A cable sheath mold change control method and system

Abstract

The present application belongs to the technical field of cable sheath production, and discloses a cable sheath mold change control method and system, the method comprising: A1. determining initial process parameters based on target sheath specifications using a historical benchmark model to start an extrusion device; A2. collecting real-time process parameters and corresponding real-time sheath product quality data during the operation of the extrusion device; A3. calculating a parameter compensation adjustment amount between a current operating condition and a historical benchmark operating condition based on the real-time process parameters and the corresponding real-time sheath product quality data; A4. combining the initial process parameters with the parameter compensation adjustment amount to obtain a process parameter adjustment value for the current operating condition, and sending the result to the control system of the extrusion device so that the extrusion device operates according to the process parameter adjustment value; A5. repeating steps A2-A4 until the sheath product quality meets the target requirements; thereby improving the efficiency and accuracy of process parameter adjustment after mold change, reducing dependence on operator experience, and reducing scrap rate.

Description

Technical Field

[0001] The present application relates to the technical field of cable sheath production, and in particular to a cable sheath mold change control method and system. Background Art

[0002] The production of cable sheaths is a critical step in the cable manufacturing process, typically using an extrusion process. In this process, polymer materials are heated and plasticized within an extruder, then extruded through a specifically shaped die. After cooling, solidification, and pulling, the final product is obtained. To accommodate varying cable specifications or materials, the extrusion die frequently needs to be changed during production.

[0003] After replacing the die, the extrusion equipment's process parameters, such as extrusion temperature, screw speed, and pull-off speed, need to be reset and adjusted to ensure that the cable sheath meets quality requirements (such as outer diameter, wall thickness, and roundness). Traditional parameter adjustment methods rely heavily on operator experience and tentative adjustments. This trial-and-error approach is inefficient, time-consuming, and prone to producing a high number of substandard products, resulting in waste of raw materials. Furthermore, the efficiency and accuracy of these adjustments are significantly affected by the operator's skill level, making it difficult to ensure stable and consistent production.

[0004] To improve the efficiency and accuracy of parameter adjustments, the industry is attempting to train machine learning models using historical production data. This approach aims to understand the relationship between process parameters and product quality, thereby recommending initial process parameters after mold changes. However, cable sheathing production lines typically operate continuously for extended periods, subjecting key equipment components to normal wear and aging, such as screws, barrels, and molds. Furthermore, even for the same raw material grade, slight differences in properties can exist between batches. These variations in equipment status and raw material properties are hidden factors that are difficult to accurately measure directly and in real time.

[0005] When using models trained on historical production data to recommend initial process parameters, the challenge lies in the fact that historical data was collected under specific equipment conditions and raw material batches, and actual operating conditions during current production may deviate from these historical conditions. These operating condition deviations, caused by subtle and intangible factors, can mean that even if production is started according to the model's initial parameters, actual product quality may not fully meet target requirements, or may require a long time to reach a stable, qualified state.

[0006] In this scenario, operators still need to manually fine-tune parameters based on actual product quality deviations. However, because the influence of equipment status and material properties is dynamic and difficult to quantify, and the relationship between process parameters and product quality is complex, operators struggle to accurately determine the cause of the deviations and determine the appropriate direction and amount of adjustment. This results in an inefficient adjustment process, prolonged mold change times, and the generation of scrap. More importantly, equipment wear and raw material batch variations are continuous, and production conditions are always slowly changing. Models trained on fixed historical data will gradually lose accuracy in their recommended parameters. A key technical challenge is how to adapt the parameter adjustment process to the current specific operating conditions, provide effective adjustment guidance, and reduce reliance on operator experience, given the influence of these difficult-to-perceive hidden factors. The existing technology lacks a method and system that can effectively perceive or adapt to operating condition deviations caused by these difficult-to-quantify hidden factors, and accordingly make accurate, rapid, and adaptive process parameter adjustments.

[0007] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the Invention

[0008] The purpose of this application is to provide a cable sheath mold change control method and system, which can improve the efficiency and accuracy of process parameter adjustment after mold change, reduce dependence on operator experience, and reduce scrap rate.

[0009] In a first aspect, the present application provides a cable sheath die change control method for adjusting and controlling the process parameters of an extrusion device after the cable sheath extrusion device changes its die. The method comprises the following steps:

[0010] A1. Based on the target jacket specifications, use the historical benchmark model to determine the initial process parameters to start the extrusion equipment;

[0011] A2. During the operation of the extrusion equipment, collect real-time process parameters and corresponding real-time sheath product quality data;

[0012] A3. Calculate the parameter compensation adjustment between the current operating conditions and the historical benchmark operating conditions based on the real-time process parameters and the corresponding real-time sheath product quality data;

[0013] A4. Combining the initial process parameters with the parameter compensation adjustment amount to obtain the process parameter adjustment value for the current working conditions, and sending it to the extrusion equipment control system so that the extrusion equipment operates according to the process parameter adjustment value;

[0014] A5. Repeat steps A2 to A4 until the sheath product quality meets the target requirements.

[0015] In a second aspect, the present application provides a cable sheath die change control system for adjusting and controlling the process parameters of the extrusion equipment after the cable sheath extrusion equipment changes its die. The system comprises:

[0016] An initial parameter recommendation module is used to determine the initial process parameters based on the target sheath specifications using a historical benchmark model to start the extrusion equipment;

[0017] Real-time data acquisition module, which collects real-time process parameters and corresponding real-time sheath product quality data during the operation of the extrusion equipment;

[0018] The working condition compensation calculation module is used to calculate the parameter compensation adjustment between the current working condition and the historical benchmark working condition based on the real-time process parameters and the corresponding real-time sheath product quality data;

[0019] A parameter comprehensive adjustment module is used to combine the initial process parameters with the parameter compensation adjustment amount to obtain the process parameter adjustment value for the current working condition, and send it to the control system of the extrusion equipment so that the extrusion equipment operates according to the process parameter adjustment value;

[0020] The iterative control module is used to trigger the real-time data acquisition module, the working condition compensation calculation module and the parameter comprehensive adjustment module to run repeatedly until the sheath product quality meets the target requirements.

[0021] Beneficial effects: The cable sheath mold change control method and system provided in the present application effectively solves the problems in the prior art of low efficiency of parameter adjustment after mold change, reliance on operator experience, and difficulty in adapting to equipment aging and material batch changes by utilizing a historical benchmark model to determine initial parameters and combining real-time data for iterative compensation adjustment. It has the advantages of improving the efficiency and accuracy of process parameter adjustment after mold change, reducing reliance on operator experience, and reducing scrap rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of a cable sheath mold change control method provided in an embodiment of the present application.

[0023] Figure 2 This is a structural diagram of the cable sheath mold changing control system provided in an embodiment of the present application.

[0024] Explanation of reference numbers: 1. Initial parameter recommendation module; 2. Real-time data acquisition module; 3. Working condition compensation calculation module; 4. Parameter comprehensive adjustment module; 5. Iterative control module. DETAILED DESCRIPTION

[0025] The technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. The components of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of this application.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0027] refer to Figure 1 The present application proposes a cable sheath die change control method for adjusting and controlling the process parameters of the extrusion equipment after the cable sheath extrusion equipment changes the die. The method comprises the following steps:

[0028] A1. Based on the target jacket specifications, use the historical benchmark model to determine the initial process parameters to start the extrusion equipment;

[0029] A2. During the operation of the extrusion equipment, collect real-time process parameters and corresponding real-time sheath product quality data;

[0030] A3. Calculate the parameter compensation adjustment between the current operating conditions and the historical benchmark operating conditions based on the real-time process parameters and the corresponding real-time sheath product quality data;

[0031] A4. Combining the initial process parameters with the parameter compensation adjustment amount to obtain the process parameter adjustment value for the current working conditions, and sending it to the extrusion equipment control system so that the extrusion equipment operates according to the process parameter adjustment value;

[0032] A5. Repeat steps A2 to A4 until the sheath product quality meets the target requirements.

