion problem that may occur in the next stage, and triggered the control module to adjust the traction speed and air cooling intensity in advance, realizing active intervention and closed-loop control of product quality, ensuring that the final output meets the target process requirements.

[0038] In a specific embodiment, the collaborative control strategy for each of the workstation equipment is generated based on the aluminum profile quality prediction parameters to obtain multi-workstation collaborative control parameters, including: Based on the aluminum profile quality prediction parameters, the quality deviation vector of the aluminum profile is analyzed, and based on the quality deviation vector, multi-station traceability mapping is performed to obtain the associated deviation contribution of each station equipment; Sorting the deviation sensitivity of each of the workstation devices according to the associated deviation contribution of each of the workstation devices to obtain a workstation device deviation sensitivity sequence, and allocating control priorities based on the workstation device deviation sensitivity sequence to obtain a collaborative control priority matrix; Calculating the deviation compensation amount of each workstation device based on the quality deviation vector to obtain a deviation compensation instruction, and weight-allocating the deviation compensation instructions based on the collaborative control priority matrix to obtain a collaborative control instruction; The control parameters of each of the workstation devices are dynamically optimized through the collaborative control instructions to obtain multi-workstation collaborative control parameters.

[0039] Specifically, the collaborative control strategy for each of the workstation equipment is generated based on the aluminum profile quality prediction parameters to obtain multi-station collaborative control parameters. The implementation method of this step is: first, after the system completes the output of the aluminum profile quality prediction parameters, these parameters contain comprehensive quality status information of the current batch of aluminum profiles in terms of surface morphology, rheological non-uniformity and cross-sectional geometric accuracy. Based on these quality prediction parameters, the system constructs a quality deviation vector that describes the overall quality deviation trend. The vector consists of multiple dimensions, corresponding to different types of process defect indicators, such as wall thickness deviation, surface roughness exceeding the standard, rheological unevenness index, etc. Subsequently, the system further carries out multi-station traceability mapping analysis based on the quality deviation vector, that is, establishes a causal association model between the quality deviation and the operating status of each workstation equipment in the production process. Through historical data analysis and physical modeling, the system identifies the main process links that lead to the current quality deviation, and calculates the contribution of each workstation to the final quality, forming the contribution of the associated deviation of each workstation equipment. For example, if the quality deviation vector indicates that a batch of aluminum profiles has significant uneven wall thickness, the system will trace the abnormal stress distribution in the mold area and the temperature gradient differences during the cooling phase, and quantify the specific contributions of the three workstations (heating, extrusion, and cooling) to the deviation. On this basis, the system ranks the deviation sensitivity of each workstation equipment based on its associated deviation contribution, constructing a workstation equipment deviation sensitivity sequence that reflects each workstation's ability to respond to quality fluctuations. This sequence reflects the potential impact of different workstations on the final quality improvement when changing their operating parameters, providing a basis for subsequent control priority setting. The system further assigns control priorities based on this deviation sensitivity sequence, forming a collaborative control priority matrix that includes the control weights and execution order of each workstation. For example, in the aforementioned case, if the system determines that the cooling workstation has the most significant impact on the wall thickness deviation, it will set its control priority to the highest, ensuring that its adjustment instructions are executed first in the control process. Next, based on the quality deviation vector, the system calculates the deviation compensation required for each workstation. This refers to the process parameter adjustments required to return the aluminum profile quality to the target range, such as the fine-tuning of the heating temperature, the rate of change of the extrusion speed, and the increase or decrease in the cooling air speed. These adjustments are encapsulated as deviation compensation instructions and weighted according to a collaborative control priority matrix. This distributes the compensation tasks according to the control capabilities and influence weights of each workstation, thereby generating a coordinated set of collaborative control instructions. Finally, the system uses these collaborative control instructions to dynamically optimize the control parameters of each workstation. This involves using intelligent algorithms (such as fuzzy control, PID self-tuning, or reinforcement learning) to adjust the set values ​​of each device in real time. The system also continuously refines the control strategy based on actual operating data fed back by the distributed sensor array, ensuring that each workstation responds in a coordinated manner under closed-loop control. The system ultimately outputs a set of multi-workstation collaborative control parameters that effectively correct deviations and improve overall quality consistency.For example, in actual applications, when the system detects slight orange peel texture on the surface of the aluminum profile and local wall thickness deviation in the cross-section, the quality prediction parameter-driven system starts the collaborative control strategy generation mechanism, and identifies the uneven flow in the mold outlet area as the main cause through traceability mapping, and concludes that the low heating temperature and excessive fluctuation in the pulling speed are the main sources of deviation; then the system ranks the sensitivity of the three stations of heating, extrusion and pulling based on the deviation contribution, determines the pulling station as the key adjustment object, and assigns it a compensation instruction with a higher weight; finally, by dynamically optimizing the control parameters of each station, including moderately increasing the holding time of the heating section, reducing the slope of the pulling speed curve, and enhancing the local cooling intensity, the aluminum profile forming quality quickly returns to the target range in subsequent production, realizing intelligent management of the entire process from quality prediction to closed-loop control.

