Automatic control system and method for hollow plate extrusion production line

Abstract

The invention relates to the technical field of data processing, and provides an automatic control system and method for a hollow plate extrusion production line, and the method comprises the steps: collecting a real-time temperature data sequence, a speed change data sequence and a pressure response data sequence in a hollow plate extrusion process, and carrying out the multi-dimensional feature extraction and response collaborative analysis; obtaining a traction speed correction instruction sequence and a screw rotation speed adjustment instruction sequence; and performing linkage control on the hollow plate extrusion production line according to the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence. Through multi-dimensional feature extraction and response collaborative analysis, accurate monitoring and adjustment of multiple key parameters such as temperature, speed and pressure are achieved, the production efficiency and the stability of product quality are improved, a hollow plate extrusion production line can operate efficiently and stably in a complex and changeable production environment, and the production efficiency is improved. The problems that an existing control method is low in reaction speed and insufficient in adjusting precision in the face of complex production working conditions are solved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular to an automatic control system and method for a hollow board extrusion production line. Background Art

[0002] Currently, most control methods for traditional hollow board extrusion production lines rely on fixed-point control systems and operations based on manual experience. Temperature sensors, pressure sensors, and speed sensors are set to monitor key data during the production process in real time, and simple feedback regulation is performed through the PID control algorithm. The role of these control systems is to adjust the corresponding execution devices according to the sensed parameters, such as adjusting the temperature control device of the heating system, controlling the speed of the traction system, and adjusting the screw speed of the extruder.

[0003] In related technical means, most control methods for hollow board extrusion production lines rely on fixed-point control systems and operations based on manual experience. Temperature sensors, pressure sensors, and speed sensors are set to monitor key data during the production process in real time, and feedback regulation is performed through the PID control algorithm. The corresponding execution devices are adjusted according to the sensed parameters, such as adjusting the temperature control device of the heating system, controlling the speed of the traction system, and adjusting the screw speed of the extruder, to ensure the continuity and stability of production.

[0004] Regarding the above technical solutions, although the existing technologies can achieve basic regulation of parameters such as temperature, speed, and pressure through traditional methods based on fixed-point control to ensure the stability of the production process, in the face of complex production conditions, especially fluctuations between different production batches, the reaction speed and regulation accuracy of the existing control methods are insufficient. Summary of the Invention

[0005] In order to improve the problems of slow reaction speed and insufficient regulation accuracy existing in the existing control methods in the face of complex production conditions, this application provides an automatic control system and method for a hollow board extrusion production line.

[0006] The present invention provides an automatic control method for a hollow board extrusion production line, comprising: collecting real-time temperature data sequences, speed change data sequences and pressure response data sequences during the hollow board extrusion process, and performing multi-dimensional feature extraction to obtain a temperature time-varying feature parameter group, a speed stability feature parameter group and a pressure fluctuation feature parameter group; performing response collaborative analysis on the temperature time-varying feature parameter group and the speed stability feature parameter group to obtain a target temperature control section sequence, and performing a time window sliding fusion operation on the pressure fluctuation feature parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence; inputting the pressure regulation control vector group and the melt reflux rate adjustment sequence into a preset high-order regulation response map to obtain a traction speed correction factor group and an extrusion speed fine-tuning vector; performing time series clustering analysis on the traction speed correction factor group to obtain an abnormal regulation identification sequence, and mapping the abnormal regulation identification sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw rotation speed adjustment instruction sequence; and performing linkage control on the hollow board extrusion production line according to the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence.

[0007] As a preferred solution, the step of collecting real-time temperature data sequences, speed change data sequences, and pressure response data sequences during the extrusion of the hollow collecting plate, and performing multi-dimensional feature extraction to obtain a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group includes: obtaining real-time temperature data sequences, speed change data sequences, and pressure response data sequences respectively through a multi-point temperature sensing unit, a traction motor speed recording unit, and a pressure sensor set in the temperature control area; performing section segmentation processing and amplitude normalization analysis on the temperature data sequences to obtain a temperature section dynamic amplitude parameter group and a temperature gradient change parameter group, performing interval weighted difference operation and steady-state stability section identification processing on the speed change data sequences to obtain a traction speed fluctuation section distribution group and a speed steady-state average vector group, and performing joint analysis on the pressure response data sequences based on the mean deviation and kurtosis coefficient of the time-domain response to obtain a pressure dynamic discrete factor group and a pressure trend response mapping vector; constructing a temperature-speed response coupling feature group by performing cross-dimensional mapping on the temperature gradient change parameter group and the traction speed fluctuation section distribution group, performing point-to-region fusion processing on the pressure dynamic discrete factor group and the temperature section dynamic amplitude parameter group to obtain a pressure-temperature cross feature factor set, and constructing a connected graph mapping structure between the speed steady-state average vector group and the pressure trend response mapping vector to obtain a voltage stabilization relationship map; merging the temperature-speed response coupling feature group, the pressure-temperature cross feature factor set, and the voltage stabilization relationship map into a data map to generate a multi-dimensional feature integration map, and performing dimension regularization and redundant factor pruning processing on the multi-dimensional feature integration map to extract a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group.

