Intelligent control system for forming process of large-span complex curved surface metal ribbon material

Abstract

The application discloses a large-span complex curved surface metal ribbon material forming process intelligent regulation and control system and relates to the field of metal processing.The system comprises a collection module, which is used for collecting blank parameters, equipment operation parameters, curved surface precision deviation data and stress distribution data in a metal ribbon forming process in real time and performing data verification synchronously; an analysis module, which is used for receiving the collected data verified in the collection module, analyzing the curved surface precision deviation data and the stress distribution data, outputting precision deviation analysis results, identifying data abnormalities and completing abnormal classification; the application collects multi-dimensional key data in the metal ribbon forming process in real time, guarantees data reliability through multiple verifications, accurately analyzes dominant influencing factors of the curved surface precision deviation and the stress distribution abnormalities, realizes real-time correction of forming precision and dynamic balance of stress distribution, effectively reduces the curved surface precision deviation and improves stress distribution uniformity.

Description

Technical Field

[0001] This invention relates to the field of metal processing technology, specifically to an intelligent control system for the forming process of large-span complex curved surface metal ribbon materials. Background Technology

[0002] Metal ribbons are decorative components that blend metalworking techniques with modern aesthetics. They are primarily made of stainless steel and aluminum alloy, and are formed through processes such as forging, bending, polishing, and painting. Their smooth, curved textures mimic the flowing movement of ribbons, mimicking the heaviness of metal itself. They can be applied to diverse scenarios such as building facades, interior decoration, and landscape sculptures, and also possess practical properties such as corrosion resistance and wear resistance.

[0003] However, during the forming process of large-span complex curved metal ribbons, insufficient surface accuracy and uneven stress distribution are easily caused by equipment errors, which affect the appearance quality of the formed metal ribbons.

[0004] To address this, we proposed an intelligent control system for the forming process of large-span, complex curved surface metal ribbon materials. Summary of the Invention

[0005] In view of the above-mentioned shortcomings of the existing technology, the present invention provides an intelligent control system for the forming process of large-span complex curved surface metal ribbon materials, which can effectively solve the problems of the existing technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions;

[0007] This invention discloses an intelligent control system for the forming process of large-span complex curved surface metal ribbons, comprising:

[0008] The system comprises four modules: a data acquisition module and a management module. The data acquisition module collects raw material parameters, equipment operating parameters, surface accuracy deviation data, and stress distribution data in real time during the metal ribbon forming process, and performs data verification simultaneously. The analysis module receives the verified data from the acquisition module, analyzes the surface accuracy deviation data and stress distribution data, outputs the accuracy deviation analysis results, and identifies and classifies data anomalies. The surface accuracy control module obtains the deviation analysis results from the analysis module, generates surface forming accuracy control commands based on these results, and performs real-time correction of forming accuracy. The stress distribution control module obtains the deviation analysis results from the analysis module, outputs stress control commands, and dynamically adjusts the stress distribution during the metal ribbon forming process. The optimization module combines feedback data from surface accuracy control and stress distribution control to optimize the associated process parameters for metal ribbon forming, generates and outputs process control commands adapted to subsequent forming processes. The management module captures system module operating data and generates system operating logs based on this data.

[0009] The acquisition module is interconnected with the analysis module via a wireless network. The analysis module is interconnected with the surface accuracy control module and the stress distribution control module via a wireless network. The surface accuracy control module and the stress distribution control module are interconnected with the optimization module via a wireless network. The management module is interconnected with the acquisition module and the analysis module via a wireless network. The management module is interconnected with the surface accuracy control module and the stress distribution control module via a wireless network. The management module is interconnected with the optimization module via a wireless network.

[0010] Furthermore, in the acquisition module, the billet parameters include billet material parameters, initial thickness distribution parameters, and microstructure parameters, and the equipment operating parameters include forming die motion parameters, pressure loading parameters, and temperature field distribution parameters;

[0011] The data verification includes data integrity verification, data consistency verification, and data validity verification. The data validity verification follows the following rules:

[0012] ;

[0013] In the formula: Confidence level for the validity of the collected data; , , These are, respectively, integrity weight, consistency weight, and timeliness weight; This is the data integrity coefficient; The data consistency coefficient; This is the data timeliness coefficient;

[0014] When confidence level If the confidence level is not lower than the preset confidence threshold, the data validation is considered successful; when the confidence level is... When the data falls below the preset threshold, the acquisition module triggers a re-acquisition command and records the data anomaly flag.