[0040] In a specific embodiment, the deviation sensitivity ranking of each of the workstation devices is performed based on the associated deviation contribution of each of the workstation devices to obtain a deviation sensitivity sequence of the workstation devices, including: Performing a multi-dimensional deviation source decomposition on the aluminum profile quality deviation vector based on the associated deviation contribution of each workstation equipment to obtain a deviation sensitivity matrix of each workstation equipment, and performing singular value decomposition processing on the deviation sensitivity matrix of each workstation equipment to obtain a workstation equipment deviation sensitivity feature vector; Performing non-dominated sorting processing on each of the workstation equipment according to the workstation equipment deviation sensitivity feature vector to obtain a workstation equipment deviation sensitivity sorting index; Based on the workstation equipment deviation sensitivity ranking index, cluster analysis is performed on the deviation sensitivity of each workstation equipment to obtain the workstation equipment deviation sensitivity cluster center, and a hierarchical clustering tree is constructed based on the workstation equipment deviation sensitivity cluster center to obtain a sensitivity hierarchical clustering structure; The deviation sensitivity sequence of each workstation equipment deviation sensitivity ranking index is reconstructed through the sensitivity hierarchical clustering structure to obtain a workstation equipment deviation sensitivity sequence, wherein the workstation equipment deviation sensitivity sequence includes a workstation equipment sequence arranged from high to low according to deviation sensitivity.