[0008] As a preferred solution, the steps of performing section segmentation processing and amplitude normalization analysis on the temperature data sequence to obtain a temperature section dynamic amplitude parameter group and a temperature gradient change parameter group, performing interval weighted difference operation and steady-state stability section identification processing on the speed change data sequence to obtain a traction speed fluctuation section distribution group and a speed steady-state average vector group, and performing joint analysis on the pressure response data sequence based on the mean deviation and kurtosis coefficient of the time-domain response to obtain a pressure dynamic discrete factor group and a pressure trend response mapping vector include: continuously segmenting the temperature data sequence through a preset sliding time window to obtain a plurality of temperature time sections, performing maximum value normalization and interval difference amplitude calculation on the temperature data within each temperature time section to obtain a temperature dynamic amplitude index group; performing adjacent section difference calculation on the temperature dynamic amplitude index group and archiving it as a temperature change rate index, constructing a temperature gradient trend curve based on the temperature change rate index, and extracting the rising section and falling section of the temperature gradient trend curve to generate a temperature gradient change parameter group; sliding the window of the speed change data sequence at a fixed time granularity, performing weighted difference calculation on the speed values within each window to obtain a speed local fluctuation factor group, comparing the speed local fluctuation factor group with the historical standard steady-state speed reference vector, and identifying the relatively stable section and the fluctuation section to generate a speed steady-state average vector group and a traction speed fluctuation section distribution group; applying the average deviation calculation and the asymmetric kurtosis measurement method to jointly process the pressure response data sequence, extracting the abnormal amplitude points and the buffer response steady interval, establishing a distribution density map of the pressure dynamic response sequence according to the abnormal amplitude points, calculating the discrete rate and deviation factor for different density sections of the distribution density map to generate a pressure dynamic discrete factor group; performing linear regression modeling on the pressure change trend in the buffer response steady interval, comparing the linear regression result with the pressure change trend data in the historical process state database, and extracting the correlation between the directionality and amplitude of the pressure change based on the comparison result to generate a pressure trend response mapping vector.

[0009] As a preferred solution, the step of performing response collaborative analysis on the temperature time-varying characteristic parameter group and the speed stability characteristic parameter group to obtain a target temperature control section sequence, and performing time-window sliding fusion operation on the pressure fluctuation characteristic parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence includes: extracting temperature interval mutation points and section stability factors from the temperature time-varying characteristic parameter group to generate a temperature node group and a temperature steady-state distribution group, performing response collaborative analysis on the temperature node group and the speed stability characteristic parameter group to obtain a temperature-speed coupling section map; extracting a traction speed sensitivity distribution map based on the temperature-speed coupling section map, performing node reconstruction processing on the traction speed sensitivity distribution map and the temperature steady-state distribution group to obtain a target temperature control section sequence, performing time-window sliding fusion operation on the target temperature control section sequence and the pressure fluctuation characteristic parameter group to obtain a pressure zone dynamic response sequence and a feedback buffer section map; performing asymmetric difference smoothing processing on the pressure zone dynamic response sequence, performing sliding window fitting and regional weight back-projection on the smoothed pressure zone dynamic response sequence and the feedback buffer section map to obtain a pressure zone disturbance response fitting surface and a section abnormal offset set, performing main disturbance source identification and hierarchical aggregation analysis on the intersection area of the pressure zone disturbance response fitting surface and the section abnormal offset set, and extracting a local disturbance compensation factor group and a pressure extreme value distribution area group; performing feature transformation and quantization on the local disturbance compensation factor group to obtain a pressure regulation control vector group, and converting the pressure extreme value distribution area group into a melt reflux rate adjustment sequence according to the non-linear mapping relationship between the pressure extreme value and the reflux rate.

[0010] As a preferred solution, the step of inputting the pressure regulation control vector group and the melt reflux rate adjustment sequence into a preset high-order regulation response map to obtain a traction speed correction factor group and an extrusion speed fine-tuning vector includes: constructing a high-order regulation response map based on historical data before regulation and output quality response, wherein the high-order regulation response map includes a regulation mapping baseline group and a quality comparison node group; mapping the pressure regulation control vector group to the regulation mapping baseline group to generate a baseline response displacement group and a regulation energy distribution vector, performing cross-projection on the melt reflux rate adjustment sequence and the quality comparison node group to obtain a reflux quality adaptation factor group and a quality deviation judgment sequence; calculating a fusion deviation between the baseline response displacement group and the reflux quality adaptation factor group to generate a deviation correction projection matrix and a reflux influence section identification set, extracting a rate sensitivity weight matrix and an extrusion efficiency disturbance factor according to the regulation energy distribution vector and the quality deviation judgment sequence; performing pointwise fusion analysis on the deviation correction projection matrix and the rate sensitivity weight matrix to obtain a traction speed correction factor group, and performing combined mapping on the reflux influence section identification set and the extrusion efficiency disturbance factor to generate an extrusion speed fine-tuning vector.

