Cable extrusion temperature control optimization method based on adaptive control algorithm

Abstract

The invention discloses a cable extrusion temperature control optimization method based on an adaptive control algorithm, and the method comprises the following steps: S1, collecting and preprocessing multi-source process data, and generating a multivariable temperature control input data set; s2, configuring a self-tuning PID (Proportion Integration Differentiation) controller, and setting an initial PID parameter; s3, performing coevolution optimization on PID parameters of each heating section to obtain an optimal multi-section PID parameter combination; s4, distributing an optimal PID parameter, and adaptively adjusting the parameter in combination with the input data set; s5, implementing closed-loop temperature regulation, monitoring deviation, coordinating section management, and collecting temperature control, energy consumption and process data; and S6, periodically feeding back temperature control and energy consumption data, optimizing parameters, dynamically adjusting the parameters, and resetting the parameters when the parameters are abnormal. According to the invention, intelligent self-adaptive optimization control of multi-section temperature in the cable extrusion process is realized, and the temperature control precision, the energy efficiency and the product quality stability are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial automation control, and particularly relates to a cable extrusion temperature control optimization method based on an adaptive control algorithm. BACKGROUND

[0002] In the modern cable manufacturing industry, temperature control of the cable extrusion process is crucial for ensuring product quality, improving production efficiency and reducing energy consumption. With the diversification of cable product specifications and the continuous improvement of process requirements, the precision and response speed of temperature regulation in the extrusion process have become an important manifestation of enterprise competitiveness. Currently, cable extrusion temperature control systems mainly use conventional PID controllers or fixed-parameter temperature control systems, which achieve temperature regulation of each heating section through manual experience setting or simple closed-loop feedback adjustment. Although traditional PID controllers have the advantages of simple structure and easy implementation, their control parameters are fixed and cannot adapt to complex working conditions such as fluctuations in material properties, changes in environmental temperature and humidity, process speed adjustments, and equipment aging during the extrusion process. This fixed-parameter control strategy is prone to cause temperature control response lag, increased temperature fluctuations, and unstable system regulation when facing process disturbances and multi-section coupling effects, which in turn affects the appearance consistency and electrical performance of cable products.

[0003] For multi-section extrusion equipment, existing technologies mostly use distributed independent PID control, and there is a lack of effective collaborative optimization mechanism between section controllers, which cannot fully consider the thermal coupling between sections and overall energy consumption optimization. In addition, traditional temperature control systems mainly rely on single data feedback from temperature sensors and lack comprehensive integration of multi-variable process information such as environmental humidity, extrusion speed, and energy consumption, resulting in a control strategy that cannot accurately reflect the dynamic changes of complex process. For parameter disturbances and system abnormalities, existing technologies mostly rely on manual intervention or shutdown correction, with low intelligent level of adjustment and insufficient self-adaptive ability and fault tolerance of the system.

[0004] Existing cable extrusion temperature control methods have obvious shortcomings in multi-section collaborative optimization, adaptive regulation, process multi-variable integration, and automatic fault diagnosis, and cannot meet the requirements of high-end cable products for process stability, energy saving and consumption reduction, and quality consistency.

[0005] Therefore, how to provide a cable extrusion temperature control optimization method based on an adaptive control algorithm is a problem that needs to be solved by those skilled in the art. SUMMARY

[0006] One purpose of the present application is to propose a cable extrusion temperature control optimization method based on adaptive control algorithm, which fully utilizes the technical means such as self-tuning PID control, adaptive weight adjustment, collaborative evolution optimization and process prior knowledge fusion, and describes in detail the whole process of multi-source process data acquisition, multi-section collaborative optimization and intelligent adaptive temperature control parameter dynamic adjustment. Through the deep fusion and dynamic feedback of multi-variable temperature control input data, the present application can realize high-precision closed-loop control, automatic collaborative adjustment and abnormal rapid response of the temperature of each heating section, and has the advantages of high adjustment precision, fast response speed, low energy consumption and strong product quality consistency.

[0007] According to the cable extrusion temperature control optimization method based on adaptive control algorithm, the method comprises the following steps:

[0008] S1, collecting multi-source process data in the cable extrusion process, preprocessing the multi-source process data to form a multi-variable temperature control input data set;

[0009] S2, configuring a self-tuning PID controller for each heating section according to the multi-variable temperature control input data set, and setting the initial value of the PID parameter of each self-tuning PID controller;

[0010] S3, using a collaborative evolution algorithm, each heating section is respectively corresponding to a plurality of collaborative populations, the individual of each population is coded as the PID control parameter combination of the corresponding section, and the collaborative evolution operation is performed on each population to obtain the optimal multi-section PID parameter combination;

[0011] S4, according to the optimal multi-section PID parameter combination, distributing to each self-tuning PID controller, and each self-tuning PID controller combining the multi-variable temperature control input data set to perform PID parameter online adaptive adjustment;

[0012] S5, using the adjusted PID parameters and the self-tuning PID controller of each section to implement closed-loop temperature adjustment for each heating section, real-time monitoring the deviation of the temperature of each section from the target value, and collaboratively managing the coupling effect between sections, while collecting the temperature control results, energy consumption and process indicators;

[0013] S6, periodically feeding the collected temperature control results, energy consumption and process indicators to the collaborative evolution algorithm for parameter optimization and dynamic adjustment, and if it is detected that any section has temperature control abnormality, a global parameter reset mechanism is automatically triggered to reinitialize the related population and re-execute the optimization and adaptive adjustment.