[0033] Among them, the historical benchmark model refers to a mathematical model trained based on historical production data that can reflect the relationship between process parameters and sheath product quality. It can be implemented using machine learning algorithms, such as neural network models, support vector machine models, and decision tree models. It is mainly used to provide a reasonable initial process parameter starting point for the production of new specifications of products.

[0034] Among them, real-time process parameters refer to the real-time values ​​of parameters such as extrusion temperature, screw speed, and traction speed collected by sensors during the actual operation of the extrusion equipment. They can be implemented using sensors and data acquisition modules of industrial automation control systems, such as temperature sensors, speed sensors, and speed sensors. They are mainly used to reflect the current operating status of the equipment.

[0035] Among them, real-time sheath product quality data refers to the quality index value obtained by measuring the sheath products actually produced during the operation of the extrusion equipment. It can be achieved by using online or offline measuring equipment, such as outer diameter measuring instruments, wall thickness measuring instruments, and roundness measuring instruments. It is mainly used to evaluate whether the quality of the current product meets the requirements.

[0036] Among them, the parameter compensation adjustment amount refers to the adjustment value calculated based on the current real-time data and used to correct the initial process parameters to adapt to the current actual production conditions. It can be calculated using methods based on model prediction error or sensitivity analysis, such as reverse deduction based on local sensitivity coefficients. It is mainly used to compensate for the deviation between the historical benchmark model and the current actual conditions.

[0037] Among them, the process parameter adjustment value refers to the parameter setting value finally used to control the extrusion equipment after combining the initial process parameters with the calculated parameter compensation adjustment amount. It can be obtained by simple addition or a more complex weighted fusion method. It is mainly used to guide the extrusion equipment to operate according to parameters that are more suitable for the current working conditions.

[0038] The core innovation of this application is that by combining the initial process parameters determined based on the historical benchmark model with the parameter compensation adjustment amount calculated based on real-time data, adaptive adjustment of the process parameters of the extrusion equipment is achieved, so as to achieve the effect of quickly and accurately making the sheath product quality meet the target requirements.

[0039] The solution of this application first utilizes a historical benchmark model to provide reasonable initial startup parameters for the extrusion equipment, avoiding reliance on manual experience. After the equipment is started up, the solution continuously collects real-time process parameter and product quality data. This real-time data reflects the current actual production conditions, including the impact of implicit factors such as equipment status and material properties that are difficult to directly quantify. Based on this real-time data, the solution calculates the deviation between the current operating conditions and the historical benchmark conditions and converts it into a parameter compensation adjustment. (Rather than converting the deviation between actual quality indicators and target sheath specifications into a parameter compensation adjustment, this solution calculates the deviation between the current operating conditions and the historical benchmark conditions to more comprehensively reflect the impact of these implicit factors, allowing for more targeted parameter compensation adjustments.) This compensation adjustment corrects the initial parameters to make them more relevant to the current actual production environment. (This means that the adjusted parameters not only bring product quality closer to the target specifications, but also better adapt to the current equipment status and material properties, thereby improving the efficiency and accuracy of the adjustment and ensuring the stability of the production process.) Subsequently, the initial parameters are combined with the compensation adjustment to form new process parameter adjustments, which are sent to the equipment control system for execution. The entire process forms a closed loop, continuously collecting real-time data, calculating compensation, and adjusting parameters until product quality meets target requirements. This iterative adjustment method enables the system to dynamically adapt to changing operating conditions during production, gradually optimizing parameter settings and ultimately producing qualified products in a stable manner.

[0040] Through the above technical solution, the present application can effectively solve the problems of low production efficiency and unstable product quality caused by relying on manual experience to adjust the process parameters of the cable sheath extrusion equipment after the mold is changed. The use of historical benchmark models to provide initial parameters shortens the startup and debugging time. By collecting data in real time and calculating the parameter compensation adjustment amount, the system can adapt to the current actual production conditions and overcome the impact of hidden factors such as equipment aging and material batch differences. Closed-loop iterative control based on compensation adjustment realizes the rapid and accurate optimization of process parameters and reduces the generation of waste during the trial and error process. Ultimately, the production efficiency and product quality stability after the mold change are improved, and the dependence on operator experience is reduced.

[0041] In some embodiments, the historical benchmark model includes a plurality of parameter optimization sub-models, each parameter optimization sub-model corresponding to a quality indicator; the parameter optimization sub-model takes process parameters as input and outputs corresponding quality indicators; the quality indicators include outer diameter, wall thickness, and roundness; the process parameters include extrusion temperature, screw speed, and pulling speed;

[0042] Step A1 includes:

[0043] A101. Extract multiple quality indicators of the target sheath specifications, including outer diameter, wall thickness, and roundness;

[0044] A102. For each quality indicator, call the corresponding parameter optimization sub-model;

[0045] A103. Based on the preset weight allocation strategy, assign a weight to each parameter optimization sub-model; the weight reflects the importance of the corresponding quality indicator in the overall quality assessment;

[0046] A104. A multi-objective optimization algorithm is used to minimize the deviation between the weighted output of all parameter optimization sub-models and the corresponding quality indicators in the target sheath specifications. A set of initial process parameters is obtained and used as the starting parameters of the extrusion equipment.

[0047] Among them, the parameter optimization sub-model refers to the model unit in the historical benchmark model that performs parameter optimization or prediction for specific quality indicators. Each sub-model focuses on describing the relationship between process parameters and a specific quality indicator, and can be implemented using an independent prediction function. Its purpose is to decompose the complex parameter-multiple quality indicator relationship.

[0048] Among them, quality indicators refer to the key parameters for measuring the quality of cable sheath products, including outer diameter, wall thickness and roundness. These indicators directly reflect the geometric size and shape accuracy of the product. Their purpose is to quantify whether the product meets the specification requirements.

[0049] Among them, process parameters refer to the key control variables that affect the cable sheath extrusion process and product quality, including extrusion temperature, screw speed and pulling speed. These parameters are inputs that can be adjusted by the control system. The purpose is to control product quality by adjusting these parameters.

[0050] Among them, the target sheath specification refers to the quality standard of the cable sheath product required to be achieved in this production task, including specific numerical requirements for outer diameter, wall thickness and roundness. Its purpose is to provide a target for parameter setting and quality control.

[0051] Among them, the weight allocation strategy refers to a method to determine the importance of different quality indicators in the overall optimization goal. It can be set based on product type or importance. Its purpose is to reflect the relative importance of different quality indicators in multi-objective optimization.

[0052] Among them, multi-objective optimization algorithm refers to a type of algorithm used to solve optimization problems with multiple objective functions. It can be implemented using genetic algorithm, and its purpose is to find a set of solutions that can optimize multiple objectives at the same time.

[0053] Among them, weighted output refers to the result obtained by weighted combination of the outputs of multiple parameter optimization sub-models according to preset weights. Its purpose is to integrate the predicted values ​​of multiple quality indicators into a comprehensive evaluation value.

[0054] Among them, deviation minimization refers to the objective function of the optimization algorithm, which aims to minimize the difference between the weighted output of the parameter optimization sub-model and the weighted target value of the corresponding quality indicator in the target sheath specification. Its purpose is to find the process parameter combination that makes the predicted quality closest to the target quality.

[0055] The solution of this application refines the historical benchmark model into multiple parameter optimization sub-models, each focusing on a specific quality indicator. This allows for a more accurate capture of the relationship between process parameters and each quality indicator. When determining the initial process parameters, the quality indicators of the target sheath specifications are first extracted and the corresponding parameter optimization sub-model predictions are invoked. By introducing a weight distribution strategy, the importance of different quality indicators can be adjusted according to actual needs, enabling the optimization process to prioritize key indicators. Subsequently, a multi-objective optimization algorithm is employed to determine a set of initial process parameters, with the goal of minimizing the weighted deviation between the weighted predictions of all parameter optimization sub-models and the target specifications. This approach simultaneously considers multiple quality indicators, such as outer diameter, wall thickness, and roundness, and finds a balance between them, avoiding the problem of a single model failing to address all indicators. Using this set of initial parameters, which balances multiple quality indicators, for the startup of the extrusion equipment, ensures that the product is closer to the target specifications during the startup phase, providing a more optimal starting state for subsequent real-time adjustments. This helps reduce startup adjustment time and waste generation, improving mold change efficiency.