[0011] As a preferred solution, the step of performing time series clustering analysis on the traction rate correction factor group to obtain an abnormal adjustment recognition sequence, and mapping the abnormal adjustment recognition sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw rotation speed adjustment instruction sequence includes: flattening the traction rate correction factor group along the time axis and resampling the nodes to obtain a reconstructed time series vector group and a node time mapping group; performing multi-scale clustering processing on the reconstructed time series vector group by applying a sliding clustering window to obtain an abnormal fluctuation node set; repositioning the abnormal fluctuation node set and the node time mapping group to generate an abnormal adjustment recognition sequence; performing dimension alignment and main cause mapping on the abnormal adjustment recognition sequence and the extrusion speed fine-tuning vector to obtain a main adjustment mapping group and a secondary perturbation response group; constructing an initial traction speed correction instruction sequence framework using the main adjustment mapping group, and fusing the secondary perturbation response group into the initial traction speed correction instruction sequence framework after linear compensation processing to generate a traction speed correction instruction sequence; performing multi-segment weight analysis on the abnormal adjustment recognition sequence based on the working condition area characteristics to obtain a screw rotation speed change trend map, and inputting the screw rotation speed change trend map into a preset correction rule node group to generate a screw rotation speed adjustment instruction sequence.

[0012] As a preferred solution, the step of performing linkage control on the hollow plate extrusion production line according to the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence includes: calculating an adjustment amplitude set of the traction execution unit according to the traction speed correction instruction sequence, converting the screw rotation speed adjustment instruction sequence into a torque adjustment strategy set, performing linkage comparison analysis on the adjustment amplitude set and the torque adjustment strategy set to generate a synchronous execution matching matrix and a feedback offset monitoring sequence; setting a traction unit PID parameter correction group in the temperature control area according to the synchronous execution matching matrix, adjusting the temperature control weight group of the screw section using the feedback offset monitoring sequence, and performing section fusion matching on the temperature control weight group of the screw section and the traction unit PID parameter correction group to generate a composite execution instruction group; applying the composite execution instruction group to the extrusion main control system and the auxiliary linkage system of the hollow plate extrusion production line.

[0013] The present application also provides an automatic control system for a hollow board extrusion production line, including: a collection module, configured to collect real-time temperature data sequences, speed change data sequences, and pressure response data sequences during the hollow board extrusion process, and perform multi-dimensional feature extraction to obtain a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group; an analysis module, configured to perform response collaborative analysis on the temperature time-varying feature parameter group and the speed stability feature parameter group to obtain a target temperature control section sequence, and perform a time window sliding fusion operation on the pressure fluctuation feature parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence; an input module, configured to input the pressure regulation control vector group and the melt reflux rate adjustment sequence into a preset high-order regulation response map to obtain a traction rate correction factor group and an extrusion speed fine-tuning vector; a mapping module, configured to perform time series clustering analysis on the traction rate correction factor group to obtain an abnormal regulation identification sequence, and map the abnormal regulation identification sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw rotation speed adjustment instruction sequence; a control module, configured to perform linkage control on the hollow board extrusion production line according to the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence.

[0014] Compared with the prior art, the present application has the following beneficial effects: fast reaction speed and high adjustment accuracy. Through multi-dimensional feature extraction and response collaborative analysis, precise monitoring and adjustment of multiple key parameters such as temperature, speed, and pressure can be achieved; through time window sliding fusion operation and high-order regulation response map, precise control of the production process can be realized, ensuring that various parameters fluctuate within the optimal range and avoiding unstable situations caused by changes in working conditions; through time series clustering analysis and abnormal regulation identification, abnormal situations in the production process can be detected in a timely manner and effective measures can be taken for correction, and the production line can be finely adjusted through the linkage control system to improve the production efficiency and the stability of product quality, enabling the hollow board extrusion production line to operate efficiently and stably in a complex and changeable production environment, and improving the problems of slow reaction speed and insufficient adjustment accuracy existing in the existing control methods in the face of complex production conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] The structures, ratios, sizes, etc. shown in the attached drawings of this specification are only used to cooperate with the content disclosed in the specification for those familiar with this technology to understand and read, and are not used to limit the conditions for the implementation of the present invention. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the efficacy that the present invention can produce and the purpose that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0017] Figure 1 It is a schematic flowchart of the automatic control method for a hollow plate extrusion production line provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of the structure of the automatic control system for a hollow plate extrusion production line provided by an embodiment of the present invention.

[0018] Explanation of reference numerals: 10. Automatic control system of the hollow plate extrusion production line; 11. Acquisition module; 12. Analysis module; 13. Input module; 14. Mapping module; 15. Control module. Specific embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the attached drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0020] The flowchart shown in the attached drawings is only an example illustration, and does not necessarily include all contents and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may change according to the actual situation.

[0021] It should also be understood that the terms used in this specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0022] It should be further understood that the term " / and" as used in this specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0023] Next, the technical solutions of the present invention will be further described in conjunction with the attached drawings and through specific embodiments.

[0024] Example 1: As Figure 1 shown, the present application provides an automatic control method for a hollow board extrusion production line, including step S100 to step S500.

[0025] Step S100, collect the real-time temperature data sequence, speed change data sequence, and pressure response data sequence during the hollow board extrusion process, and perform multi-dimensional feature extraction to obtain a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group.