[0014] Optionally, the multi-source process data specifically includes the real-time temperature, extrusion speed, environmental temperature and humidity and process parameters related to the extrusion process of each heating section.

[0015] Optionally, the preprocessing of the multi-source process data specifically includes denoising, normalization, standardization and the like of the collected multi-source process data to generate a multi-variable temperature control input data set in a unified format.

[0016] Optionally, S2 specifically includes:

[0017] S21, according to the multi-variable temperature control input data set, configuring a self-tuning PID controller for each heating section, analyzing the process state and historical running data of each heating section, combining with the process priori knowledge, setting the initial value of the PID parameters of the self-tuning PID controller;

[0018] S22, combining with the process priori knowledge base and the historical running data, generating a recommended PID parameter interval corresponding to each heating section, and determining the initial value of the proportional coefficient K p (0), the integral coefficient K i (0) and the differential coefficient K d (0);

[0019] S23, using the recursive least squares method and introducing a forgetting factor to perform online identification on the dynamic characteristic parameters of the heating section;

[0020] S24, in the parameter identification process, for abnormal disturbance and data noise, using an abnormal data suppression method and an adaptive gain adjustment method to improve the robustness and accuracy of parameter identification;

[0021] S25, using the identified dynamic characteristic parameters of the heating section to correct the proportional coefficient K p (t), the integral coefficient K i (t) and the differential coefficient K d (t);

[0022] S26, introducing dynamic weight coefficients w p (t), w i (t), w d (t) for the proportional coefficient, the integral coefficient and the differential coefficient, respectively, and dynamically adjusting the weight of each parameter according to the temperature deviation, the adjustment speed and the process characteristic;

[0023] S27, calculating the dynamically weighted PID control parameters, and the output signal of the self-tuning PID controller is u(t);

[0024] S28, combining with the process priori knowledge base to perform interval constraint on the real-time updated PID parameters, and when the parameters exceed the recommended interval or the adjustment effect is poor, automatically adjusting the parameters according to the priori knowledge;

[0025] S29, in the running process, continuously using the collected multi-variable temperature control input data set and the historical running data to dynamically improve the process priori knowledge base;

[0026] S210, periodically evaluate the self-tuning PID controller adjustment performance of each heating section configuration, and adaptively optimize the parameter identification method, dynamic weight adjustment strategy and process prior knowledge calling method according to the actual operation state.

[0027] Optionally, the S3 specifically comprises:

[0028] S31, using a co-evolution algorithm, each heating section is respectively corresponding to a plurality of cooperative populations, the individual of each population is coded as the PID control parameter combination of the corresponding section, the PID control parameter combination includes the proportional coefficient K p , the integral coefficient K i , the differential coefficient K d and the dynamic weight coefficient w p , w i , w d ;

[0029] S32, according to the process prior knowledge and historical operation data, the experience guidance is used to initialize the cooperative population respectively corresponding to each heating section, the PID control parameter combination of each population individual is set to be distributed in the historical optimal interval, and the parameter disturbance is combined with the process characteristics;

[0030] S33, a fitness function F is constructed, which comprehensively considers the temperature control error, response time, energy consumption and cooperative coupling index of temperature change between sections of each heating section;

[0031] S34, a multi-level information interaction mechanism is established, and all cooperative populations respectively corresponding to the heating sections are divided into local cooperative groups according to the physical position and process correlation, and high-frequency parameter information exchange is carried out in each local cooperative group;

[0032] S35, in each local cooperative group, the individuals of the corresponding cooperative population respectively generate a new generation of PID control parameter combination through crossover and mutation operation, and are screened according to the fitness function;

[0033] S36, in the global range, the parameter information between different local cooperative groups is periodically synchronized, and the parameter migration or the best individual sharing is carried out;

[0034] S37, in the process of individual mutation, the mutation range of the PID control parameter combination is limited in the recommended interval of the process prior knowledge, so as to prevent the invalid or abnormal change of the parameter;

[0035] S38, according to the real-time adjustment result of the dynamic cooperative weight and the coupling penalty coefficient in the fitness function, the contribution of the cooperative population respectively corresponding to each heating section in the overall fitness is continuously optimized, and the influence of different heating sections on the temperature control performance is dynamically balanced;

[0036] S39, repeating the steps S34 to S38, iteratively optimizing until the evolution termination condition is met, obtaining a globally optimal multi-section PID control parameter combination, including the proportional coefficient, the integral coefficient, the differential coefficient and the dynamic weight coefficient of each heating section;

[0037] S310, periodically using the collected temperature control results, energy consumption and process indicators to adaptively optimize the multi-level information interaction mechanism, dynamic coordination weight, coupling penalty coefficient and experience guidance mechanism during operation.