[0041] Specifically, the deviation sensitivity of each workstation is ranked based on its associated deviation contribution, resulting in a workstation deviation sensitivity sequence. This step is accomplished by analyzing the aluminum profile quality prediction parameters and generating a quality deviation vector. This quality deviation vector characterizes the degree of deviation for the current batch of aluminum profiles across multiple key quality dimensions. Subsequently, based on the associated deviation contribution of each workstation, the system maps these contributions to the quality deviation vector for a multi-dimensional model, thereby constructing a deviation sensitivity matrix for each workstation that reflects the degree of impact of each workstation on different types of quality deviation. Each row in this deviation sensitivity matrix corresponds to a specific quality deviation indicator (e.g., wall thickness deviation, surface roughness exceeding the standard), and each column represents the sensitivity of a particular workstation to that quality deviation, thus forming a multi-dimensional mapping relationship. To extract key characteristic information, the system further performs singular value decomposition (SVD) on the deviation sensitivity matrix for each workstation, resulting in a set of workstation deviation sensitivity feature vectors that reflect the importance of each workstation in the overall process chain. These eigenvectors reveal the dominant role of different workstations in controlling quality fluctuations and provide a mathematical basis for subsequent ranking. Next, the system uses these workstation deviation sensitivity eigenvectors to perform a non-dominated ranking of each workstation. This approach, similar to the Pareto frontier approach in multi-objective optimization, identifies "highly sensitive" workstations with significant impact across multiple quality deviation dimensions, generating a ranking index for workstation deviation sensitivity. This ranking index not only considers the impact of a single quality metric but also comprehensively assesses each workstation's performance across multiple quality defect types, ensuring a holistic and interpretable ranking result. Furthermore, the system performs cluster analysis based on this deviation sensitivity ranking index, using a K-means or hierarchical clustering algorithm to group the deviation sensitivities of each workstation, identify clusters of workstations with similar sensitivity characteristics, and extract several cluster centers for the deviation sensitivity of each workstation. These cluster centers represent typical behavior patterns of different workstation types in quality control. For example, heating workstations may exhibit high sensitivity to temperature-related defects, while cooling workstations may have a greater impact on surface quality stability. The system then constructs a hierarchical sensitivity clustering tree structure based on the workstation equipment deviation sensitivity cluster centers, forming a hierarchical sensitivity distribution map from the overall to the local level. This structure not only reflects the functional relationships between the various workstations but also provides a structured reference framework for subsequent control strategy formulation. Finally, the system reconstructs the deviation sensitivity ranking index of each workstation equipment using this hierarchical sensitivity clustering structure, integrating the clustering information at each level and the original ranking weights to output a sequence of workstation equipment deviation sensitivities ranked from high to low.For example, in actual applications, when the system detects that a batch of aluminum profiles has uneven wall thickness and orange peel texture on the surface, based on the quality deviation vector and the deviation contribution associated with each workstation equipment, the system identifies stress concentration in the mold area as the main cause, and combines the influence of traction speed fluctuation and uneven cooling to construct a deviation sensitivity matrix; after extracting the characteristic vector through SVD, it is found that the extrusion station and cooling station have the greatest impact on quality fluctuation; then through non-dominated sorting and cluster analysis, it is confirmed that the traction and cooling stations are at a high sensitivity level, and the final generated workstation equipment deviation sensitivity sequence is: "extrusion>cooling>traction>heating", which provides a scientific basis for the subsequent collaborative control priority allocation and realizes the intelligent connection from data-driven to control decision-making.

[0042] The above describes the intelligent management method of the aluminum profile extrusion conveying production line in the embodiment of the present invention. The following describes the intelligent management system of the aluminum profile extrusion conveying production line in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an intelligent management system for an aluminum profile extrusion conveying production line includes: A monitoring module 21 is used to monitor the parameters of the multi-station equipment in real time through a distributed sensor array during the aluminum profile extrusion process to obtain aluminum profile production process parameters; An analysis module 22 is configured to perform a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain a rheological characteristic vector of the aluminum profile; A mapping module 23 is configured to perform quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain quality prediction parameters of the aluminum profile; A generating module 24 is configured to generate a collaborative control strategy for each of the workstation devices based on the aluminum profile quality prediction parameters to obtain multi-workstation collaborative control parameters when the aluminum profile quality prediction parameters are not within a preset target quality parameter range; The control module 25 is used to drive the production line equipment to perform closed-loop collaborative control on the aluminum profile through the multi-station collaborative control parameters, so as to achieve a production management process that meets the target process requirements.

[0043] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0044] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided, wherein the internal structure of the computer device can be as follows: Figure 3As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0045] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0046] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0047] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0048] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0049] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent management method for an aluminum profile extrusion conveying production line, characterized in that: Applied to aluminum profile extrusion conveying production line, the aluminum profile extrusion conveying production line is provided with multi-station equipment, and the multi-station equipment is provided with a distributed sensor array. The following steps are involved: During the aluminum profile extrusion process, the parameters of the multi-station equipment are monitored in real time by a distributed sensor array to obtain the aluminum profile production process parameters; Performing a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain a rheological characteristic vector of the aluminum profile; Performing quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain quality prediction parameters of the aluminum profile; When the aluminum profile quality prediction parameter is not within the preset target quality parameter range, a collaborative control strategy is generated for each of the workstation equipment based on the aluminum profile quality prediction parameter to obtain a multi-workstation collaborative control parameter; By means of the multi-station collaborative control parameters, the production line equipment is driven to perform closed-loop collaborative control on the aluminum profiles, so as to realize a production management process that meets the target process requirements.