[0026] In this step, by installing temperature sensors, traction motor speed recording units, and pressure sensors at key positions on the hollow board extrusion production line, the temperature data sequence, speed change data sequence, and pressure response data sequence are collected in real time. Specifically, the temperature sensors are distributed in the heating zone and the die zone to obtain accurate temperature data, the traction motor speed recording unit monitors the change in the traction speed in real time, and the pressure sensor monitors the change in the melt pressure. These data sources can reflect the dynamic changes of key parameters such as temperature, speed, and pressure in real time at different stages of the extrusion process.

[0027] For example, the temperature data sequence recorded by the temperature sensor shows a sharp fluctuation in the heating zone; while the speed change data sequence captured by the traction motor speed recording unit shows a sudden increase or decrease at certain moments, indicating an abnormal fluctuation in the extrusion speed; at the same time, the pressure response data sequence collected by the pressure sensor can reflect a sharp fluctuation or abnormality in the pressure. By synchronously collecting and analyzing these data, various changes in the production process can be comprehensively monitored, and data support can be provided for subsequent multi-dimensional feature extraction.

[0028] Step S200, perform response collaborative analysis on the temperature time-varying feature parameter group and the speed stability feature parameter group to obtain a target temperature control section sequence, and perform time window sliding fusion operation on the pressure fluctuation feature parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence.

[0029] In this step, the temperature time-varying feature parameter group and the speed stability feature parameter group are collaboratively analyzed to establish the mutual relationship between temperature and traction speed. Specifically, the temperature time-varying feature parameter group includes the dynamic change, change amplitude, and change trend of temperature, while the speed stability feature parameter group analyzes the smoothness and change law of the traction speed. By collaboratively analyzing these two parameter groups, a target temperature control section sequence can be obtained, that is, the optimal cooperation interval between temperature and speed under different production conditions.

[0030] For example, when there is a large deviation between the temperature and the drawing speed, the system will automatically identify this state and map it to the target temperature control section sequence. According to the results of this sequence, the system further performs a time window sliding fusion operation on the pressure fluctuation characteristic parameter group, identifies the abnormal section of the pressure fluctuation, and calculates the pressure regulation control vector group and the melt return rate adjustment sequence. Through this adjustment sequence, the pressure and the return rate can be precisely adjusted within the temperature control section to maintain the stable operation of the extrusion production line.

[0031] Step S300: Input the pressure regulation control vector group and the melt return rate adjustment sequence into a preset high-order regulation response map to obtain a drawing speed correction factor group and an extrusion speed fine-tuning vector.

[0032] In this step, the input pressure regulation control vector group and the melt return rate adjustment sequence are sent to a preset high-order regulation response map for processing. Specifically, the high-order regulation response map is a complex feedback control model established by analyzing historical data and real-time production data. According to the input control vectors, this map generates the corresponding drawing speed correction factor group and extrusion speed fine-tuning vector.

[0033] For example, in a certain production cycle, the fluctuations of the pressure and the return rate are large. At this time, through the high-order regulation response map, the system can predict and output an accurate drawing speed correction factor group based on this input data. These factor groups will affect the speed of the drawing motor, thereby precisely adjusting the drawing speed and the extrusion speed during the production process, making the entire production process smoother.

[0034] Step S400: Perform time series clustering analysis on the drawing speed correction factor group to obtain an abnormal regulation identification sequence, and map the abnormal regulation identification sequence and the extrusion speed fine-tuning vector to obtain a drawing speed correction instruction sequence and a screw speed adjustment instruction sequence.

[0035] In this step, by performing time series clustering analysis on the drawing speed correction factor group, the abnormal fluctuations therein are identified. Specifically, a clustering algorithm is used to analyze the correction factors to identify the patterns of abnormal fluctuations or mutations, forming an abnormal regulation identification sequence. These abnormal fluctuations reflect some problems in the production process, such as too high temperature or too low pressure, etc.

[0036] For example, when there is a mutation in the drawing speed correction factor group, the system will regard this change as abnormal, identify and mark this abnormal regulation identification sequence. Then, map this sequence with the extrusion speed fine-tuning vector to obtain a drawing speed correction instruction sequence and a screw speed adjustment instruction sequence. These instruction sequences will be used as adjustment instructions to guide the production line to adjust the drawing speed and the screw speed to ensure the smooth progress of the production process.

[0037] Step S500: Carry out coordinated control of the hollow board extrusion production line according to the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence.

[0038] In this step, the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence are sent into the coordinated control system of the extrusion production line. Specifically, the system automatically adjusts the working states of the traction system and the extrusion system according to the contents of these two instruction sequences, so that the traction rate, extrusion speed, pressure and reflux rate in the whole production process reach the best coordination.

[0039] For example, when the traction rate and the screw rotation speed adjustment instructions are input, the system will control the traction motor and the screw motor to run at an appropriate rate, so as to ensure the stable operation of the production line and avoid product quality fluctuations or production interruptions caused by speed fluctuations.