[0038] Optionally, the S4 specifically includes:

[0039] S41, according to the optimal multi-section PID parameter combination, distributing the proportional coefficient K p , the integral coefficient K i , the differential coefficient K d and the dynamic weight coefficient w p , w i , w d of each heating section to the respective tuning PID controller;

[0040] S42, the respective tuning PID controller combines the multivariate temperature control input data set to real-time extract the target temperature r(t), the current actual temperature y(t), the environmental humidity h env (t), the extrusion speed v ex (t) and other process variables, and calculate the comprehensive temperature error e * (t);

[0041] S43, the respective tuning PID controller outputs the control signal u(t) according to the distributed PID parameter combination and the comprehensive temperature error e * (t);

[0042] S44, the respective tuning PID controller adaptively adjusts the proportional coefficient, the integral coefficient, the differential coefficient and the dynamic weight coefficient according to the comprehensive temperature error e * (t) and the process variable change, and continuously corrects the PID parameter to adapt to the actual working condition;

[0043] S45, the respective tuning PID controller combines the priori knowledge of the process to interval constrain the adjusted PID parameter;

[0044] S46, periodically evaluating the adjustment performance of the self-tuning PID controller, and optimizing the parameter adjustment method according to the temperature control accuracy, energy consumption and response characteristics.

[0045] Optionally, the S5 specifically includes:

[0046] S51, using the adjusted PID parameters and the self-tuning PID controller of each section, respectively implementing closed-loop temperature regulation on each heating section, and adjusting the heating power in real time to make the temperature of each heating section approach the target value;

[0047] S52, collecting the actual temperature and the set target temperature of each heating section in real time, and monitoring the deviation of the temperature of each heating section from the target value;

[0048] S53, recording the temperature regulation data and the running state of each heating section, and dynamically analyzing the stability and response speed of the regulation process of each heating section;

[0049] S54, for the thermal coupling effect between the heating sections, implementing cooperative regulation between the sections, and suppressing the interference and coupling effect in the temperature control process through parameter coordination and information interaction;

[0050] S55, continuously collecting the temperature control results, energy consumption data and key process indicators of each heating section, and forming a data record.

[0051] Optionally, the S6 specifically comprises:

[0052] S61, periodically collecting the temperature control results, energy consumption data and process indicators of each heating section, and forming a complete feedback data set;

[0053] S62, feeding the feedback data set to the co-evolution algorithm, and comprehensively evaluating the temperature control effect, energy consumption level and process indicators of the current multi-section PID parameter combination;

[0054] S63, based on the comprehensive evaluation result of the co-evolution algorithm, dynamically optimizing the parameter combination of the self-tuning PID controller of each heating section, and updating the coefficient K p , the integral coefficient K i , the differential coefficient K d and the dynamic weight coefficient w p , w i , w d ;

[0055] S64, continuously monitoring the temperature control running state of each heating section, and automatically detecting whether there is an abnormality or deviation from the set standard in the temperature control result, energy consumption and process indicators;

[0056] S65, if it is detected that any section has a temperature control abnormality, energy consumption abnormality or process indicator abnormality, the corresponding cooperative population is reinitialized, and the optimization and adaptive adjustment operation of the co-evolution algorithm is re-executed.

[0057] The beneficial effects of the present application are:

[0058] The present application overcomes many deficiencies of the prior art in multi-section coupling, intelligent parameter adjustment and system adaptive ability by introducing an adaptive control algorithm, a co-evolution mechanism and dynamic fusion of multi-source process data in the cable extrusion temperature control system. By configuring a self-tuning PID controller for each heating section and using a co-evolution algorithm to achieve global optimization and collaborative adjustment of parameters between sections, the present application not only improves the adaptability of the temperature control system to changes in raw materials, environmental disturbances and process switching, but also dynamically optimizes the temperature control strategy of each section, thereby reducing temperature overshoot and fluctuations and ensuring the uniformity and stability of the temperature of each section. Compared with traditional independent temperature control or fixed parameter methods, the present application feeds back the temperature control results, energy consumption and process indicators to the algorithm module in real time, continuously performs parameter adaptive optimization and dynamic reorganization, and realizes closed-loop intelligent optimization of the extrusion process. When the system detects temperature control abnormalities in any section, it can automatically trigger the parameter reset mechanism and quickly recover to the optimal control state, greatly improving the fault tolerance of the temperature control system and the continuous operation capability of the production line. The present application effectively improves the automation, intelligence and lean level of cable extrusion temperature control, significantly improves product quality consistency and production energy efficiency, and provides a solid technical guarantee for the upgrading of high-end cable manufacturing processes. BRIEF DESCRIPTION OF DRAWINGS