2. The intelligent management method for aluminum profile extrusion conveying production line according to claim 1, characterized in that: The real-time monitoring of the multi-station equipment parameters by a distributed sensor array to obtain aluminum profile production process parameters includes: Multi-dimensional physical field signals of the multi-station equipment are collected through the distributed sensor array to obtain the original signals of the multi-station equipment, wherein the original signals include temperature field signals, stress field signals, displacement field signals and vibration field signals; multi-scale wavelet noise reduction processing is performed on the original signals to obtain noise-reduced signals; time-frequency domain feature extraction is performed on the noise-reduced signals to obtain aluminum profile production process parameters.

3. The intelligent management method for aluminum profile extrusion conveying production line according to claim 1, characterized in that: The step of performing a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain the aluminum profile rheological characteristic vector includes: Reconstructing the thermal-mechanical coupling field of the multi-station equipment using the aluminum profile production process parameters to obtain a multi-station thermal-mechanical coupling field distribution; Constructing a rheological constitutive equation for the aluminum profile based on the multi-station thermal-mechanical coupling field distribution to obtain a rheological constitutive equation group for the aluminum profile; Numerical solution of the rheological field of the aluminum profile is performed by using the rheological constitutive equation group of the aluminum profile to obtain a numerical solution of the rheological field of the aluminum profile; The rheological characteristic index of the aluminum profile is quantified based on the numerical solution of the rheological field of the aluminum profile to obtain the rheological characteristic vector of the aluminum profile.

4. The intelligent management method for aluminum profile extrusion conveying production line according to claim 1, characterized in that: The performing quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain the quality prediction parameter of the aluminum profile includes: performing quantitative calculation of the non-uniformity deviation of the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain a rheological non-uniformity index of the aluminum profile; Performing surface quality correlation modeling on the aluminum profile using the aluminum profile rheological heterogeneity index to obtain surface morphology prediction features of the aluminum profile, and extracting multi-scale texture features from the surface morphology prediction features of the aluminum profile to obtain surface quality correlation parameters of the aluminum profile; performing a cross-sectional geometric mapping analysis on the aluminum profile based on the aluminum profile surface quality correlation parameter to obtain an aluminum profile cross-sectional deviation prediction vector, and evaluating the aluminum profile cross-sectional quality based on the aluminum profile cross-sectional deviation prediction vector; The aluminum profile quality prediction parameters are obtained by performing a multi-dimensional quality feature fusion calculation on the aluminum profile through the aluminum profile rheological non-uniformity index, the aluminum profile surface quality correlation parameter and the aluminum profile cross-sectional quality.

5. The intelligent management method for aluminum profile extrusion conveying production line according to claim 4, characterized in that: The step of performing cross-sectional geometric mapping analysis on the aluminum profile based on the aluminum profile surface quality correlation parameters to obtain an aluminum profile cross-sectional deviation prediction vector includes: Reconstructing the local morphology gradient of the aluminum profile based on the surface quality correlation parameters of the aluminum profile, and discretizing the boundary contour of the aluminum profile using the local morphology gradient to obtain contour feature points of the aluminum profile; Performing non-uniform B-spline fitting processing on the aluminum profile profile feature points to obtain an aluminum profile cross-sectional profile reference curve, and obtaining actual measured cross-sectional data based on the aluminum profile cross-sectional profile reference curve; Calculating a geometric deviation field between a preset theoretical cross-sectional topology model of the aluminum profile and the actual measured cross-sectional data to obtain a cross-sectional deviation distribution matrix of the aluminum profile; Based on the aluminum profile cross-section deviation distribution matrix, the aluminum profile is subjected to multi-dimensional deviation coupling modeling to obtain the aluminum profile cross-section deviation coupling coefficient matrix, and the aluminum profile is subjected to global deviation trend prediction through the aluminum profile cross-section deviation coupling coefficient matrix to obtain the aluminum profile cross-section deviation prediction vector.