[0015] Furthermore, the analysis module analyzes the surface accuracy deviation data during operation and identifies the dominant deviation factors through deviation contribution calculation:

[0016] ;

[0017] In the formula: The deviation contribution of the i-th influencing factor; This represents the total accuracy deviation value of the curved surface. The actual value of the i-th influencing factor; Let be the working condition adaptation coefficient of the i-th influencing factor; Let be the partial derivative of the total accuracy deviation with respect to the i-th influencing factor;

[0018] Simultaneously, anomaly identification and classification are performed based on the matching degree between the feature vectors of the data and the preset anomaly type feature library.

[0019] Furthermore, the analysis module analyzes the stress distribution data during operation and identifies the dominant stress anomaly factors by calculating the contribution of stress anomalies:

[0020] ;

[0021] In the formula; The contribution of the stress anomaly to the j-th influencing factor; The actual value of the j-th influencing factor; This represents the total deviation between the actual stress distribution and the ideal stress distribution. Let be the stress adaptation coefficient of the j-th influencing factor; Let be the partial derivative of the total stress deviation with respect to the j-th influencing factor.

[0022] Furthermore, the acquisition module and the analysis module employ a real-time data synchronization protocol. During data transmission, data integrity is verified using a data checksum, the formula for which the data checksum is calculated is:

[0023] ;

[0024] In the formula: For data verification codes; These are the split data collection blocks; For hash functions; This is an XOR operation; Preset verification key;

[0025] After receiving the data, the analysis module recalculates the checksum and compares it with the transmitted checksum. If the comparison matches, the data is confirmed to be valid and parsed. If the comparison does not match, a data retransmission request is sent to the acquisition module.

[0026] Furthermore, when the surface accuracy control module generates surface forming accuracy control instructions, it calculates the control based on the dominant deviation factors and their contribution in the deviation analysis results:

[0027] ;

[0028] In the formula: Let j be the adjustment amount of the j-th process parameter; The deviation contribution of the corresponding dominant deviation factor; This represents the total accuracy deviation value of the curved surface. Let be the sensitivity coefficient of the j-th process parameter; is the control constraint coefficient for the j-th process parameter; n is the total number of process parameters involved in the control. This is a dynamic correction factor;

[0029] The real-time correction of molding accuracy adopts a step-by-step control strategy. First, the process parameters corresponding to the dominant factors with the highest deviation contribution are controlled, and then other related process parameters are controlled based on the control feedback results.

[0030] Furthermore, the stress control command output by the stress distribution control module is generated based on the stress anomaly contribution and stress distribution uniformity evaluation indicators:

[0031] ;

[0032] In the formula: This is the stress distribution uniformity coefficient; This is the preset maximum allowable total stress deviation; This represents the total deviation between the actual stress distribution and the ideal stress distribution.

[0033] This is the stress adjustment amount; This refers to the stress-controlled gain coefficient. This is the stress gradient correction factor; The stress gradient rate of change; The maximum contribution of stress anomaly to the dominant factor; Set a preset uniformity threshold;

[0034] Finally, the stress adjustment amount is determined through a preset stress-process parameter mapping relationship. The stress distribution control module is converted into corresponding equipment operating parameter control commands. The stress distribution control module adopts a hierarchical control strategy: first, it controls the process parameters corresponding to the dominant stress anomaly factors, and then, based on the controlled stress distribution feedback data, it performs secondary control on the associated process parameters.

[0035] Furthermore, when optimizing the process parameters associated with the metal ribbon forming, the optimization module constructs a multi-objective optimization function with the optimization objectives of minimizing the surface forming accuracy deviation, maximizing the stress distribution uniformity, and minimizing process energy consumption. The expression of the optimization function is as follows:

[0036] ;

[0037] In the formula: To optimize the objective function value; This is the set of molding-related process parameters to be optimized. These are the accuracy weight, stress uniformity weight, and energy consumption weight, respectively. This is the preset maximum allowable accuracy deviation value; This represents the current energy consumption of the process. This is the preset energy consumption baseline value; This is the set of lower limits for process parameters; This is the upper limit set of process parameters;

[0038] The optimization module solves the optimization function through an iterative optimization algorithm. During the iteration process, the convergence speed is optimized by dynamically adjusting the weight coefficients. The iterative update formula is as follows:

[0039] ;

[0040] In the formula: This is the set of process parameters after the (k+1)th iteration; This is the set of process parameters for the k-th iteration; This is the iteration step size; This represents the gradient of the objective function at the k-th iteration. This is the iterative decay coefficient.