[0040] In this embodiment, by collecting the real-time temperature data sequence, speed change data sequence and pressure response data sequence in the hollow board extrusion process, multi-dimensional feature extraction is carried out to obtain the time-varying temperature characteristic parameter group, speed stability characteristic parameter group and pressure fluctuation characteristic parameter group. Then, response collaborative analysis is carried out on the time-varying temperature characteristic parameter group and the speed stability characteristic parameter group to obtain the target temperature control section sequence. Based on the target temperature control section sequence, time-window sliding fusion operation is carried out on the pressure fluctuation characteristic parameter group, so as to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence. The pressure regulation control vector group and the melt reflux rate adjustment sequence are input into a preset high-order regulation response map, and a traction rate correction factor group and an extrusion speed fine-tuning vector are obtained therefrom. Time series clustering analysis is carried out on the traction rate correction factor group to obtain an abnormal regulation identification sequence, and the abnormal regulation identification sequence is mapped with the extrusion speed fine-tuning vector, and finally a traction speed correction instruction sequence and a screw rotation speed adjustment instruction sequence are obtained. Finally, the hollow board extrusion production line is coordinately controlled according to the traction speed correction instruction sequence and the screw rotation speed adjustment instruction sequence, so as to optimize the whole production process.

[0041] By performing multi-dimensional feature extraction on the real-time temperature data sequence, speed change data sequence, and pressure response data sequence during the hollow board extrusion production line process, the changing rules of various key parameters during the production process can be accurately captured. Based on the target temperature control section sequence and pressure fluctuation characteristics, the pressure adjustment control vector group and melt reflux rate adjustment sequence generated by the time window sliding fusion operation can effectively cope with the fluctuations and mutations in production, ensuring the stable and efficient production process. By introducing high-order adjustment response maps and time series clustering analysis, the traction speed and screw speed can be adjusted according to the real-time working conditions, thereby greatly improving the automation control accuracy of the production line and improving the problems of slow reaction speed and insufficient adjustment accuracy existing in the existing control methods when facing complex production conditions.

[0042] Example 2: In step S100, the real-time temperature data sequence, speed change data sequence, and pressure response data sequence are respectively obtained through the multi-point temperature sensing unit, traction motor speed recording unit, and pressure sensor set within the temperature control area.

[0043] The real-time temperature data sequence, speed change data sequence, and pressure response data sequence are respectively obtained through the multi-point temperature sensing unit, traction motor speed recording unit, and pressure sensor set within the temperature control area; specifically, within the temperature control area of the extrusion production line, multiple temperature sensing units are evenly distributed in key areas such as the heating area, cooling area, and die area to monitor the temperature change in real time. The traction motor speed recording unit is installed on the traction motor and is responsible for collecting the change in the motor speed to obtain the change data of the traction speed in real time. The pressure sensor is installed at the melt channel and the die outlet to accurately record the change data of the melt pressure. Through the real-time data collection of these sensors, the system can obtain important production parameters including temperature, traction speed, and melt pressure, providing support for subsequent feature extraction.

[0044] For example, during an extrusion production process, the temperature data sequence recorded by the temperature sensing unit in the temperature control area shows that the temperature in the heating area rises relatively rapidly, while the temperature in the cooling area drops slowly; the speed data sequence captured by the traction motor speed recording unit shows that the speed of the traction motor suddenly increases during a certain period, indicating a change in the traction load; at the same time, the pressure response data sequence monitored by the pressure sensor also shows unstable fluctuations in the melt pressure, which is related to the fluctuations in temperature or speed. By collecting and synchronizing these data in real time, the system can comprehensively understand the operating state of the production line.

[0045] Perform section segmentation processing and amplitude normalization analysis on the temperature data sequence to obtain a temperature section dynamic amplitude parameter group and a temperature gradient change parameter group. Perform interval weighted difference operation and steady-state stability section identification processing on the speed change data sequence to obtain a traction speed fluctuation section distribution group and a speed steady-state average vector group. Based on the mean deviation and kurtosis coefficient of the time-domain response, jointly analyze the pressure response data sequence to obtain a pressure dynamic discrete factor group and a pressure trend response mapping vector.

[0046] Perform continuous section segmentation on the temperature data sequence through a preset sliding time window to obtain multiple temperature time sections. Specifically, first, perform section segmentation on the temperature data sequence using the sliding time window processing method, select a reasonable time window length, and gradually divide the temperature data into multiple time sections. The data within each section will be used to calculate the temperature dynamic amplitude index through maximum value normalization and interval difference amplitude calculation. This process can effectively remove the noise in the temperature sequence and extract the main features of temperature changes.

[0047] For example, within a certain section, the temperature data collected by the temperature sensor fluctuates greatly. The system standardizes the temperature data in this section according to the maximum value normalization algorithm, and then performs interval difference amplitude calculation to obtain the temperature dynamic amplitude index of this section. These indexes can accurately reflect the temperature fluctuation degree within this section, facilitating subsequent temperature control optimization.