[0059] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate embodiments of the present application and explain the present application together with the content of the specification, but do not constitute a limitation of the present application. In the drawings:

[0060] Figure 1 A flowchart of a cable extrusion temperature control optimization method based on an adaptive control algorithm according to the present application;

[0061] Figure 2 A structure block diagram of the fusion of multi-section self-tuning PID control and co-evolution algorithm of a cable extrusion temperature control optimization method based on an adaptive control algorithm according to the present application. DETAILED DESCRIPTION

[0062] The present application will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams that only schematically illustrate the basic structure of the present application, and therefore only show the components related to the present application.

[0063] REFERENCE Figure 1 and Figure 2 A cable extrusion temperature control optimization method based on an adaptive control algorithm, comprising the following steps:

[0064] S1, collecting multi-source process data in the cable extrusion process, preprocessing the multi-source process data to form a multi-variable temperature control input data set;

[0065] S2, configuring a self-tuning PID controller for each heating section according to the multivariate temperature control input dataset, setting the initial value of the PID parameters of the respective self-tuning PID controller;

[0066] S3, using a co-evolution algorithm, corresponding to multiple co-evolution populations for each heating section, encoding the individuals of each population as the PID control parameter combination of the corresponding section, performing co-evolution operation on each population to obtain the optimal multi-section PID parameter combination;

[0067] S4, according to the optimal multi-section PID parameter combination, distributing to the respective self-tuning PID controller, and the respective self-tuning PID controller combining the multivariate temperature control input dataset to perform PID parameter online adaptive adjustment;

[0068] S5, using the adjusted PID parameters and the self-tuning PID controller of each section to implement closed-loop temperature regulation for each heating section, real-time monitoring the deviation of each section temperature from the target value, and cooperatively managing the coupling effect between sections, while collecting temperature control results, energy consumption and process indicators;

[0069] S6, periodically feeding the collected temperature control results, energy consumption and process indicators back to the co-evolution algorithm for parameter optimization and dynamic adjustment, and if any section is detected to have temperature control abnormalities, automatically triggering a global parameter reset mechanism to reinitialize the related population and re-execute optimization and adaptive adjustment.

[0070] In the embodiment, the multi-source process data specifically includes real-time temperature, extrusion speed, environmental temperature and humidity, and process parameters related to the extrusion process of each heating section.

[0071] In the embodiment, the preprocessing of the multi-source process data specifically includes denoising, normalization and standardization of the collected multi-source process data to generate a multivariate temperature control input dataset in a unified format.

[0072] In the embodiment, S2 specifically includes:

[0073] S21, configuring a self-tuning PID controller for each heating section according to the multivariate temperature control input dataset, analyzing the process state and historical running data of each heating section, and setting the initial value of the PID parameters of the respective self-tuning PID controller in combination with the process priori knowledge;

[0074] S22, generating the recommended PID parameter interval corresponding to each heating section in combination with the process priori knowledge base and historical running data, and determining the initial value of the proportionality coefficient K p (0), the integral coefficient K i (0) and the differential coefficient K d (0);

[0075] S23, the dynamic characteristic parameters of the heating section are identified online by using recursive least square method and introducing forgetting factor;

[0076] S24, in the parameter identification process, the abnormal data suppression method and the adaptive gain adjustment method are used to improve the robustness and accuracy of parameter identification for abnormal disturbance and data noise;

[0077] S25, the identified dynamic characteristic parameters of the heating section are used to correct the proportional coefficient K p (t), integral coefficient K i (t) and differential coefficient K d (t) in real time;

[0078] S26, dynamic weight coefficients w p (t), w i (t) and w d (t) are introduced for the proportional coefficient, integral coefficient and differential coefficient respectively, and the weight of each parameter is dynamically adjusted according to the temperature deviation, adjustment speed and process characteristics;

[0079] S27, the PID control parameters after dynamic weighting are calculated, and the output signal of the self-tuning PID controller is u(t):

[0080]

[0081] Wherein, e(t) is the error between the set temperature and the actual temperature;

[0082] S28, the interval constraint is combined with the process prior knowledge base to update the PID parameters in real time, and when the parameters exceed the recommended interval or the adjustment effect is not good, the parameters are automatically adjusted by referring to the prior knowledge;

[0083] S29, in the running process, the collected multivariate temperature control input data set and historical running data are continuously used to dynamically improve the process prior knowledge base;

[0084] S210, periodically evaluate the adjustment performance of the self-tuning PID controller configured for each heating section, and adaptively optimize the parameter identification method, dynamic weight adjustment strategy and process prior knowledge calling mode according to the actual running state.