[0056] Through the above technical solution, the historical benchmark model is refined and combined with multi-objective optimization, which can better balance multiple quality indicators such as outer diameter, wall thickness and roundness when determining the initial process parameters. This allows the extrusion equipment to obtain product quality closer to the target specifications during the startup phase, reducing the difficulty and time of subsequent adjustments, improving mold change efficiency, and reducing scrap rates.

[0057] Preferably, step A103 may include:

[0058] For the target sheath specification, query the preset mapping relationship table of product specifications and weight allocation strategies to determine the weight allocation strategy that matches the current target sheath specification;

[0059] If a matching weight allocation strategy is found, weights are directly assigned to each parameter optimization sub-model according to the strategy found; if no matching weight allocation strategy is found, weights are assigned to each parameter optimization sub-model according to the preset default weight allocation strategy, or according to the operator's custom settings;

[0060] In response to the aging degree of the extrusion equipment, a weight adjustment coefficient that matches the current aging degree of the extrusion equipment is determined based on a preset mapping relationship table between the aging degree of the equipment and the weight adjustment coefficient, and the assigned weight is adjusted based on the weight adjustment coefficient; wherein the weight adjustment coefficient is used to adjust the relative importance between different quality indicators to adapt to the impact of equipment aging.

[0061] Among them, the mapping relationship table of preset product specifications and weight allocation strategies refers to a data structure used to store the association between different target sheath specifications and corresponding weight allocation strategies. Specifically, it can be a lookup table or database, and its purpose is to quickly obtain the corresponding weight configuration according to the target sheath specifications currently produced.

[0062] Among them, the weight allocation strategy refers to a set of numerical values, each of which corresponds to a parameter optimization sub-model, indicating the relative importance of the quality indicators corresponding to the parameter optimization sub-model in determining the initial process parameters. Specifically, it can be a set of normalized weight values, the purpose of which is to quantify the priority of different quality indicators in the overall optimization goal.

[0063] Among them, the preset default weight allocation strategy refers to the basic weight configuration adopted when no strategy matching the current target sheath specification is found in the preset mapping relationship table between product specifications and weight allocation strategies. Its purpose is to provide a universal, comprehensive weight allocation solution.

[0064] Among them, the operator's customized settings allow the operator to manually input or modify the weight distribution value based on actual production experience or specific needs. Its purpose is to increase the flexibility of the system and the ability of manual intervention.

[0065] Among them, the preset mapping relationship table between the aging degree of equipment and the weight adjustment coefficient refers to another data structure, which is used to store the association between the aging degree of different extrusion equipment and the corresponding weight adjustment coefficient. Specifically, it can be a lookup table or database, the purpose of which is to obtain the adjustment factor for correcting the weight according to the current aging status of the equipment.

[0066] Among them, the weight adjustment coefficient refers to the numerical value used to correct the assigned weight, which can be a multiplication factor or an addition amount. Its purpose is to dynamically adjust the relative importance of different quality indicators to better adapt to the impact of equipment aging on product quality.

[0067] The solution of this application dynamically adjusts the weight allocation of the parameter optimization sub-model by combining the target sheath specification and the aging of the extrusion equipment. First, based on the current target sheath specification, the system queries a preset mapping table to obtain a weight allocation strategy that matches that specification. This specification-based weight allocation enables the system to prioritize the most impactful quality indicators for different sheath types and sizes. For example, for thin-walled sheaths, wall thickness uniformity may be more important, while for large-diameter sheaths, roundness may be more important. If no preset strategy exists for a specific specification, a default strategy is used or the operator can manually set it, ensuring the solution's universality and flexibility. Furthermore, the aging of the extrusion equipment is further considered. Equipment aging can affect the sensitivity of certain process parameters to specific quality indicators. For example, screw wear may make wall thickness less sensitive to changes in screw speed. The aging level can be pre-assessed by combining factors such as accumulated equipment operating time, energy consumption changes, and operating vibration (e.g., using an evaluation model or expert experience). By querying the mapping table between equipment aging level and weight adjustment coefficients, the system obtains the adjustment coefficient corresponding to the current equipment aging status. These adjustment factors are applied to the weights previously determined based on product specifications, providing a secondary correction to the relative importance of different quality indicators. For example, if wall thickness is more susceptible to deviation due to aging equipment, the weight corresponding to wall thickness may be increased by the adjustment factor, giving wall thickness a higher priority during parameter optimization.

[0068] Thus, through the dual consideration and dynamic adjustment of product specifications and equipment aging, the weight distribution used in the multi-objective optimization algorithm is ultimately determined. This dynamic weight adjustment mechanism enables the parameter optimization process based on the historical benchmark model to more accurately reflect the needs and challenges of current actual production conditions, improving the accuracy of initial process parameter recommendations. Compared with solutions that rely solely on fixed weights or single-factor adjustments, this can more effectively address the uncertainties brought about by product diversity and equipment status changes in actual production, thereby providing a more accurate starting point for subsequent process parameter adjustments, reducing trial and error and adjustment time, and improving production efficiency and product quality stability after mold changes.

[0069] Preferably, step A104 may include:

[0070] Determine the constraints of the multi-objective optimization algorithm; the constraints include upper and lower limits of extrusion temperature, upper and lower limits of screw speed, and upper and lower limits of pulling speed;

[0071] Initialize the parameters of the multi-objective optimization algorithm; the initialized parameters include population size, crossover probability, and mutation probability;

[0072] Genetic algorithm is used as a multi-objective optimization algorithm, and the objective function is to minimize the deviation between the weighted output of all parameter optimization sub-models and the corresponding quality indicators in the target sheath specifications;

[0073] Under the constraints, based on the objective function, a Pareto optimal solution set is obtained by iteratively searching for the optimal solution through a genetic algorithm; each solution in the Pareto optimal solution set corresponds to a set of initial process parameters;

[0074] From the Pareto optimal solution set, a set of initial process parameters are selected as the startup parameters of the extrusion equipment according to preset evaluation indicators; the evaluation indicators comprehensively consider the degree of deviation between each quality indicator and the target sheath specifications and the stability of the process parameters.

[0075] Among them, constraints refer to restrictions imposed on the value range of optimization variables or the relationship between variables, which can be handled by penalty function method, feasibility rule method or special operator method.

[0076] Initializing the parameters of a multi-objective optimization algorithm refers to setting key configuration items that affect the behavior and performance of the algorithm before the algorithm starts running. It can be determined by random initialization, initialization based on prior knowledge, or adaptive initialization methods.

[0077] Genetic algorithms are search algorithms that simulate natural selection and heredity, iteratively improving the solution set through operations such as selection, crossover, and mutation. These algorithms can be implemented using standard genetic algorithms, elite-preserving genetic algorithms, or genetic algorithms with constraints. The objective function is the mathematical expression to be minimized or maximized in an optimization problem, used to measure the quality of the solution. It can be constructed as a weighted sum of sub-objective functions, a Chebyshev function, or a function based on an ideal point.

[0078] The Pareto optimal solution set refers to the set of all Pareto optimal solutions in a multi-objective optimization problem. A Pareto optimal solution is one that cannot improve any objective without deteriorating at least one objective. The process of iteratively optimizing using a genetic algorithm to obtain the Pareto optimal solution set is well known in the art and will not be described in detail here.

[0079] The evaluation index refers to the standard used to measure the quality or applicability of each solution in the Pareto optimal solution set, which can include dimensions such as the degree of closeness to the target, the robustness of the solution, the difficulty of implementation, and the adaptability to the equipment status.