6. The intelligent management method for aluminum profile extrusion conveying production line according to claim 1, characterized in that: The generating of a collaborative control strategy for each of the workstation equipment based on the aluminum profile quality prediction parameters to obtain multi-workstation collaborative control parameters includes: Based on the aluminum profile quality prediction parameters, the quality deviation vector of the aluminum profile is analyzed, and based on the quality deviation vector, multi-station traceability mapping is performed to obtain the associated deviation contribution of each station equipment; Sorting the deviation sensitivity of each of the workstation devices according to the associated deviation contribution of each of the workstation devices to obtain a workstation device deviation sensitivity sequence, and allocating control priorities based on the workstation device deviation sensitivity sequence to obtain a collaborative control priority matrix; Calculating the deviation compensation amount of each workstation device based on the quality deviation vector to obtain a deviation compensation instruction, and weight-allocating the deviation compensation instructions based on the collaborative control priority matrix to obtain a collaborative control instruction; The control parameters of each workstation device are dynamically optimized through the collaborative control instructions to obtain multi-workstation collaborative control parameters.

7. The intelligent management method for aluminum profile extrusion conveying production line according to claim 6, characterized in that: The step of sorting the deviation sensitivity of each of the workstation devices according to the deviation contribution associated with each of the workstation devices to obtain a deviation sensitivity sequence of the workstation devices includes: Performing a multi-dimensional deviation source decomposition on the aluminum profile quality deviation vector based on the associated deviation contribution of each workstation equipment to obtain a deviation sensitivity matrix of each workstation equipment, and performing singular value decomposition processing on the deviation sensitivity matrix of each workstation equipment to obtain a workstation equipment deviation sensitivity feature vector; Performing non-dominated sorting processing on each of the workstation equipment according to the workstation equipment deviation sensitivity feature vector to obtain a workstation equipment deviation sensitivity sorting index; Based on the workstation equipment deviation sensitivity ranking index, cluster analysis is performed on the deviation sensitivity of each workstation equipment to obtain the workstation equipment deviation sensitivity cluster center, and a hierarchical clustering tree is constructed based on the workstation equipment deviation sensitivity cluster center to obtain a sensitivity hierarchical clustering structure; The deviation sensitivity sequence of each workstation equipment deviation sensitivity ranking index is reconstructed through the sensitivity hierarchical clustering structure to obtain a workstation equipment deviation sensitivity sequence, wherein the workstation equipment deviation sensitivity sequence includes a workstation equipment sequence arranged from high to low according to deviation sensitivity.

8. An intelligent management system for an aluminum profile extrusion conveying production line, characterized in that: Applied to aluminum profile extrusion conveying production line, the aluminum profile extrusion conveying production line is equipped with multi-station equipment, and the multi-station equipment is equipped with a distributed sensor array, including: A monitoring module is used to monitor the parameters of the multi-station equipment in real time through a distributed sensor array during the aluminum profile extrusion process to obtain the aluminum profile production process parameters; An analysis module, configured to perform a thermal-mechanical coupling analysis on the aluminum profile based on the aluminum profile production process parameters to obtain a rheological characteristic vector of the aluminum profile; A mapping module, configured to perform quality correlation mapping on the aluminum profile based on the rheological characteristic vector of the aluminum profile to obtain quality prediction parameters of the aluminum profile; A generation module, configured to generate a collaborative control strategy for each of the workstation devices based on the aluminum profile quality prediction parameters when the aluminum profile quality prediction parameters are not within a preset target quality parameter range, to obtain multi-workstation collaborative control parameters; The control module is used to drive the production line equipment to perform closed-loop collaborative control on the aluminum profile through the multi-station collaborative control parameters, so as to achieve a production management process that meets the target process requirements.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images