[0085] In the embodiment, the S3 specifically includes:

[0086] S31, the collaborative evolution algorithm is used, and each heating section is respectively corresponding to a plurality of collaborative populations, the individual of each population is coded as the PID control parameter combination of the corresponding section, and the PID control parameter combination includes proportional coefficient K p , integral coefficient K i , differential coefficient K d and dynamic weight coefficient wp , w i , w d ;

[0087] S32, according to the process priori knowledge and historical operation data, the experience guidance is used to initialize the corresponding collaborative population of each heating section, the PID control parameter combination of each population individual is set to be distributed in the historical preferred interval, and the parameter disturbance is combined with the process characteristics;

[0088] S33, the fitness function F is constructed, the temperature control error, the response time, the energy consumption and the collaborative coupling index of the temperature change between the sections of each heating section are integrated:

[0089]

[0090] Wherein, N is the total number of heating sections, β i (t) is the dynamic collaborative weight of the corresponding collaborative population of the i-th heating section, f i is the sub fitness of the i-th heating section, γ(t) is the coupling penalty coefficient which is self-adaptive to the running state, |y i+1 (t)-y i (t) | is the difference value of the actual temperature of adjacent heating sections;

[0091] S34, a multi-level information interaction mechanism is established, the corresponding collaborative population of all heating sections is divided into local collaborative groups according to the physical position and process correlation, and high-frequency parameter information exchange is carried out in each local collaborative group;

[0092] S35, in each local collaborative group, the corresponding collaborative population individual respectively generates a new generation of PID control parameter combination through crossover and mutation operation, and carries out screening according to the fitness function;

[0093] S36, in the global range, the parameter information between different local collaborative groups is synchronized regularly, and the parameter migration or the best individual sharing is carried out;

[0094] S37, in the individual mutation process, the mutation range of the PID control parameter combination is limited in the process priori knowledge recommended interval, so as to prevent the invalid or abnormal change of the parameter;

[0095] S38, according to the real-time adjustment result of the dynamic collaborative weight and the coupling penalty coefficient in the fitness function, the contribution of the corresponding collaborative population of each heating section in the overall fitness is continuously optimized, and the influence of different heating sections on the temperature control performance is dynamically balanced;

[0096] S39, repeat steps S34 to S38, iterative optimization until the evolution termination condition is met, and obtain the globally optimal multi-section PID control parameter combination, including the proportional coefficient, integral coefficient, differential coefficient and dynamic weight coefficient of each heating section;

[0097] S310, during operation, periodically use the collected temperature control results, energy consumption and process indicators to adaptively optimize the multi-level information interaction mechanism, dynamic coordination weight, coupling penalty coefficient and experience guidance mechanism.

[0098] In this embodiment, S4 specifically includes:

[0099] S41, according to the optimal multi-section PID parameter combination, the proportional coefficient K p , integral coefficient K i , differential coefficient K d and dynamic weight coefficient w p , w i , w d of each heating section are distributed to the respective tuning PID controllers;

[0100] S42, the respective tuning PID controllers combine the multivariate temperature control input data set to real-time extract the target temperature r(t), the current actual temperature y(t), the environmental humidity h env (t), the extrusion speed v ex (t) and other process variables, and calculate the comprehensive temperature error e * (t):

[0101]

[0102] Wherein, α1, α2, α3 are weighting coefficients, is the environmental humidity reference value, is the extrusion speed reference value, and t is the current time;

[0103] S43, the respective tuning PID controllers output the control signal u(t) according to the distributed PID parameter combination and the comprehensive temperature error e * (t);

[0104] S44, the respective tuning PID controllers adjust the proportional coefficient, integral coefficient, differential coefficient and dynamic weight coefficient online according to the comprehensive temperature error e * (t) and the process variable change, and continuously correct the PID parameters to adapt to the actual working condition;

[0105] S45, the respective tuning PID controllers combine the process priori knowledge to interval constrain the adjusted PID parameters;

[0106] S46, periodically evaluate the adjustment performance of the self-tuning PID controller, and optimize the parameter adjustment method according to the temperature control accuracy, energy consumption and response characteristics.

[0107] In this embodiment, S5 specifically includes:

[0108] S51, using the adjusted PID parameters and the self-tuning PID controller of each section, respectively implementing closed-loop temperature regulation for each heating section, and adjusting the heating power in real time to make the temperature of each heating section approach the target value;

[0109] S52, collecting the actual temperature and the set target temperature of each heating section in real time, and monitoring the deviation of the temperature of each heating section from the target value;

[0110] S53, recording the temperature regulation data and the running state of each heating section, and dynamically analyzing the stability and response speed of the regulation process of each heating section;

[0111] S54, for the thermal coupling effect between the heating sections, implementing collaborative regulation between the sections, and suppressing the interference and coupling effect in the temperature control process through parameter coordination and information interaction;

[0112] S55, continuously collecting the temperature control results, energy consumption data and key process indicators of each heating section to form a data record.