[0080] The solution of this application first clearly defines the constraints of the multi-objective optimization algorithm when solving the initial process parameters using a multi-objective optimization algorithm. These constraints directly correspond to the physical limitations and process requirements of the extrusion equipment during actual operation, such as the upper and lower limits of extrusion temperature, screw speed, and pulling speed. It is precisely because of the introduction of these constraints that the search space of the optimization algorithm is limited to a practical range, thus avoiding the solution of parameter combinations that do not conform to production reality and ensuring the effectiveness and security of the solution. At the same time, by initializing the parameters of the multi-objective optimization algorithm, a foundation is set for the subsequent iterative optimization process. Reasonable parameter settings help improve the algorithm's convergence efficiency and solution quality. Furthermore, a genetic algorithm is used as the specific multi-objective optimization algorithm, and the objective function is to minimize the deviation between the weighted output of all parameter optimization sub-models and the corresponding quality indicators in the target sheath specifications. This enables the algorithm to effectively search in the multi-objective space and find a series of Pareto-locked optimal solutions that achieve a balance between different quality indicators. Each solution in this Pareto-optimal solution set represents a set of potential initial process parameters. However, simply obtaining a Pareto-optimal solution set is insufficient for direct production application, as different solutions may perform differently in actual production. Therefore, this application further selects a set of initial process parameters from the Pareto-optimal solution set based on a preset evaluation metric. This evaluation metric comprehensively considers the degree of deviation between each quality indicator and the target sheath specification, as well as the stability of the process parameters. This means that the selected parameters must not only ensure that product quality approaches the target but also ensure smooth equipment operation.

[0081] It is precisely because of this comprehensive evaluation and selection mechanism that the finalized initial process parameters can not only guide product quality to quickly approach target specifications, but also reduce production risks caused by parameter fluctuations or instability. Applying such a set of initial process parameters, obtained through constrained optimization and comprehensive evaluation screening, to the startup of extrusion equipment can provide more reliable and safer startup parameters than optimization methods that rely solely on historical benchmark models or fail to consider actual constraints and parameter stability. This can shorten the debugging time after mold change, reduce scrap generation, and improve mold change efficiency and production stability. This method is combined with methods based on historical benchmark models and parameter optimization sub-models. On the basis of leveraging the predictive power of historical data, it further optimizes the initial parameter determination process by introducing actual constraints and stability considerations, making the entire mold change control method more robust and practical.

[0082] Furthermore, the step of selecting a set of initial process parameters from the Pareto optimal solution set according to preset evaluation indicators as the startup parameters of the extrusion equipment may include:

[0083] B1. For each solution in the Pareto optimal solution set, calculate the degree of deviation between the corresponding quality indicators and the target sheath specifications. The degree of deviation includes absolute deviation and relative deviation. The absolute deviation and relative deviation are normalized to obtain the normalized degree of deviation.

[0084] B2. For each solution in the Pareto optimal solution set, evaluate the stability of the corresponding process parameters. The stability of the process parameters is determined by calculating the fluctuation range of each process parameter in historical production data. The smaller the fluctuation range, the higher the stability.

[0085] B3 according to the degree of aging of the extrusion equipment, the stability of the aging correction, the aging-corrected parameter stability;

[0086] B4. Determine the weighting factors for the normalized deviation and the stability of the aging-corrected parameters based on the target sheath specifications and the aging of the extrusion equipment;

[0087] B5. Using a weighted summation method, based on the determined weight factors, comprehensively score the normalized deviation degree and the stability of the aging-corrected parameters to obtain a comprehensive score for each solution;

[0088] B6. Select the solution with the highest comprehensive score as the starting parameters for the extrusion equipment.

[0089] Among them, normalization processing refers to converting data of different dimensions or ranges to a unified scale, which can be achieved by using methods such as minimum-maximum normalization or Z-score normalization. Its purpose is to eliminate the influence of different quality indicator deviations and parameter stability dimensions so that they can be effectively compared and weighted.

[0090] The stability of process parameters is determined by calculating the fluctuation range of each process parameter in historical production data. This fluctuation range can be measured using statistics such as standard deviation, range (the difference between the maximum and minimum values), or interquartile range. The inverse of the fluctuation range can be normalized to obtain the corresponding process parameter stability assessment result.

[0091] Aging correction refers to adjustments to parameter stability assessments based on the aging of the extrusion equipment. This can be achieved by looking up a table mapping the equipment aging degree to the correction coefficient, or by calculating the correction coefficient using an equipment aging model. The goal is to compensate for the impact of equipment aging on parameter stability, making parameter selection more consistent with the current equipment status. The value range for parameter stability after aging correction is [0, 1], with larger values ​​indicating greater stability.

[0092] Among them, the weight factor refers to the numerical value used to measure the relative importance of the normalized deviation degree and the parameter stability after aging correction in the comprehensive score. It can be determined based on expert experience, historical data analysis, or fuzzy rule reasoning. Its purpose is to balance the quality requirements and parameter stability requirements in a targeted manner according to the target sheath specifications and equipment aging degree.

[0093] The solution of this application performs a multi-dimensional evaluation of each candidate solution in the Pareto optimal solution set to select the initial process parameters that best suit the current operating conditions. First, the deviation of each solution's corresponding quality indicator from the target specification is calculated and normalized, providing a quantitative assessment of product quality compliance. Simultaneously, the stability of each solution's corresponding process parameter in historical production is evaluated, reflecting the reliability of the parameter in actual application. Key to this is the implementation of an aging correction for parameter stability based on the aging of the extrusion equipment. This is because equipment aging can affect the actual fluctuations and effects of the parameters. This correction ensures that the stability assessment more accurately reflects the current state of the equipment. Next, weighting factors for quality deviation and aging-corrected stability are dynamically determined based on the target sheath specifications and equipment aging. This allows parameter selection to take into account the varying priorities for quality and stability across different products, as well as the impact of equipment status. Finally, a weighted summation is used to comprehensively score the normalized deviation and aging-corrected parameter stability. Solutions with higher scores are considered to be more effective in meeting quality requirements, ensuring parameter stability, and adapting to equipment aging. This comprehensive consideration leads to the selection of the solution with the highest overall score as the starting parameter, thereby improving the accuracy of the initial parameters and reducing the need for subsequent adjustments. It is precisely because on the basis of the Pareto optimal solution set, the correction of parameter stability due to equipment aging and the dynamic determination of weight factors are further introduced, so that the initial parameters selected from the solution set can better adapt to the actual working conditions of the current equipment, thus solving the problem that only considering quality deviation and original stability is not enough to cope with the challenges brought by equipment aging, and improving the mold change efficiency and product quality stability.

[0094] Through the above technical solution, when selecting initial process parameters from the Pareto optimal solution set, not only the degree of deviation between the quality index and the target specification and the stability of the process parameters are considered, but the parameter stability is further corrected according to the aging of the extrusion equipment, and the weight of the evaluation index is dynamically determined based on the target sheath specification and the aging of the equipment. This parameter selection method that comprehensively considers the actual status of the equipment enables the selected initial process parameters to better adapt to the current production conditions, improves the accuracy and applicability of the initial parameters, reduces the need and time for manual parameter adjustment after mold changes, thereby improving the mold change efficiency of cable sheath production and enhancing the stability of product quality.

[0095] In some embodiments, step A2 includes: disturbing each process parameter to obtain the disturbed process parameters, and collecting real-time sheath product quality data corresponding to the disturbed process parameters; the process parameters include extrusion temperature, screw speed, and pulling speed, and the real-time sheath product quality data includes three quality indicators: outer diameter, wall thickness, and roundness;

[0096] Step A3 includes:

[0097] A301. Calculate the local sensitivity coefficient of each process parameter to each quality indicator based on the process parameters before and after the disturbance and the corresponding real-time sheath product quality data. The local sensitivity coefficient represents the degree of impact of the process parameter change on the quality indicator under the current operating conditions.

[0098] A302. Calculate the predicted values ​​of each quality indicator under the current process parameters based on the historical benchmark model;

[0099] A303. For each quality indicator, calculate the deviation between the current real-time sheath product quality data indicator value and the corresponding predicted value, recorded as the predicted deviation;

[0100] A304. Based on the local sensitivity coefficient, reversely deduce the amount of adjustment required for each process parameter, recorded as the parameter adjustment amount, to reduce the prediction deviation;

[0101] A305. Comprehensively consider the parameter adjustment amounts corresponding to the prediction deviations of various quality indicators and use the weighted average method to calculate the final parameter compensation adjustment amount.