[0041] Furthermore, the system operation log generated by the management module includes the operating status parameters of each module, data processing time, execution results of control commands, records of abnormal occurrences, and abnormal handling processes.

[0042] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects:

[0043] This invention collects multi-dimensional key data in real time during the metal ribbon forming process, and ensures data reliability through multiple verifications. It accurately analyzes the dominant influencing factors of surface accuracy deviation and stress distribution anomalies, achieving real-time correction of forming accuracy and dynamic equilibrium of stress distribution. This effectively reduces surface accuracy deviation and improves stress distribution uniformity. With forming quality, stress uniformity, and energy consumption as the core, the process parameters are optimized to adapt to subsequent forming requirements and improve production efficiency. At the same time, it fully records relevant operational information, providing support for process optimization and problem traceability, and significantly improving the stability of forming quality and reliability of production processes for large-span complex curved surface metal ribbons. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0045] Figure 1 This is a schematic diagram of the intelligent control system for the forming process of large-span, complex curved metal ribbon materials. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0047] The present invention will be further described below with reference to embodiments.

[0048] Example:

[0049] The intelligent control system for the forming process of large-span complex curved surface metal ribbons in this embodiment, such as... Figure 1 As shown, it includes:

[0050] The data acquisition module is used to collect in real time the blank parameters, equipment operating parameters, surface accuracy deviation data and stress distribution data during the metal ribbon forming process, and to perform data verification simultaneously.

[0051] In the data acquisition module, the billet parameters include billet material parameters, initial thickness distribution parameters, and microstructure parameters, while the equipment operation parameters include forming die motion parameters, pressure loading parameters, and temperature field distribution parameters.

[0052] Data validation includes data integrity validation, data consistency validation, and data validity validation. Data validity validation follows the following rules:

[0053] ;

[0054] In the formula: Confidence level for the validity of the collected data; , , These are, respectively, integrity weight, consistency weight, and timeliness weight; This is the data integrity coefficient; The data consistency coefficient; This is the data timeliness coefficient;

[0055] The above formula combines the actual need for data verification to cover multiple dimensions of validity, and comprehensively considers the three core dimensions of data integrity, consistency and timeliness. By setting manually adaptive weight coefficients, the data integrity coefficient, data consistency coefficient and data timeliness coefficient are weighted and averaged to quantify the confidence of the validity of the collected data. This ensures the comprehensiveness of the verification and can adapt to the data verification needs under different molding conditions through weight adjustment, so that the data verification results are more in line with the actual application scenario.

[0056] When confidence level If the confidence level is not lower than the preset confidence threshold, the data validation is considered successful; when the confidence level is... When the data falls below a preset threshold, the acquisition module triggers a re-acquisition command and records an anomaly flag.

[0057] in, , , All three are positive numbers, and their sum is 1. Furthermore, the weights are manually and adaptively adjusted by the user on the system side. The value is the ratio of the number of target parameter items collected to the total number of preset parameter items. The similarity is calculated by comparing the collected data with standard data samples under the same working conditions. The value is the ratio of a preset timeliness threshold to the data collection time. When the data collection time does not exceed the preset timeliness threshold... =1;

[0058] The analysis module is used to receive the acquired data that has been verified in the acquisition module, analyze the surface accuracy deviation data and stress distribution data, output the accuracy deviation analysis results, and identify data anomalies and complete the anomaly classification.

[0059] The analysis module analyzes the surface accuracy deviation data and identifies the dominant deviation factors by calculating the deviation contribution rate.

[0060] ;

[0061] In the formula: The deviation contribution of the i-th influencing factor; This represents the total accuracy deviation value of the curved surface. The actual value of the i-th influencing factor; Let be the working condition adaptation coefficient of the i-th influencing factor; Let be the partial derivative of the total accuracy deviation with respect to the i-th influencing factor;

[0062] The above formula is used to accurately identify the dominant factors affecting the surface accuracy deviation. It introduces the actual value of the influencing factor, the partial derivative of the total accuracy deviation with respect to the factor, and the working condition adaptation coefficient. The deviation contribution is obtained by the correlation calculation of the three with the total accuracy deviation. This formula can not only reflect the sensitivity of a single influencing factor to the total deviation, but also take into account the differences in the actual role of the influencing factor under different working conditions. This effectively filters out secondary influencing factors and accurately locks the dominant factors that play a key role in the surface accuracy deviation.