[0113] In this embodiment, S6 specifically includes:

[0114] S61, periodically collecting the temperature control results, energy consumption data and process indicators of each heating section to form a complete feedback data set;

[0115] S62, feeding the feedback data set to the co-evolution algorithm, and comprehensively evaluating the temperature control effect, energy consumption level and process indicators of the current multi-section PID parameter combination;

[0116] S63, based on the comprehensive evaluation result of the co-evolution algorithm, dynamically optimizing the parameter combination of the self-tuning PID controller of each heating section, and updating the coefficient K p , the integral coefficient K i , the differential coefficient K d and the dynamic weight coefficient w p , w i , w d ;

[0117] S64, continuously monitoring the temperature control running state of each heating section, and automatically detecting whether there is an abnormality or deviation from the set standard in the temperature control result, energy consumption and process indicators;

[0118] S65. If any section is detected to have abnormal temperature control, abnormal energy consumption or abnormal process indicators, the corresponding collaborative population is reinitialized and the optimization and adaptive adjustment operations of the collaborative evolution algorithm are re-executed.

[0119] Example 1:

[0120] In order to verify the feasibility of the present invention in practice, the present invention is applied to a smart manufacturing plant for a certain cable. For a long time, the temperature control of the heating section of the extruder on the production line has been facing problems such as slow response, fixed parameters that are difficult to adapt to complex working conditions, high energy consumption, and fluctuations in product qualification rates. The factory originally adopted the traditional partitioned independent PID temperature control system, which was unable to achieve comprehensive adjustment of multi-variable process parameters. Whenever encountering high temperatures in summer or low temperatures in winter, replacement of raw material batches, or adjustment of extrusion speed, it often leads to multi-section temperature loss or overshoot. The temperature difference in some heating sections was as high as ±4.2°C at one time, and problems such as bubbles and rough surface appeared on the outer sheath of the product. In more serious cases, the production line needs to be frequently shut down for manual intervention to adjust parameters. The monthly energy consumption is 7.5% higher than that of similar factories in the industry, and the scrap rate is as high as 2.4%.

[0121] In March 2025, the factory upgraded one of its 110kV high-voltage cable extrusion production lines using a cable extrusion temperature control optimization method based on an adaptive control algorithm proposed in this invention. During the upgrade process, each heating section was equipped with a PID controller with self-tuning capabilities, and all controllers were connected to multi-source sensors such as temperature, humidity, and speed, as well as process data acquisition ports. After pre-processing, the data from the entire line is sent to the co-evolutionary algorithm module, and the PID parameters are automatically optimized according to the actual working conditions and historical experience of each section. The co-evolutionary algorithm not only takes into account the temperature control of each section, but also fully incorporates the influence of energy consumption, process coupling, and historical fluctuations, and dynamically adjusts the PID parameters and weights of multiple sections. The system can detect temperature control anomalies in real time and autonomously trigger parameter resets to ensure stable production operations at all times.

[0122] The upgraded production line ran 20 batches of high-voltage cross-linked polyethylene insulated cables in trial production between March and May 2025, covering a variety of scenarios with varying raw material batches, ambient temperature and humidity, and extrusion speeds. Data monitoring showed that temperature overshoots in each heating zone were kept within an average of ±1.4°C, significantly shortening the time it takes to stabilize the temperature control, and significantly improving the product qualification rate. Energy consumption was reduced by 8.2% compared to the same period before the upgrade, saving an average of 5.8 kWh per kilometer. Even during peak production loads in early May and an ambient temperature of 35°C, the temperature control system automatically adapted to various disturbances without the need for human intervention, resetting the adaptive parameters and returning to normal within 90 seconds.

[0123] Table 1 Comparison of data before and after application of cable extrusion temperature control optimization based on adaptive control algorithm

[0124]

[0125] From the data in Table 1, after applying the cable extrusion temperature control optimization method based on the adaptive control algorithm proposed in the present application, the temperature control effect and overall process performance of the cable production line have been significantly improved. The temperature overshoot amplitude is greatly reduced from ±4.2℃ before upgrading to ±1.4℃, a reduction of 66.7%, indicating that the temperature control is more accurate, effectively avoiding quality defects caused by excessive temperature fluctuations during the extrusion process. The temperature control stability time is shortened from 17 minutes to 6.8 minutes, improving the production response efficiency and enabling faster adaptation to working conditions and product switching, greatly improving production rhythm and flexibility.

[0126] In terms of energy consumption, the unit energy consumption per kilometer is reduced from 73.5kWh / km to 67.7kWh / km, with a energy saving rate of 7.9%, not only helping enterprises reduce production costs, but also contributing to green manufacturing and energy efficiency improvement goals. The first-time pass rate of cable products is improved from 96.7% to 99.2%, an increase of 2.5%, which is echoed by the decrease in production scrap rate from 2.4% to 0.6%, indicating that the production stability is enhanced after temperature control optimization, the number of defective products is significantly reduced, and the product consistency and market competitiveness are further improved.