[0102] Among them, disturbance refers to a small, planned change of the selected process parameters during the normal operation of the extrusion equipment without significantly affecting the product quality. It can be achieved by using pseudo-random sequences, step signals or pulse signals.

[0103] Among them, the local sensitivity coefficient refers to the change in each quality indicator caused by a unit change in a process parameter under the current production conditions. It can be calculated by linear regression, nonlinear fitting or differential calculation based on disturbance data. Its purpose is to quantify the influence of different process parameters on each quality indicator near the current working point.

[0104] Among them, reverse derivation refers to calculating the process parameter change required to eliminate or reduce the deviation based on the predicted deviation of the quality indicator and the local sensitivity relationship between the process parameter and the quality indicator. It can be achieved by using inverse operations based on the sensitivity matrix, gradient descent method or optimization solution, etc. Its purpose is to determine how to adjust the process parameters in response to the quality deviation;

[0105] Among them, weighted average refers to assigning different weights to the parameter adjustment amounts calculated for different quality indicators according to the importance or degree of deviation of each quality indicator, and then performing linear or nonlinear combination to obtain a comprehensive parameter adjustment amount. It can be achieved by using methods such as preset weights, dynamic adjustment of weights based on deviation size, or weight distribution based on fuzzy rules. Its purpose is to balance the adjustment needs of different quality indicators and obtain an overall optimized or satisfactory parameter adjustment plan.

[0106] The solution of this application proactively captures the actual impact of process parameter changes on product quality under current operating conditions by systematically perturbing various process parameters during extrusion equipment operation and simultaneously collecting both pre- and post-perturbation process parameter values ​​and corresponding real-time product quality data. Based on the collected perturbation data, the local sensitivity coefficients of each process parameter to various quality indicators are calculated. These coefficients reflect the degree of impact of small changes in process parameters on product quality indicators under current specific production conditions. Simultaneously, theoretical values ​​of each quality indicator are predicted based on the current process parameters using a historical benchmark model. Real-time product quality data is compared with the predicted values ​​to calculate the predicted deviations for each quality indicator. Using the calculated local sensitivity coefficients and the predicted deviations for each quality indicator, the theoretical adjustments required for each process parameter to mitigate these deviations are deduced. Because multiple quality indicators may require adjustment, and different adjustment directions may conflict, a weighted average approach is employed to comprehensively consider the adjustment requirements for each quality indicator and calculate a final parameter adjustment to compensate for the current operating deviations. This adjustment is then combined with the initial process parameters to form new process parameter adjustment values, which are then applied to the extrusion equipment. This compensation calculation mechanism, based on real-time disturbance and local sensitivity analysis, accurately perceives the impact of current operating conditions on the relationship between process parameters and quality, and accordingly calculates parameter adjustments that meet actual needs, overcoming the limitations of relying solely on historical models or current parameters for adjustment. Applying this precise compensation calculation method to the iterative adjustment framework of the cable sheath die change control method enables the system to quickly converge to the target quality despite the influence of hidden factors such as equipment wear and material batch differences. This improves the accuracy and efficiency of parameter adjustment and reduces trial and error and scrap.

[0107] Through the above technical solution, this application can obtain real-time information on the relationship between process parameters and quality indicators under current working conditions by disturbing process parameters and collecting data, calculate local sensitivity coefficients, and accurately quantify this relationship. Combining the predicted value of the historical model and the deviation of real-time quality data, the parameter adjustment amount is reversely deduced using the local sensitivity coefficient, and the direction and magnitude of the adjustment can be accurately determined. Taking into account the adjustment needs of different quality indicators, the final compensation amount is obtained by using methods such as weighted averaging, making the adjustment plan effective. This adjustment method based on real-time working condition information and local sensitivity analysis can effectively deal with changes in working conditions caused by hidden factors that are difficult to directly perceive, such as equipment wear and material batch differences, and improves the calculation accuracy of the parameter compensation adjustment amount, so that the product quality can be adjusted to the target requirements faster and more accurately, reducing the number of trial and error and the generation of waste.

[0108] Furthermore, in step A2, each real-time process parameter is disturbed to obtain the disturbed process parameter, and real-time sheath product quality data corresponding to the disturbed process parameter is collected, including:

[0109] C1. Generate a pseudo-random perturbation sequence using extrusion temperature, screw speed, and pull-off speed as the process parameters to be perturbed. The perturbation amplitude of the pseudo-random perturbation sequence is determined based on the fluctuation range of each process parameter in historical production data, and the perturbation frequency is determined based on the dynamic response characteristics of the extrusion process.

[0110] C2. According to the generated pseudo-random perturbation sequence, the process parameters to be disturbed are disturbed in turn to obtain the disturbed process parameters and collect the corresponding real-time sheath product quality data in real time;

[0111] Step A301 includes:

[0112] For each process parameter to be disturbed, the local sensitivity coefficient of the process parameter to each quality index is fitted using the least squares method according to its numerical change before and after the disturbance and the change of each quality index caused by the disturbance.

[0113] Among them, a pseudo-random perturbation sequence refers to a sequence with statistical characteristics similar to a random signal but generated by a deterministic algorithm. It can be generated using methods such as a linear feedback shift register (LFSR) or an M sequence. Its purpose is to provide a wide-band, repeatable perturbation signal for system identification.

[0114] Among them, the disturbance amplitude refers to the maximum offset of the disturbance signal relative to the reference value of the process parameter, which is determined based on the fluctuation range of each process parameter in the historical production data. Its purpose is to ensure that the disturbance is within the range allowed by normal production and avoid adverse effects on the production process.

[0115] The disturbance frequency refers to the frequency components and their distribution contained in the disturbance signal, which is determined according to the dynamic response characteristics of the extrusion process. Its purpose is to make the frequency components of the disturbance signal fully cover the main dynamic response frequency range of the extrusion process, thereby effectively stimulating the dynamic behavior of the system and obtaining effective data for identification.

[0116] Among them, the dynamic response characteristics refer to the response behavior of the system to changes in the input signal, including at least one of the response speed, delay, time constant, etc., which can be obtained by performing step response, pulse response or frequency response tests on the extrusion process. Its purpose is to guide the design of the disturbance frequency and ensure that the disturbance can fully reflect the dynamic characteristics of the system.

[0117] Among them, the least squares method refers to a mathematical optimization technique that estimates model parameters by minimizing the sum of the squares of the errors between the observed data and the model predicted values. It can be used to fit linear or nonlinear models. Its purpose is to accurately estimate the local linear relationship between process parameters and quality indicators, that is, the local sensitivity coefficient, from the disturbance data containing measurement noise.

[0118] The solution of the present application provides a more accurate and effective method for calculating process parameter perturbations and local sensitivity coefficients by introducing a pseudo-random perturbation sequence and the least squares method. Specifically, in step C1, the extrusion temperature, screw speed, and pulling speed are used as the process parameters to be disturbed, and a pseudo-random perturbation sequence is generated for each parameter. The perturbation amplitude of the pseudo-random perturbation sequence is determined based on the fluctuation range of each process parameter in the historical production data, which means that the perturbation will not exceed the normal production range, avoiding excessive interference with the production process. The perturbation frequency is determined based on the dynamic response characteristics of the extrusion process, ensuring that the perturbation can effectively stimulate the system response, thereby obtaining useful data. In this way, it can be ensured that the perturbation can provide sufficient information for parameter identification without causing significant negative impact on the production process. In step C2, each process parameter to be disturbed is perturbed in turn according to the generated pseudo-random perturbation sequence, and the corresponding real-time sheath product quality data is collected in real time. This perturbation method can avoid the coupling effect between parameters and improve the interpretability of the data. In step A301, for each process parameter to be disturbed, the least squares method is used to fit the local sensitivity coefficient of the process parameter to each quality indicator based on the change in its value before and after the disturbance and the resulting change in each quality indicator. The least squares method is a commonly used data fitting method that can effectively extract the relationship between parameters from noisy data.

[0119] In this way, the impact of process parameters on quality indicators can be more accurately estimated, providing a more reliable basis for subsequent parameter adjustments. This more precise sensitivity coefficient calculation method enables more accurate input for the steps of reverse deducing parameter adjustments based on sensitivity coefficients and comprehensively calculating parameter compensation adjustments, thereby improving the accuracy and effectiveness of overall parameter compensation adjustments.