[0063] Synchronously, based on the matching degree between the feature vector of the data and the preset anomaly type feature library, anomaly identification and classification are performed. Anomaly types include data mutation anomaly, trend deviation anomaly, and threshold overrun anomaly. Data mutation anomaly includes surface accuracy deviation mutation and stress distribution mutation. Trend deviation anomaly includes accuracy deviation trend deviation and stress distribution trend deviation. The matching degree is calculated by a weighted fusion method of Euclidean distance and Mahalanobis distance.

[0064] in, ∈[0.1,1], its value increases as the adaptability of the influencing factor to the current metal ribbon forming condition increases, and decreases as the adaptability decreases;

[0065] The analysis module analyzes stress distribution data and identifies dominant stress anomaly factors by calculating the contribution of stress anomalies.

[0066] ;

[0067] In the formula; The contribution of the stress anomaly to the j-th influencing factor; The actual value of the j-th influencing factor; This represents the total deviation between the actual stress distribution and the ideal stress distribution. Let be the stress adaptation coefficient of the j-th influencing factor; Let be the partial derivative of the total stress deviation with respect to the j-th influencing factor;

[0068] The above formula addresses the need to identify factors causing abnormal stress distribution. It takes the total deviation between the actual stress distribution and the ideal stress distribution as the core, combines the actual value of the j-th influencing factor, the partial derivative of the total stress deviation with respect to that factor, and the stress fit coefficient that increases or decreases with the intensity of action and the degree of adaptability to the working conditions, and obtains the contribution of stress anomaly through correlation calculation. This highlights the direct correlation between influencing factors and stress deviation, and fully considers the differences in the role of influencing factors under different working conditions, thus achieving the goal of accurately locating the dominant stress anomaly factors.

[0069] in, ∈[0.1,1], its value increases with the increase of the direct effect of the influencing factor on the stress distribution and the degree of adaptation and matching with the current molding condition, and decreases with the decrease of the above effect intensity and degree of adaptation and matching.

[0070] The acquisition module and the analysis module use a real-time data synchronization protocol. During data transmission, data integrity is verified using a data checksum. The formula for calculating the data checksum is:

[0071] ;

[0072] In the formula: For data verification codes; These are the split data collection blocks; For hash functions; This is an XOR operation; Preset verification key;

[0073] To ensure the integrity and security of real-time data transmission between the acquisition module and the analysis module, the acquired data is first split into multiple data blocks and hashed separately. Then, the hash results are integrated through an XOR operation. Finally, the data is XORed with a preset verification key to generate a data verification code. The receiving end can quickly determine whether the data is complete by recalculating the verification code and comparing it with the transmitted verification code. This approach utilizes the fixed-length mapping characteristic of hash functions to ensure the stability of data mapping and enhances the security of data transmission through key XOR, thus adapting to the integrity verification requirements in real-time data synchronization scenarios.

[0074] After receiving the data, the analysis module recalculates the checksum and compares it with the transmitted checksum. If the checksum matches, the data is confirmed to be valid and parsed. If the checksum does not match, a data retransmission request is sent to the acquisition module.

[0075] It should be noted that the hash function mentioned above can be any conventional hash algorithm in this field, such as the SHA series, SM3, etc., as long as it can achieve a fixed-length mapping of data blocks. The specific selection is not limited.

[0076] The surface accuracy control module is used to obtain the deviation analysis results of the surface accuracy deviation data in the analysis module, and generate surface forming accuracy control instructions based on the deviation analysis results to perform real-time correction of forming accuracy.

[0077] When the surface accuracy control module generates surface forming accuracy control instructions, it calculates the control based on the dominant deviation factors and their contribution in the deviation analysis results:

[0078] ;

[0079] In the formula: Let j be the adjustment amount of the j-th process parameter; The deviation contribution of the corresponding dominant deviation factor; This represents the total accuracy deviation value of the curved surface. Let be the sensitivity coefficient of the j-th process parameter; is the control constraint coefficient for the j-th process parameter; n is the total number of process parameters involved in the control. This is a dynamic correction factor;

[0080] The above formula revolves around the precise control target of surface forming accuracy. Based on the contribution of the dominant deviation factors and the total surface accuracy deviation value, it incorporates the sensitivity coefficient, control constraint coefficient and dynamic correction coefficient of the process parameters. Through multi-coefficient linkage calculation, the control amount of a single process parameter is obtained. At the same time, it follows the logic of first controlling the parameter corresponding to the dominant factor with the highest deviation contribution, and then controlling the related parameters according to the feedback. This makes the process parameter control both targeted and adaptable to the needs of different forming stages, avoiding accuracy fluctuations caused by blind adjustment.