[0127] In terms of system intelligence and abnormal response, the average time for temperature control abnormality automatic recovery is greatly shortened from 310 seconds to 90 seconds, indicating that the system can quickly adapt and recover when encountering process fluctuations or unexpected events without human intervention, greatly reducing downtime risks and personnel workload. The number of production line shutdowns caused by changes in environmental temperature and humidity is reduced from 3.2 times per month to 0, further demonstrating the adaptive ability and robustness of the present application under complex disturbances. Overall, these data comprehensively reflect the multi-dimensional improvement of the present application in production efficiency, energy consumption, product quality and intelligent operation and maintenance level, and effectively support its wide application value in modern cable manufacturing.

[0128] The above describes only the preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can make equivalent substitutions or changes within the technical scope disclosed in the present application according to the technical solutions and inventive concepts of the present application, which should be covered within the protection scope of the present application.

Claims

1. A cable extrusion temperature control optimization method based on an adaptive control algorithm, characterized in that: The steps include: S1. Collect multi-source process data during cable extrusion, pre-process the multi-source process data, and form a multi-variable temperature control input data set; S2. Based on the multivariable temperature control input data set, configure a self-tuning PID controller for each heating section and set the initial values ​​of the PID parameters of each self-tuning PID controller; S3. Using a co-evolutionary algorithm, each heating section is mapped to multiple co-populations. The individuals in each population are encoded as the PID control parameter combination of the corresponding section. Co-evolutionary operations are performed on each population to obtain the optimal multi-section PID parameter combination. S4. Allocate the optimal multi-segment PID parameter combination to each tuned PID controller. Each tuned PID controller performs online adaptive adjustment of the PID parameters in combination with the multivariable temperature control input data set. S5. Use the adjusted PID parameters and the self-tuning PID controller of each section to implement closed-loop temperature regulation for each heating section, monitor the deviation between the temperature of each section and the target value in real time, and coordinately manage the coupling effect between sections. At the same time, collect temperature control results, energy consumption and process indicators; S6. The collected temperature control results, energy consumption, and process indicators are periodically fed back to the co-evolutionary algorithm for parameter optimization and dynamic adjustment. If temperature control anomalies are detected in any section, the global parameter reset mechanism is automatically triggered, the relevant population is reinitialized, and optimization and adaptive adjustment are re-executed.

2. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The multi-source process data specifically includes the real-time temperature of each heating section, extrusion speed, ambient temperature and humidity, and process parameters related to the extrusion process.

3. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The preprocessing of the multi-source process data specifically includes performing denoising, normalization and standardization on the collected multi-source process data to generate a multivariate temperature control input data set in a unified format.

4. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The S2 specifically includes: S21. Based on the multivariable temperature control input data set, configure a self-tuning PID controller for each heating section, analyze the process status and historical operation data of each heating section, and set the initial values ​​of the PID parameters of each self-tuning PID controller in combination with prior process knowledge; S22. Combine the process prior knowledge base and historical operation data to generate the recommended PID parameter range corresponding to each heating section and determine the proportional coefficient K p (0), integral coefficient K i (0) and differential coefficient K d (0) initial value; S23, using the recursive least square method and introducing the forgetting factor to perform online identification of the dynamic characteristic parameters of the heating section; S24. During the parameter identification process, abnormal data suppression methods and adaptive gain adjustment methods are used to improve the robustness and accuracy of parameter identification in response to abnormal disturbances and data noise; S25, using the identified dynamic characteristic parameters of the heating section to correct the proportional coefficient K in real time p (t), integral coefficient K i (t), differential coefficient K d (t); S26, introduce dynamic weight coefficients w for proportional coefficient, integral coefficient and differential coefficient respectively p (t), w i (t), w d (t), dynamically adjust the weight of each parameter according to temperature deviation, adjustment speed and process characteristics; S27, calculating the dynamically weighted PID control parameters, and the self-tuning PID controller output signal is u(t); S28. Combine the process prior knowledge base to perform interval constraints on the real-time updated PID parameters. When the parameters exceed the recommended range or the adjustment effect is not good, the parameters are automatically adjusted by referring to the prior knowledge; S29. During operation, continuously utilize the collected multivariable temperature control input data set and historical operation data to dynamically improve the process prior knowledge base; S210, periodically evaluate the adjustment performance of the self-tuning PID controller configured in each heating section, and adaptively optimize the parameter identification method, dynamic weight adjustment strategy and process prior knowledge calling method according to the actual operating status.

5. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The S3 specifically includes: S31, using the collaborative evolution algorithm, each heating section is respectively mapped to multiple collaborative populations, and the individual encoding of each population is a PID control parameter combination of the corresponding section. The PID control parameter combination includes the proportional coefficient K p , integral coefficient K i , differential coefficient K d and dynamic weight coefficient w p 、w i 、w d ; S32. Based on prior process knowledge and historical operating data, the collaborative population corresponding to each heating section is initialized using experience as a guide, the PID control parameter combination of each population individual is set to be distributed within the historical optimal range, and the parameter perturbations are performed in combination with the process characteristics; S33, constructing a fitness function F, which integrates the temperature control error, response time, energy consumption of each heating section and the synergistic coupling index of temperature change between sections; S34. Establish a multi-level information interaction mechanism to divide the collaborative populations corresponding to all heating sections into local collaborative groups according to physical locations and process relevance, and exchange high-frequency parameter information within each local collaborative group; S35. In each local cooperative group, the corresponding cooperative population individuals generate a new generation of PID control parameter combinations through crossover and mutation operations, and screen them according to the fitness function; S36. Globally, different local collaborative groups regularly synchronize parameter information to perform parameter migration or optimal individual sharing; S37. During the individual variation process, the variation range of the PID control parameter combination is limited to the range recommended by the process prior knowledge to prevent invalid or abnormal parameter changes; S38. Based on the real-time adjustment results of the dynamic synergy weight and coupling penalty coefficient in the fitness function, the contribution of the synergistic population corresponding to each heating section to the overall fitness is continuously optimized, and the impact of different heating sections on the temperature control performance is dynamically balanced; S39, repeating steps S34 to S38, iterative optimization, until the evolution termination condition is met, and obtaining the global optimal multi-segment PID control parameter combination, including the proportional coefficient, integral coefficient, differential coefficient and dynamic weight coefficient of each heating section; S310. During operation, the collected temperature control results, energy consumption and process indicators are periodically used to adaptively optimize the multi-level information interaction mechanism, dynamic collaborative weight, coupling penalty coefficient and experience-guided mechanism.

6. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The S4 specifically includes: S41, according to the optimal multi-segment PID parameter combination, the proportional coefficient K of each heating segment is p , integral coefficient K i , differential coefficient K d and dynamic weight coefficient w p 、w i 、w d Assigned to each tuned PID controller; S42, each PID controller is tuned to combine with the multivariable temperature control input data set to extract the target temperature r(t), the current actual temperature y(t), the ambient humidity h in real time. env (t), extrusion speed v ex (t) and other process variables, calculate the comprehensive temperature error e * (t); S43, each PID controller is tuned according to the assigned PID parameter combination and the comprehensive temperature error e * (t), output control signal u(t); S44, each PID controller is adjusted according to the comprehensive temperature error e * (t) and process variable changes, online adaptive adjustment of proportional coefficient, integral coefficient, differential coefficient and dynamic weight coefficient, continuous correction of PID parameters to adapt to actual working conditions; S45, respectively tuning the PID controllers and combining the process prior knowledge to impose interval constraints on the adjusted PID parameters; S46. Periodically evaluate the regulation performance of the self-tuning PID controller and optimize the parameter adjustment method based on temperature control accuracy, energy consumption and response characteristics.

7. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The S5 specifically includes: S51, using the adjusted PID parameters and the self-tuning PID controller of each section, respectively implement closed-loop temperature regulation for each heating section, and adjust the heating power in real time to make the temperature of each heating section approach the target value; S52, collecting the actual temperature and setting the target temperature of each heating section in real time, and monitoring the deviation between the temperature of each heating section and the target value; S53, recording the temperature adjustment data and operating status of each heating section, and dynamically analyzing the stability and response speed of the adjustment process of each heating section; S54. Aiming at the thermal coupling effect between heating sections, implement coordinated regulation between sections, and suppress interference and coupling effects during temperature control through parameter coordination and information interaction; S55. Continuously collect the temperature control results, energy consumption data and key process indicators of each heating section to form data records.

8. The cable extrusion temperature control optimization method based on the adaptive control algorithm according to claim 1 is characterized in that: The S6 specifically includes: S61. Periodically collect temperature control results, energy consumption data, and process indicators of each heating zone to form a complete feedback data set; S62, feeding the feedback data set into the collaborative evolution algorithm to comprehensively evaluate the temperature control effect, energy consumption level and process indicators of the current multi-segment PID parameter combination; S63, based on the comprehensive evaluation results of the collaborative evolutionary algorithm, dynamically optimize the parameter combination of the self-tuning PID controller of each heating section and update the coefficient K p , integral coefficient K i , differential coefficient K d and dynamic weight coefficient w p 、w i 、w d ; S64, continuously monitor the temperature control operation status of each heating section, and automatically detect whether there are any abnormalities or deviations from the set standards in the temperature control results, energy consumption and process indicators; S65. If any section is detected to have abnormal temperature control, abnormal energy consumption or abnormal process indicators, the corresponding collaborative population is reinitialized and the optimization and adaptive adjustment operations of the collaborative evolution algorithm are re-executed.

Images