[0120] In some preferred embodiments, a pseudo-random perturbation sequence is generated for the extrusion temperature, screw speed, and pull-off speed. This pseudo-random perturbation sequence can be generated using a linear feedback shift register (LFSR) algorithm to create a binary sequence. Appropriate scaling and offset transformations are then used to obtain a perturbation sequence suitable for the process parameters. The perturbation amplitude can be determined based on a statistical analysis of historical production data. For example, if historical data indicates a normal fluctuation range of ±5°C for extrusion temperature, the perturbation amplitude for extrusion temperature can be set within a ±2°C range. Similarly, the perturbation amplitudes for screw speed and pull-off speed can be determined based on historical data. The perturbation frequency can be determined by first analyzing the dynamic response characteristics of the extrusion process through step response testing. For example, if the response time constants for outer diameter and wall thickness are observed to be 10 seconds and 15 seconds, respectively, an appropriate perturbation frequency, such as 0.1 Hz (10-second period), can be selected to fully stimulate these dynamic responses. During the actual perturbation process, the extrusion temperature is first perturbed for a period of time according to a generated pseudo-random perturbation sequence, while corresponding outer diameter, wall thickness, and roundness data are collected in real time. The extrusion temperature is then restored to its baseline value, the screw speed is perturbed, and data is collected. Finally, the screw speed is restored, the pull-off speed is perturbed, and data is collected. After collecting the instantaneous values ​​of each process parameter and the corresponding quality indicator during the perturbation period, a least-squares fit is performed for each perturbed process parameter and each quality indicator. For example, to calculate the local sensitivity coefficient of extrusion temperature to outer diameter, a simple linear model can be constructed: ΔOD = S_Temperature * ΔExtrusionTemperature + Error, where ΔOD is the change in outer diameter, S_Temperature is the local sensitivity coefficient of extrusion temperature to outer diameter, and ΔExtrusionTemperature is the change in extrusion temperature. Using multiple collected (ΔExtrusionTemperature, ΔOuterDiameter) data pairs, the coefficient S_Temperature is solved using the least-squares method. Similarly, the local sensitivity coefficients of other process parameters to other quality indicators are calculated.

[0121] Through the above technical solution, the design of the pseudo-random perturbation sequence takes into account production reality and system characteristics, can effectively stimulate the system's dynamic response, obtain information-rich data, and at the same time ensure that the disturbance is within a safe range and does not affect normal production; sequential perturbations avoid parameter coupling and improve data purity; the least squares method can accurately fit the local sensitivity coefficient from the noise data, improve the calculation accuracy and reliability of the local sensitivity coefficient, and provide a more accurate basis for subsequent parameter compensation adjustment, thereby improving the efficiency of parameter adjustment after mold change and product quality stability.

[0122] Preferably, step A304 may include:

[0123] D1. For each quality indicator, based on the local sensitivity coefficient and in combination with preset parameter adjustment constraints, an optimization model is constructed with the goal of minimizing the prediction deviation of that quality indicator. The parameter adjustment constraints include upper and lower limits on the adjustment range and adjustment rate of each process parameter, as well as stability constraints during the adjustment process. The stability constraints are implemented by limiting the second-order derivatives of the process parameter adjustments (i.e., the stability constraints include upper and lower limits on the second-order derivatives of the process parameter adjustments).

[0124] D2. For each quality indicator, use a sequential quadratic programming algorithm to solve the optimization model and obtain the optimal parameter adjustment amount that satisfies the parameter adjustment constraints, thereby forming an optimal parameter adjustment amount set;

[0125] D3. Based on the preset quality indicator priority and in combination with the fuzzy logic reasoning method, the optimal parameter adjustment amount set is screened and integrated to obtain the final parameter compensation adjustment amount.

[0126] In step D1, a mathematical optimization model is constructed for each key quality indicator in the cable sheath production process, such as outer diameter, wall thickness, and roundness, using the calculated local sensitivity coefficients and pre-set process parameter adjustment constraints. The objective function of this optimization model is to minimize the prediction deviation of the current quality indicator, that is, the difference between the actual measured value and the historical benchmark model prediction value.

[0127] Parameter adjustment constraints refer to the restrictions that must be met when adjusting process parameters. These may include the maximum and minimum values ​​allowed for each process parameter, as well as the maximum change allowed for each process parameter per unit time. Stability constraints refer to restrictions imposed during parameter adjustment to prevent drastic fluctuations in process conditions. These constraints can be pre-set based on specific equipment characteristics, material properties, and production experience.

[0128] Among them, the sequential quadratic programming algorithm is an iterative optimization algorithm used to solve nonlinear programming problems, and is particularly suitable for processing constrained optimization problems. The specific calculation process of the sequential quadratic programming algorithm is an existing technology and will not be described in detail here; the optimal parameter adjustment amount refers to the process parameter adjustment amount that can minimize the prediction deviation of a specific quality indicator while satisfying all parameter adjustment constraints; the optimal parameter adjustment amount set refers to a set of optimal parameter adjustment amounts obtained after solving the optimization model for each quality indicator separately.

[0129] Among them, quality indicator priority refers to the different levels of importance assigned to different quality indicators based on product requirements or production needs when there are multiple quality indicators. It can be determined by expert experience setting, historical data analysis or user customization; fuzzy logic reasoning method is a reasoning method based on fuzzy set theory and fuzzy rules, which can handle uncertainty and fuzzy information and make decisions; screening and fusion refers to selecting or synthesizing a final parameter adjustment amount from the optimal parameter adjustment amount set based on quality indicator priority and fuzzy logic reasoning method; the final parameter compensation adjustment amount refers to the process parameter adjustment amount obtained after screening and fusion, which is used to compensate for the current working condition deviation.

[0130] The solution of this application constructs an optimization model for each quality indicator based on the local sensitivity coefficient and pre-set parameter adjustment constraints, aiming to minimize the prediction deviation of that quality indicator. This transforms the parameter adjustment problem into a constrained optimization problem. The parameter adjustment constraints include upper and lower limits on the adjustment range and rate of each process parameter, as well as stability constraints during the adjustment process. The stability constraints are implemented by constraining the second-order derivatives of the process parameter adjustments. This ensures that the resulting parameter adjustments are within the feasible range of the actual process and the adjustment process is smooth, avoiding the impact of excessive or unstable adjustments on product quality. Based on this, a sequential quadratic programming algorithm is used to solve the optimization model for each quality indicator, obtaining the optimal parameter adjustment that satisfies the parameter adjustment constraints and forming an optimal parameter adjustment set. The sequential quadratic programming algorithm effectively finds the optimal solution to constrained nonlinear optimization problems, ensuring the reliability of the solution. Because different quality indicators may interact or even conflict with each other, directly applying a solution from the optimal parameter adjustment set may degrade other indicators. Therefore, the optimal parameter adjustment set is screened and integrated based on the pre-set quality indicator priorities and combined with fuzzy logic reasoning methods. The fuzzy logic reasoning method can handle the trade-off problem between multiple objectives. According to the deviation degree and priority of each quality indicator, the advantages and disadvantages of different adjustment schemes are comprehensively evaluated, and finally a parameter compensation adjustment amount that comprehensively considers all quality indicators is obtained.

[0131] This method utilizes the current operating condition information provided by the local sensitivity coefficient, combined with actual process constraints and multi-objective decision-making mechanism, to overcome the problems of parameter infeasibility, adjustment instability and multi-objective conflict that may result from simple reverse deduction based on the sensitivity coefficient. It improves the accuracy, stability and robustness of parameter adjustment, thereby more effectively reducing prediction deviation and enabling the sheath product quality to quickly meet the target requirements.