[0048] Among them, the steps of performing section segmentation processing and amplitude normalization analysis on the temperature data sequence to obtain a temperature section dynamic amplitude parameter group and a temperature gradient change parameter group, performing interval weighted difference operation and steady-state stability section identification processing on the speed change data sequence to obtain a traction speed fluctuation section distribution group and a speed steady-state average vector group, and jointly analyzing the pressure response data sequence based on the mean deviation and kurtosis coefficient of the time-domain response to obtain a pressure dynamic discrete factor group and a pressure trend response mapping vector include: Perform continuous section segmentation on the temperature data sequence through a preset sliding time window to obtain multiple temperature time sections, and perform maximum value normalization and interval difference amplitude calculation on the temperature data within each temperature time section to obtain a temperature dynamic amplitude index group.

[0049] Perform continuous section segmentation on the temperature data through sliding time window processing; specifically, set a sliding window according to the actual time window of the extrusion process (such as every 1 second or every 10 seconds). The system uses this window to segment the temperature data sequence to generate multiple time periods, and each period contains a certain number of temperature data. The data in each section is standardized through the maximum value normalization method, so that the temperature change data in each time section can be compared and analyzed under a unified standard. In addition, the system also performs interval difference amplitude calculation on the temperature data of each section to obtain the maximum fluctuation amplitude within this section.

[0050] For example, during a certain production cycle, after the temperature data sequence is segmented by a sliding window, multiple time periods are obtained, and the temperature data within each time period fluctuates greatly. Through maximum normalization, the system converts these data into the same scale, removes the differences between them, and ensures the accuracy of subsequent analysis. Then, for each section, the difference amplitude of the temperature change is calculated, and the generated temperature dynamic amplitude index group can accurately reflect the temperature fluctuation characteristics within each time period.

[0051] Perform adjacent section difference calculation on the temperature dynamic amplitude index group and archive it as the temperature change rate index. Based on the temperature change rate index, construct a temperature gradient trend curve, and extract the rising section and falling section of the temperature gradient trend curve to generate a temperature gradient change parameter group.

[0052] By performing adjacent section difference calculation on the temperature dynamic amplitude index group; specifically, by performing difference calculation on the data of adjacent sections in the temperature dynamic amplitude index group, the temperature change rate index is obtained. The temperature change rate represents the change speed of the temperature within each time period, and further constructs a temperature gradient trend curve to depict the change trend of the temperature. According to the change of the temperature change rate, the system can extract the rising section and falling section in the temperature gradient trend curve, and these sections represent the stages of accelerated temperature increase or decrease.

[0053] For example, the adjacent sections in the temperature dynamic amplitude index group are [20°C, 25°C] and [25°C, 30°C] respectively. Through difference calculation, the change rate is obtained as 5°C / unit time. Based on this, the system constructs a temperature gradient trend curve and observes the rising section (such as when the temperature changes from 20°C to 25°C) and falling section (such as when the temperature drops from 30°C to 25°C) of the temperature curve. These rising sections and falling sections constitute the temperature gradient change parameter group, which is used for the formulation of subsequent temperature control strategies.

[0054] Slide the window of the speed change data sequence at a fixed time granularity, perform weighted difference calculation on the speed values within each window, obtain the speed local fluctuation factor group, compare the speed local fluctuation factor group with the historical standard steady-state speed reference vector, identify the relatively stable sections and fluctuating sections, and generate the speed steady-state average vector group and the traction speed fluctuation section distribution group.

[0055] Process the speed data by window sliding; specifically, set a fixed time granularity (such as 1 second or 10 seconds), and based on this, perform window sliding on the speed change data sequence. For the speed values in each time window, use weighted difference calculation to obtain the local speed fluctuation factors, which reflect the intensity of speed fluctuation in this interval. Then, compare the calculated local speed fluctuation factors with the historical standard steady-state speed reference vector to identify the stable sections and fluctuating sections among them.

[0056] For example, within a certain period, the rotational speed of the traction motor shows significant fluctuations. Through window sliding processing, the speed change within each window is calculated to obtain the fluctuation factor by weighted difference. The system compares with the historical stable speed reference vector and finds that this period is a fluctuating section. Finally, based on the identification results of fluctuations and stability, the system generates a traction speed fluctuation section distribution group and a speed steady-state average vector group for formulating subsequent speed adjustment strategies.

[0057] Apply the joint processing of average deviation calculation and asymmetric kurtosis measurement method to the pressure response data sequence, extract the abnormal amplitude points and the buffer response steady intervals, establish the distribution density map of the pressure dynamic response sequence based on the abnormal amplitude points, and calculate the discrete rate and deviation factor for different density sections of the distribution density map to generate the pressure dynamic discrete factor group.

[0058] Analyze the pressure response data by applying the average deviation calculation and asymmetric kurtosis measurement method; specifically, first, evaluate the average fluctuation degree in the pressure response data through average deviation calculation. Then, use the asymmetric kurtosis measurement method to further analyze the abnormal fluctuations in the pressure response. Through these two statistical methods, extract the abnormal amplitude points and the buffer response steady intervals in the pressure response sequence. Then, based on these abnormal amplitude points, establish the distribution density map of the pressure dynamic response sequence, and calculate the discrete rate and deviation factor for different density sections to obtain the pressure dynamic discrete factor group.