[0081] Among them, the real-time correction of molding accuracy adopts a step-by-step control strategy. First, the process parameters corresponding to the dominant factors with the highest deviation contribution are controlled, and then other related process parameters are controlled according to the control feedback results.

[0082] The preset value range is [0.1, 1.5]. The greater the influence of the process parameter on the surface accuracy deviation, the larger the value; the smaller the influence on the surface accuracy deviation, the smaller the value. The preset value range is [0.3, 1]. The more relaxed the control constraint of the process parameter, the larger the value; the more strict the control constraint, the smaller the value. The preset value range is [0.8, 1.2]. The larger the value is when the metal ribbon is in the early stage of forming or the surface accuracy deviation has not reached the preset progress requirement, the smaller the value is when it is in the later stage of forming or the surface accuracy is close to the target value.

[0083] The stress distribution control module is used to obtain the deviation analysis results of the stress distribution data in the analysis module, output stress control commands, and dynamically adjust the stress distribution during the metal ribbon forming process.

[0084] The stress control commands output by the stress distribution control module are generated based on the evaluation indices of stress anomaly contribution and stress distribution uniformity.

[0085] ;

[0086] In the formula: This is the stress distribution uniformity coefficient; This is the preset maximum allowable total stress deviation; the closer the value of U is to 1, the more uniform the stress distribution. This represents the total deviation between the actual stress distribution and the ideal stress distribution.

[0087] The above formula is a visual evaluation of the uniformity of stress distribution. The uniformity coefficient is constructed by the ratio of the actual total stress deviation to the preset maximum allowable total stress deviation. The closer the coefficient is to 1, the more uniform the stress distribution is, which makes it easier to quickly grasp the stress distribution status.

[0088] When calculating the stress adjustment amount, the maximum contribution of the dominant stress anomaly, the difference between the preset uniformity threshold and the actual uniformity coefficient, the stress control gain coefficient and the stress gradient correction coefficient are comprehensively considered. The stress-process parameter mapping relationship is converted into equipment operation parameter control instructions. At the same time, a hierarchical strategy of first controlling the parameters corresponding to the dominant factors and then controlling the related parameters is adopted to ensure that the stress adjustment accurately adapts to the dynamic stress change requirements of complex curved surface forming.

[0089] This is the stress adjustment amount; This refers to the stress-controlled gain coefficient. This is the stress gradient correction factor; The stress gradient rate of change; The maximum contribution of stress anomaly to the dominant factor; Set a preset uniformity threshold;

[0090] Finally, the stress adjustment amount is determined through a preset stress-process parameter mapping relationship. The stress distribution control module adopts a hierarchical control strategy: first, it controls the process parameters corresponding to the dominant stress anomaly factors, and then, based on the controlled stress distribution feedback data, it performs secondary control on the related process parameters.

[0091] in, The preset value range is [0.2, 1.5]. Larger and and When the difference is significant, A larger value indicates that when the stress deviation is within a slight range and the molding condition is highly stable, the stress deviation is less than expected. The smaller the value; The preset value range is [0.1, 0.8]. The higher the value of ζ, the larger the value of ζ, and vice versa.

[0092] The optimization module is used to combine feedback data from surface accuracy control and stress distribution control to optimize the process parameters associated with metal ribbon forming, generate process control instructions adapted to the subsequent forming process, and output them.

[0093] When optimizing the process parameters associated with metal ribbon forming, the optimization module constructs a multi-objective optimization function with the objectives of minimizing surface forming accuracy deviation, maximizing stress distribution uniformity, and minimizing process energy consumption. The expression of the optimization function is as follows:

[0094] ;

[0095] In the formula: To optimize the objective function value; This is the set of molding-related process parameters to be optimized. These are the accuracy weight, stress uniformity weight, and energy consumption weight, respectively, and their sum is 1. This is the preset maximum allowable accuracy deviation value; This represents the current energy consumption of the process. This is the preset energy consumption baseline value; This is the set of lower limits for process parameters; This is the upper limit set of process parameters;

[0096] The above formula addresses the need for multi-objective optimization in the metal ribbon forming process. It constructs an optimization function with the core objectives of minimizing the surface forming accuracy deviation, maximizing the stress distribution uniformity, and minimizing process energy consumption. Through user-defined weight coefficients that sum to 1, the normalized accuracy deviation, stress uniformity inverse index, and energy consumption index are integrated. At the same time, upper and lower limits of process parameters are set to ensure the feasibility of optimization.