[0132] Furthermore, step D3 may include:

[0133] D301. Divide each quality indicator into core indicators and secondary indicators based on the preset quality indicator priorities;

[0134] D302. For each set of optimal parameter adjustment amounts in the optimal parameter adjustment amount set, calculate its impact on the core indicator, and select the optimal parameter adjustment amount that can make the core indicator reach the preset quality threshold range to form a sub-set of core parameter adjustment amounts;

[0135] D303. For each parameter adjustment set in the core parameter adjustment subset, fuzzy logic reasoning is used to calculate the membership degree based on the deviation degree of the secondary indicators and the amplitude of the process parameter adjustment. Fuzzy reasoning is then performed based on the membership degree to obtain a comprehensive evaluation value.

[0136] D304. Select the parameter adjustment amount with the highest comprehensive evaluation value as the final parameter compensation adjustment amount.

[0137] Among them, core indicators and secondary indicators refer to the division of all quality indicators into core indicators that must strictly meet the requirements and secondary indicators with relatively lower importance based on the priority of quality indicators. They can be divided by setting priority thresholds or directly specifying them.

[0138] In step D302, the optimal parameter adjustment for each set can be applied to the current process parameters. The adjusted quality indicators are then predicted using a historical benchmark model and compared with a preset quality threshold range to achieve screening. The preset quality threshold range refers to an acceptable product quality range set for the core indicator, which can be determined using process specifications, product standards, or user requirements.

[0139] Step D303 can be implemented by constructing a fuzzy inference system. This system takes the current deviation of the secondary indicator (e.g., the predicted deviation of roundness) and the magnitude of the process parameter change caused by the parameter adjustment (e.g., the adjustment of extrusion temperature, screw speed, and pull-off speed) as input. Through fuzzification, fuzzy rule inference, and defuzzification, it outputs a quantitative comprehensive evaluation value. For example, fuzzy sets such as "small secondary indicator deviation," "large secondary indicator deviation," "small adjustment range," and "large adjustment range" can be defined, and fuzzy rules such as "if the secondary indicator deviation is small and the adjustment range is small, the comprehensive evaluation value is high" can be established.

[0140] The solution of the present application divides each quality indicator into core indicators and secondary indicators according to the preset quality indicator priority, thereby distinguishing the importance of different quality indicators and providing a basis for the subsequent parameter adjustment amount screening. Then, for each set of optimal parameter adjustment amounts in the optimal parameter adjustment amount set, the degree of its influence on the core indicator is calculated, and the optimal parameter adjustment amount that can make the core indicator reach the preset quality threshold range is screened out to form a core parameter adjustment sub-set. Through this step, it can be ensured that the adjusted process parameters can meet the requirements of the core quality indicator and avoid the situation where the core indicator exceeds the tolerance. Next, for each set of parameter adjustment amounts in the core parameter adjustment sub-set, a fuzzy logic reasoning method is used to calculate the membership degree based on the deviation degree of the secondary indicator and the amplitude of the process parameter adjustment, and fuzzy reasoning is performed based on the membership degree to obtain a comprehensive evaluation value. The fuzzy logic reasoning method can comprehensively consider the influence of multiple factors, avoid the excessive influence of a single factor on the parameter adjustment amount selection, and improve the rationality of the parameter adjustment. At the same time, considering the deviation degree of the secondary indicator and the amplitude of the process parameter adjustment, it can take into account the secondary indicator as much as possible while ensuring that the core indicator meets the requirements, and avoid excessive adjustment of the process parameter, thereby ensuring the stability of the production process. Finally, the parameter adjustment amount with the highest comprehensive evaluation value is selected as the final parameter compensation adjustment amount. By selecting the parameter adjustment amount with the highest comprehensive evaluation value, it is possible to take into account the secondary indicators as much as possible while meeting the core indicator requirements, and ensure the rationality and stability of the process parameter adjustment, thereby obtaining the optimal parameter compensation adjustment amount.

[0141] Based on the optimal parameter adjustment amount set, this scheme further introduces quality indicator priority division and fuzzy logic reasoning to conduct targeted screening and fusion of the set, so that the final selected adjustment amount can not only reduce the prediction deviation, but also meet the differentiated requirements of different quality indicators in actual production. In particular, it gives priority to core indicators while taking into account secondary indicators and adjustment stability, making the entire parameter adjustment process closer to actual production needs and improving the effectiveness and robustness of the adjustment.

[0142] refer to Figure 2The present application provides a cable sheath die change control system for adjusting and controlling the process parameters of the extrusion equipment after the cable sheath extrusion equipment changes its die. The system includes:

[0143] Initial parameter recommendation module 1 is used to determine the initial process parameters based on the target sheath specifications using the historical benchmark model to start the extrusion equipment (the specific process refers to step A1 above);

[0144] Real-time data acquisition module 2, which collects real-time process parameters and corresponding real-time sheath product quality data during the operation of the extrusion equipment (refer to step A2 above for the specific process);

[0145] Working condition compensation calculation module 3, used to calculate the parameter compensation adjustment between the current working condition and the historical reference working condition based on the real-time process parameters and the corresponding real-time sheath product quality data (for the specific process, please refer to step A3 above);

[0146] Parameter comprehensive adjustment module 4 is used to combine the initial process parameters with the parameter compensation adjustment amount to obtain the process parameter adjustment value for the current working condition, and send it to the control system of the extrusion equipment so that the extrusion equipment operates according to the process parameter adjustment value (for the specific process, refer to step A4 above);

[0147] Iterative control module 5 is used to trigger the real-time data acquisition module, working condition compensation calculation module and parameter comprehensive adjustment module to run repeatedly until the sheath product quality meets the target requirements (for the specific process, refer to step A5 above).

[0148] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A cable sheath die change control method for adjusting and controlling the process parameters of an extrusion device after the die change of the cable sheath extrusion device, characterized in that: The steps of the method include: A1. Based on the target jacket specifications, use the historical benchmark model to determine the initial process parameters to start the extrusion equipment; A2. During the operation of the extrusion equipment, collect real-time process parameters and corresponding real-time sheath product quality data; A3. Calculate the parameter compensation adjustment between the current operating conditions and the historical benchmark operating conditions based on the real-time process parameters and the corresponding real-time sheath product quality data; A4. Combining the initial process parameters with the parameter compensation adjustment amount to obtain the process parameter adjustment value for the current working conditions, and sending it to the extrusion equipment control system so that the extrusion equipment operates according to the process parameter adjustment value; A5. Repeat steps A2-A4 until the sheath product quality meets the target requirements; The historical benchmark model includes multiple parameter optimization sub-models, each of which corresponds to a quality indicator; the parameter optimization sub-model takes process parameters as input and outputs corresponding quality indicators; the quality indicators include outer diameter, wall thickness and roundness; the process parameters include extrusion temperature, screw speed and pulling speed; Step A1 includes: A101. Extract multiple quality indicators of the target sheath specifications, including outer diameter, wall thickness, and roundness; A102. For each quality indicator, call the corresponding parameter optimization sub-model; A103. Based on the preset weight allocation strategy, assign a weight to each parameter optimization sub-model; the weight reflects the importance of the corresponding quality indicator in the overall quality assessment; A104. A multi-objective optimization algorithm is used to minimize the deviation between the weighted output of all parameter optimization sub-models and the corresponding quality indicators in the target sheath specifications. A set of initial process parameters is obtained and used as the starting parameters of the extrusion equipment.

2. A cable sheath mold change control method according to claim 1, characterized in that: Step A103 includes: For the target sheath specification, query the preset mapping relationship table of product specifications and weight allocation strategies to determine the weight allocation strategy that matches the current target sheath specification; If a matching weight allocation strategy is found, weights are directly assigned to each parameter optimization sub-model according to the strategy found; if no matching weight allocation strategy is found, weights are assigned to each parameter optimization sub-model according to the preset default weight allocation strategy, or according to the operator's custom settings; In response to the aging degree of the extrusion equipment, a weight adjustment coefficient that matches the current aging degree of the extrusion equipment is determined based on a preset mapping relationship table between the aging degree of the equipment and the weight adjustment coefficient, and the assigned weight is adjusted based on the weight adjustment coefficient; wherein the weight adjustment coefficient is used to adjust the relative importance between different quality indicators to adapt to the impact of equipment aging.