[0059] For example, in the pressure data sequence, a certain section of data shows large fluctuations. After using the average deviation calculation, the fluctuation level of this section of data is high, and then the asymmetric kurtosis method is applied to further confirm its abnormality. By establishing the distribution density map of the pressure dynamic response sequence, it can be found that the density of some sections is much higher than other regions. The system calculates the discrete rate for these regions and finally generates the pressure dynamic discrete factor group to provide a basis for the pressure control strategy.

[0060] Perform linear regression modeling on the pressure change trend in the buffer response steady interval, compare the linear regression results with the pressure change trend data in the historical process state database, and extract the correlation relationship between the directionality and amplitude of the pressure change based on the comparison results to generate the pressure trend response mapping vector.

[0061] Model the pressure change trend through linear regression; specifically, in the stable interval of the buffer response, use the linear regression method to model the pressure change trend to obtain the pressure change curve in this section. Then, compare the obtained regression result with the pressure change trend in the similar section in the historical process state database to identify the directionality (such as rising or falling trend) and amplitude (such as the rate and amplitude of pressure change) of the pressure change.

[0062] For example, in a certain time period, the pressure data shows a stable linear rising trend, and the linear regression model can fit this trend. By comparing with the similar trends in the historical process state database, the system can extract the directionality of this rising trend and its change amplitude. Finally, the pressure trend response mapping vector generated by this method will provide an accurate basis for subsequent pressure regulation.

[0063] Perform cross-dimensional mapping on the temperature gradient change parameter group and the traction speed fluctuation section distribution group to construct a temperature-speed response coupling feature group, perform point-to-region fusion processing on the pressure dynamic discrete factor group and the temperature section dynamic amplitude parameter group to obtain a pressure-temperature cross feature factor set, and perform connected graph mapping structure construction on the speed steady-state average vector group and the pressure trend response mapping vector to obtain a voltage stabilization relationship map.

[0064] Through cross-dimensional mapping and point-to-region fusion processing; specifically, perform cross-dimensional mapping on the temperature gradient change parameter group and the traction speed fluctuation section distribution group, combine the change trends of temperature and traction speed to obtain a temperature-speed response coupling feature group. Subsequently, perform point-to-region fusion processing on the pressure dynamic discrete factor group and the temperature section dynamic amplitude parameter group to obtain a pressure-temperature cross feature factor set. Finally, through the connected graph mapping method, map the speed steady-state average vector group and the pressure trend response mapping vector to obtain a voltage stabilization relationship map.

[0065] For example, through cross-dimensional mapping, the system can combine the changes in temperature gradient and traction speed fluctuation to generate a temperature-speed response coupling feature group, revealing the mutual relationship between the two. Then, through point-to-region fusion processing, the system combines the dynamic discreteness of pressure with the amplitude of temperature change to form a pressure-temperature cross feature factor set. Finally, through graph mapping, the relationship between speed and pressure is connected to obtain a voltage stabilization relationship map, providing an accurate basis for subsequent control.

[0066] Merge the temperature-speed response coupling feature group, the pressure-temperature cross feature factor set, and the voltage stabilization relationship map into a data graph to generate a multi-dimensional feature integration map, and perform dimension regularization and redundant factor pruning processing on the multi-dimensional feature integration map to extract the temperature time-varying feature parameter group, the speed stability feature parameter group, and the pressure fluctuation feature parameter group.

[0067] Through multi-dimensional feature merging and pruning processing; specifically, merge the above temperature-speed response coupling feature groups, pressure-temperature cross-feature factor sets, and voltage stabilization relationship maps to generate a comprehensive multi-dimensional feature integration map. Then, perform dimensional regularization on this map, remove redundant factors, optimize data representation, and finally extract the core temperature time-varying feature parameter group, speed stability feature parameter group, and pressure fluctuation feature parameter group.

[0068] For example, through map merging, the system can integrate the complex relationships between temperature, speed, and pressure, and use pruning algorithms to remove duplicate or irrelevant feature factors, ultimately generating a concise and effective feature integration map. This map provides a simple and efficient multi-dimensional data model for subsequent production control.

[0069] In step S200, extract the temperature interval mutation points and section stability factors based on the temperature time-varying feature parameter group to generate a temperature node group and a temperature steady-state distribution group, and perform response collaborative analysis on the temperature node group and the speed stability feature parameter group to obtain a temperature-speed coupling section map.

[0070] By analyzing the temperature time-varying feature parameter group; specifically, by extracting the mutation points and section stability factors in the temperature time-varying feature parameter group, the system can determine the sharp change (such as sudden rise or fall) points in the temperature data, which are the key adjustment moments of the temperature control system. In addition, by analyzing the stability of each section, a temperature steady-state distribution group can be obtained, which shows the stability degree of the temperature within the temperature control range. Then, based on these feature parameters, the system performs response collaborative analysis on the temperature node group and the speed stability feature parameter group to generate a temperature-speed coupling section map.

[0071] For example, in the actual production process, the temperature rapidly rises or drops sharply within a certain interval in the temperature data sequence. The system will identify these temperature mutation points through the mutation point detection algorithm, analyze the stable sections, identify the sections with relatively stable temperature changes, and form a temperature steady-state distribution group. Then, by combining the temperature node group and the speed stability feature parameter group, analyze the relationship between the two to generate a temperature-speed coupling section map, showing the interaction effect between temperature changes and traction speed.