[0097] The optimization module solves the optimization function through an iterative optimization algorithm. During the iteration process, the convergence speed is optimized by dynamically adjusting the weight coefficients. The iterative update formula is as follows:

[0098] ;

[0099] In the formula: This is the set of process parameters after the (k+1)th iteration; This is the set of process parameters for the k-th iteration; This is the iteration step size; This represents the gradient of the objective function at the k-th iteration. The iterative decay coefficient;

[0100] During the iterative solution process, the iteration step size, objective function gradient, and iteration decay coefficient that gradually decreases with the number of iterations are introduced. By dynamically adjusting the weight coefficients, the convergence speed is optimized, so that the process parameter optimization can not only fully cover the key performance indicators, but also efficiently converge to the optimal solution, in order to adapt to the multi-dimensional requirements of complex curved surface metal ribbon forming.

[0101] in, The values ​​are user-defined on the system side and are all positive numbers. The initial value is preset and gradually decreases as the number of iterations increases;

[0102] The management module is used to capture system module operation data and generate system operation logs based on the system module operation data.

[0103] The system operation log generated by the management module includes the operating status parameters of each module, data processing time, execution results of control commands, records of anomalies, and the anomaly handling process;

[0104] The acquisition module interacts with the analysis module via a wireless network. The analysis module interacts with the surface accuracy control module and the stress distribution control module via a wireless network. The surface accuracy control module and the stress distribution control module interact with the optimization module via a wireless network. The management module interacts with the acquisition module and the analysis module via a wireless network. The management module interacts with the surface accuracy control module and the stress distribution control module via a wireless network. The management module interacts with the optimization module via a wireless network.

[0105] In this embodiment, the acquisition module collects billet parameters, equipment operating parameters, surface accuracy deviation data, and stress distribution data in real time during the metal ribbon forming process, and performs data verification simultaneously. The analysis module receives the verified acquisition data from the acquisition module, analyzes the surface accuracy deviation data and stress distribution data, outputs the accuracy deviation analysis results, identifies data anomalies, and classifies them. The surface accuracy control module runs afterward to obtain the deviation analysis results of the surface accuracy deviation data from the analysis module, generates surface forming accuracy control instructions based on the deviation analysis results, and performs real-time correction of forming accuracy. Then, the stress distribution control module obtains the deviation analysis results of the stress distribution data from the analysis module, outputs stress control instructions, and dynamically adjusts the stress distribution during the metal ribbon forming process. The optimization module combines the feedback data from surface accuracy control and stress distribution control to optimize the metal ribbon forming-related process parameters, generates process control instructions adapted to the subsequent forming process, and outputs them. Finally, the management module captures the system module operating data and generates a system operating log based on the system module operating data.

[0106] In the above embodiments, the system can capture and verify key data of metal ribbon forming in real time, accurately identify the core factors affecting forming accuracy and stress distribution, dynamically adjust process parameters, and optimize the forming process. This not only greatly improves the forming accuracy of complex curved surfaces and makes the stress distribution more uniform, but also reduces process energy consumption and the occurrence rate of abnormalities.

[0107] Application example:

[0108] This system was used to control the forming process during the production of large-span, complex curved metal ribbons for building facade decoration.

[0109] The system's data acquisition module captures the material parameters, initial thickness distribution parameters, and microstructure parameters of the billet in real time. Simultaneously, it records the motion parameters of the forming die, pressure loading parameters, temperature field distribution parameters, and surface accuracy deviation data and stress distribution data during the forming process. After data integrity, consistency, and validity verification, the calculated confidence level of the acquired data is 0.92, higher than the preset confidence threshold of 0.8. The data verification is passed and synchronized to the analysis module.

[0110] The analysis module receives the verified data, analyzes and calculates the surface accuracy deviation data, and determines that the mold motion parameters are the main influencing factors, with a deviation contribution of 0.75. After analyzing the stress distribution data, it identifies the pressure loading parameters as the dominant stress anomaly factor, with a maximum stress anomaly contribution of 0.68. The data anomaly identification results show no data abrupt changes, trend deviations, or threshold exceeding anomalies.