3. A cable sheath mold change control method according to claim 1, characterized in that: Step A104 includes: Determine the constraints of the multi-objective optimization algorithm; the constraints include upper and lower limits of extrusion temperature, upper and lower limits of screw speed, and upper and lower limits of pulling speed; Initialize the parameters of the multi-objective optimization algorithm; the initialized parameters include population size, crossover probability, and mutation probability; Genetic algorithm is used as a multi-objective optimization algorithm, and the objective function is to minimize the deviation between the weighted output of all parameter optimization sub-models and the corresponding quality indicators in the target sheath specifications; Under the constraints, based on the objective function, a Pareto optimal solution set is obtained by iteratively searching for the optimal solution through a genetic algorithm; each solution in the Pareto optimal solution set corresponds to a set of initial process parameters; From the Pareto optimal solution set, a set of initial process parameters are selected as the startup parameters of the extrusion equipment according to preset evaluation indicators; the evaluation indicators comprehensively consider the degree of deviation between each quality indicator and the target sheath specifications and the stability of the process parameters.

4. A cable sheath mold change control method according to claim 3, characterized in that: The step of selecting a set of initial process parameters from the Pareto optimal solution set according to preset evaluation indicators as the starting parameters of the extrusion equipment includes: B1. For each solution in the Pareto optimal solution set, calculate the degree of deviation between the corresponding quality indicators and the target sheath specifications. The degree of deviation includes absolute deviation and relative deviation. The absolute deviation and relative deviation are normalized to obtain the normalized degree of deviation. B2. For each solution in the Pareto optimal solution set, evaluate the stability of the corresponding process parameters. The stability of the process parameters is determined by calculating the fluctuation range of each process parameter in historical production data. The smaller the fluctuation range, the higher the stability. B3 according to the degree of aging of the extrusion equipment, the stability of the aging correction, the aging-corrected parameter stability; B4. Determine the weighting factors for the normalized deviation and the stability of the aging-corrected parameters based on the target sheath specifications and the aging of the extrusion equipment; B5. Using a weighted summation method, based on the determined weight factors, comprehensively score the normalized deviation degree and the stability of the aging-corrected parameters to obtain a comprehensive score for each solution; B6. Select the solution with the highest comprehensive score as the starting parameters for the extrusion equipment.

5. A cable sheath mold change control method according to claim 1, characterized in that: Step A2 includes: disturbing each process parameter to obtain the disturbed process parameters, and collecting real-time sheath product quality data corresponding to the disturbed process parameters; the process parameters include extrusion temperature, screw speed, and pulling speed; and the real-time sheath product quality data includes three quality indicators: outer diameter, wall thickness, and roundness; Step A3 includes: A301. Calculate the local sensitivity coefficient of each process parameter to each quality indicator based on the process parameters before and after the disturbance and the corresponding real-time sheath product quality data. The local sensitivity coefficient represents the degree of impact of the process parameter change on the quality indicator under the current operating conditions. A302. Calculate the predicted values ​​of each quality indicator under the current process parameters based on the historical benchmark model; A303. For each quality indicator, calculate the deviation between the current real-time sheath product quality data indicator value and the corresponding predicted value, recorded as the predicted deviation; A304. Based on the local sensitivity coefficient, reversely deduce the amount of adjustment required for each process parameter, recorded as the parameter adjustment amount, to reduce the prediction deviation; A305. Comprehensively consider the parameter adjustment amounts corresponding to the prediction deviations of various quality indicators and use the weighted average method to calculate the final parameter compensation adjustment amount.

6. A cable sheath mold change control method according to claim 5, characterized in that: In step A2, each real-time process parameter is disturbed to obtain the disturbed process parameters, and real-time sheath product quality data corresponding to the disturbed process parameters is collected, including: C1. Generate a pseudo-random perturbation sequence using extrusion temperature, screw speed, and pull-off speed as the process parameters to be perturbed. The perturbation amplitude of the pseudo-random perturbation sequence is determined based on the fluctuation range of each process parameter in historical production data, and the perturbation frequency is determined based on the dynamic response characteristics of the extrusion process. C2. According to the generated pseudo-random perturbation sequence, the process parameters to be disturbed are disturbed in turn to obtain the disturbed process parameters and collect the corresponding real-time sheath product quality data in real time; Step A301 includes: For each process parameter to be disturbed, the local sensitivity coefficient of the process parameter to each quality index is fitted using the least squares method according to its numerical change before and after the disturbance and the change of each quality index caused by the disturbance.

7. A cable sheath mold change control method according to claim 5, characterized in that: Step A304 includes: D1. For each quality indicator, based on the local sensitivity coefficient and in combination with preset parameter adjustment constraints, an optimization model is constructed with the goal of minimizing the prediction deviation of the quality indicator. The parameter adjustment constraints include upper and lower limits on the adjustment range and adjustment rate of each process parameter, as well as stability constraints during the adjustment process. The stability constraints are implemented by limiting the second-order derivatives of the process parameter adjustments. D2. For each quality indicator, use a sequential quadratic programming algorithm to solve the optimization model and obtain the optimal parameter adjustment amount that satisfies the parameter adjustment constraints, thereby forming an optimal parameter adjustment amount set; D3. Based on the preset quality indicator priority and in combination with the fuzzy logic reasoning method, the optimal parameter adjustment amount set is screened and integrated to obtain the final parameter compensation adjustment amount.

8. A cable sheath mold change control method according to claim 7, characterized in that: Step D3 includes: D301. Divide each quality indicator into core indicators and secondary indicators based on the preset quality indicator priorities; D302. For each set of optimal parameter adjustment amounts in the optimal parameter adjustment amount set, calculate its impact on the core indicator, and select the optimal parameter adjustment amount that can make the core indicator reach the preset quality threshold range to form a sub-set of core parameter adjustment amounts; D303. For each parameter adjustment set in the core parameter adjustment subset, fuzzy logic reasoning is used to calculate the membership degree based on the deviation degree of the secondary indicators and the amplitude of the process parameter adjustment. Fuzzy reasoning is then performed based on the membership degree to obtain a comprehensive evaluation value. D304. Select the parameter adjustment amount with the highest comprehensive evaluation value as the final parameter compensation adjustment amount.

9. A cable sheath die change control system, used to adjust and control the process parameters of the extrusion equipment after the cable sheath extrusion equipment changes the die, characterized in that: The system includes: An initial parameter recommendation module is used to determine the initial process parameters based on the target sheath specifications using a historical benchmark model to start the extrusion equipment; Real-time data acquisition module, which collects real-time process parameters and corresponding real-time sheath product quality data during the operation of the extrusion equipment; The working condition compensation calculation module is used to calculate the parameter compensation adjustment between the current working condition and the historical benchmark working condition based on the real-time process parameters and the corresponding real-time sheath product quality data; A parameter comprehensive adjustment module is used to combine the initial process parameters with the parameter compensation adjustment amount to obtain the process parameter adjustment value for the current working condition, and send it to the control system of the extrusion equipment so that the extrusion equipment operates according to the process parameter adjustment value; Iterative control module, used to trigger the real-time data acquisition module, working condition compensation calculation module and parameter comprehensive adjustment module to run repeatedly until the sheath product quality meets the target requirements; The historical benchmark model includes multiple parameter optimization sub-models, each of which corresponds to a quality indicator; the parameter optimization sub-model takes process parameters as input and outputs corresponding quality indicators; the quality indicators include outer diameter, wall thickness and roundness; the process parameters include extrusion temperature, screw speed and pulling speed; The initial parameter recommendation module uses the historical benchmark model to determine the initial process parameters based on the target sheath specifications to start the extrusion equipment. When performing the following operations: A101. Extract multiple quality indicators of the target sheath specifications, including outer diameter, wall thickness, and roundness; A102. For each quality indicator, call the corresponding parameter optimization sub-model; A103. Based on the preset weight allocation strategy, assign a weight to each parameter optimization sub-model; the weight reflects the importance of the corresponding quality indicator in the overall quality assessment; A104. A multi-objective optimization algorithm is used to minimize the deviation between the weighted output of all parameter optimization sub-models and the corresponding quality indicators in the target sheath specifications. A set of initial process parameters is obtained and used as the starting parameters of the extrusion equipment.

Images