[0111] Based on the above analysis results, the surface accuracy control module calculates that the adjustment amount of the mold motion parameter is 0.3mm / s. It adopts a step-by-step control strategy, first correcting the parameter in real time, and then adjusting the associated process parameters according to the feedback results, and finally reducing the total surface accuracy deviation from the initial 0.8mm to 0.3mm.

[0112] The stress distribution control module calculated the stress distribution uniformity coefficient to be 0.72. Based on the contribution of the dominant stress anomaly, the stress adjustment amount was determined to be 15 MPa. The stress-process parameter mapping relationship was converted into a pressure loading parameter control command. After the first round of control was completed using a graded control strategy, a second round of control was carried out based on the feedback data. Finally, the stress distribution uniformity coefficient was increased to 0.91, which met the preset requirements.

[0113] The optimization module sets a weight of 0.4 for accuracy, 0.4 for stress uniformity, and 0.2 for energy consumption. It constructs a multi-objective optimization function and solves it using an iterative optimization algorithm, outputting the optimized set of process parameters. After applying these parameters, the process energy consumption decreased from the initial 120 kWh to 105 kWh, while maintaining surface accuracy deviation and stress distribution uniformity in compliance with production standards.

[0114] The management module captures information such as the operating status parameters of each module, data processing time (average 0.5 seconds), and execution results of control commands throughout the process, generating a complete system operation log to provide data support for subsequent production review.

[0115] In summary, the system in the above embodiments collects multi-dimensional key data in real time during the metal ribbon forming process, ensures data reliability through multiple verifications, accurately analyzes the dominant influencing factors of surface accuracy deviation and stress distribution anomalies, achieves real-time correction of forming accuracy and dynamic equilibrium of stress distribution, effectively reduces surface accuracy deviation, improves stress distribution uniformity, optimizes process parameters with forming quality, stress uniformity and energy consumption as the core, adapts to subsequent forming requirements, improves production efficiency, and at the same time, fully records relevant operating information, providing support for process optimization and problem traceability, significantly improving the stability of forming quality and reliability of production process for large-span complex curved surface metal ribbons.

[0116] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent control system for the forming process of large-span, complex curved surface metal ribbons, characterized in that: include: The data acquisition module is used to collect in real time the blank parameters, equipment operating parameters, surface accuracy deviation data and stress distribution data during the metal ribbon forming process, and to perform data verification simultaneously. In the acquisition module, the billet parameters include billet material parameters, initial thickness distribution parameters, and microstructure parameters, and the equipment operation parameters include forming die motion parameters, pressure loading parameters, and temperature field distribution parameters. The data verification includes data integrity verification, data consistency verification, and data validity verification. The data validity verification follows the following rules: ； In the formula: Confidence level for the validity of the collected data; , , These are, respectively, integrity weight, consistency weight, and timeliness weight; This is the data integrity coefficient; The data consistency coefficient; This is the data timeliness coefficient; When confidence level If the confidence level is not lower than the preset confidence threshold, the data validation is considered successful; when the confidence level is... When the data falls below a preset threshold, the acquisition module triggers a re-acquisition command and records an anomaly flag. The analysis module is used to receive the acquired data that has been verified in the acquisition module, analyze the surface accuracy deviation data and stress distribution data, output the accuracy deviation analysis results, and identify data anomalies and complete the anomaly classification. The surface accuracy control module is used to obtain the deviation analysis results of the surface accuracy deviation data in the analysis module, and generate surface forming accuracy control instructions based on the deviation analysis results to perform real-time correction of forming accuracy. The stress distribution control module is used to obtain the deviation analysis results of the stress distribution data in the analysis module, output stress control commands, and dynamically adjust the stress distribution during the metal ribbon forming process. The stress control command output by the stress distribution control module is generated based on the stress anomaly contribution and stress distribution uniformity evaluation indicators: ； In the formula: This is the stress distribution uniformity coefficient; This is the preset maximum allowable total stress deviation; This represents the total deviation between the actual stress distribution and the ideal stress distribution. This is the stress adjustment amount; This refers to the stress-controlled gain coefficient. This is the stress gradient correction factor; The stress gradient rate of change; The maximum contribution of stress anomaly to the dominant factor; Set a preset uniformity threshold; Finally, the stress adjustment amount is determined through a preset stress-process parameter mapping relationship. Converted into corresponding equipment operating parameter control commands; The stress distribution control module adopts a hierarchical control strategy: first, it controls the process parameters corresponding to the dominant stress anomaly factors, and then, based on the controlled stress distribution feedback data, it performs secondary control on the associated process parameters. The optimization module is used to combine feedback data from surface accuracy control and stress distribution control to optimize the process parameters associated with metal ribbon forming, generate process control instructions adapted to the subsequent forming process, and output them. The management module is used to capture system module operation data and generate system operation logs based on the system module operation data.

2. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 1, characterized in that, The analysis module analyzes the surface accuracy deviation data during operation and identifies the dominant deviation factors by calculating the deviation contribution rate. ； In the formula: The deviation contribution of the i-th influencing factor; This represents the total accuracy deviation value of the curved surface. The actual value of the i-th influencing factor; Let be the working condition adaptation coefficient of the i-th influencing factor; Let be the partial derivative of the total accuracy deviation with respect to the i-th influencing factor; Simultaneously, anomaly identification and classification are performed based on the matching degree between the feature vectors of the data and the preset anomaly type feature library.

3. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 2, characterized in that, The analysis module analyzes stress distribution data during operation and identifies dominant stress anomaly factors by calculating the contribution of stress anomalies. ； In the formula; The contribution of the stress anomaly to the j-th influencing factor; The actual value of the j-th influencing factor; This represents the total deviation between the actual stress distribution and the ideal stress distribution. Let be the stress adaptation coefficient of the j-th influencing factor; Let be the partial derivative of the total stress deviation with respect to the j-th influencing factor.

4. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 1, characterized in that, The acquisition module and the analysis module use a real-time data synchronization protocol. During data transmission, data integrity is verified using a data checksum. The formula for calculating the data checksum is as follows: ； In the formula: For data verification codes; These are the split data collection blocks; For hash functions; This is an XOR operation; Preset verification key; After receiving the data, the analysis module recalculates the checksum and compares it with the transmitted checksum. If the comparison matches, the data is confirmed to be valid and parsed. If the comparison does not match, a data retransmission request is sent to the acquisition module.

5. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 1, characterized in that, When the surface accuracy control module generates surface forming accuracy control instructions, it calculates the control based on the dominant deviation factors and deviation contribution in the deviation analysis results: ； In the formula: Let j be the adjustment amount of the j-th process parameter; The deviation contribution of the corresponding dominant deviation factor; This represents the total accuracy deviation value of the curved surface. Let be the sensitivity coefficient of the j-th process parameter; Let be the control constraint coefficient for the j-th process parameter; n represents the total number of process parameters involved in the control; This is a dynamic correction factor; The real-time correction of molding accuracy adopts a step-by-step control strategy. First, the process parameters corresponding to the dominant factors with the highest deviation contribution are controlled, and then other related process parameters are controlled based on the control feedback results.

6. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 2, characterized in that, When optimizing the process parameters associated with metal ribbon forming, the optimization module constructs a multi-objective optimization function with the objectives of minimizing surface forming accuracy deviation, maximizing stress distribution uniformity, and minimizing process energy consumption. The expression of the optimization function is as follows: ； In the formula: To optimize the objective function value; This is the set of molding-related process parameters to be optimized. These are the accuracy weight, stress uniformity weight, and energy consumption weight, respectively. This is the preset maximum allowable accuracy deviation value; This represents the current energy consumption of the process. This is a preset energy consumption baseline value; This is the set of lower limits for process parameters; This is the upper limit set of process parameters; The optimization module solves the optimization function through an iterative optimization algorithm. During the iteration process, the convergence speed is optimized by dynamically adjusting the weight coefficients. The iterative update formula is as follows: ； In the formula: This is the set of process parameters after the (k+1)th iteration; This is the set of process parameters for the k-th iteration; This is the iteration step size; This represents the gradient of the objective function at the k-th iteration. This is the iterative decay coefficient.

7. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 1, characterized in that, The system operation log generated by the management module includes the operation status parameters of each module, data processing time, execution results of control commands, records of abnormal occurrences, and abnormal handling processes.

8. The intelligent control system for the forming process of large-span complex curved surface metal ribbons according to claim 1, characterized in that, The acquisition module is interconnected with the analysis module via a wireless network. The analysis module is interconnected with the surface accuracy control module and the stress distribution control module via a wireless network. The surface accuracy control module and the stress distribution control module are interconnected with the optimization module via a wireless network. The management module is interconnected with the acquisition module and the analysis module via a wireless network. The management module is interconnected with the surface accuracy control module and the stress distribution control module via a wireless network. The management module is interconnected with the optimization module via a wireless network.

Images