[0072] Extract the traction rate sensitivity distribution map based on the temperature-speed coupling section map, perform node reconstruction processing on the traction rate sensitivity distribution map and the temperature steady-state distribution group to obtain the target temperature control section sequence, and perform time window sliding fusion operation on the target temperature control section sequence and the pressure fluctuation feature parameter group to obtain the pressure zone dynamic response sequence and the feedback buffer section map.

[0073] Extract the traction rate sensitivity distribution map through the temperature-speed coupling section map; specifically, from the generated temperature-speed coupling section map, the system can extract the traction rate sensitivity distribution map. This map reflects the response sensitivity of the traction rate to temperature changes and shows the impact of the traction rate on the production process in different temperature control sections. Then, the system reconstructs the nodes of the traction rate sensitivity distribution map and the temperature steady-state distribution group to identify the optimal impact of the traction rate on the temperature control system under specific conditions, thereby obtaining the target temperature control section sequence. Finally, based on the target temperature control section sequence and the pressure fluctuation characteristic parameter group, perform a time window sliding fusion operation to generate the nip zone dynamic response sequence and the feedback buffer section map.

[0074] For example, in practical applications, when the temperature changes rapidly, the change in the traction rate has a significant impact on the temperature control process. The system extracts the sensitivity of the traction rate to temperature changes according to the temperature-speed coupling section map, combines it with the temperature steady-state distribution group, and identifies the optimal temperature control section through node reconstruction. Subsequently, the target temperature control section sequence and the pressure fluctuation characteristic parameter group are used together to perform a sliding window fusion calculation to obtain the dynamic response sequence of pressure regulation and temperature control.

[0075] Perform an asymmetric difference smoothing process on the nip zone dynamic response sequence, perform a sliding window fitting and regional weight back-projection on the smoothed nip zone dynamic response sequence and the feedback buffer section map to obtain the nip zone disturbance response fitting surface and the section abnormal offset set, and identify the main disturbance source and perform hierarchical aggregation analysis based on the intersection area of the nip zone disturbance response fitting surface and the section abnormal offset set, and extract the local disturbance compensation factor group and the pressure extreme value distribution area group.

[0076] Perform an asymmetric difference smoothing process on the nip zone dynamic response sequence; specifically, apply the asymmetric difference smoothing algorithm to the nip zone dynamic response sequence to remove the high-frequency noise in the data and maintain the overall trend of the pressure change. The smoothed data can more accurately reflect the basic pattern of the pressure change. Subsequently, combine the smoothed data with the feedback buffer section map and use the sliding window fitting and regional weight back-projection methods to obtain the nip zone disturbance response fitting surface. This process helps the system identify the key disturbance areas in the pressure change and extract the characteristics of these disturbances. By analyzing the intersection area of the disturbance response fitting surface and the abnormal offset set, further identify the main disturbance source and use hierarchical aggregation analysis to find the main disturbance sources, and finally extract the local disturbance compensation factor group and the pressure extreme value distribution area group.

[0077] For example, during a certain production process, the pressure fluctuates greatly. After the system performs asymmetric difference smoothing processing, it is found that the smoothed curve shows a prominent fluctuation trend. By combining with the feedback buffer section map, the system can accurately identify the main disturbance area of the pressure change and classify it as the disturbance source. Then, based on this analysis, the system will identify the local disturbance compensation factor group and use the pressure extreme value distribution area group as the adjustment basis to ensure the stability of the production process.

[0078] Perform feature transformation and quantization on the local disturbance compensation factor group to obtain a pressure adjustment control vector group, and convert the pressure extreme value distribution area group into a melt return rate adjustment sequence according to the non-linear mapping relationship between the pressure extreme value and the return rate.

[0079] By performing feature transformation and quantization on the local disturbance compensation factor group; specifically, after extracting the local disturbance compensation factor group, the system performs feature transformation on it to convert it into a data format more suitable for control and adjustment. Through quantization processing, these factors are converted into discrete control signals to generate a pressure adjustment control vector group. Then, according to the non-linear mapping relationship between the pressure extreme value and the return rate, the system maps the pressure extreme value distribution area group into a melt return rate adjustment sequence. This mapping relationship takes into account the complex non-linear relationship between the pressure and the return rate to achieve precise return rate adjustment.

[0080] For example, during a certain production process, when the system detects that the pressure extreme value in the pressure area exceeds the normal range, based on the quantization of the local disturbance compensation factor group, a corresponding pressure adjustment control vector group is generated. According to the non-linear mapping relationship, the system models the non-linear relationship between the pressure extreme value and the return rate, and converts the pressure extreme value distribution area group into a melt return rate adjustment sequence, thereby precisely adjusting the return rate and optimizing the production process.

[0081] In step S300, construct a high-order adjustment response map based on the historical data before adjustment and the output quality response. Among them, the high-order adjustment response map includes an adjustment mapping baseline group and a quality comparison node group.

[0082] By comparing the historical data with the quality response; specifically, the system constructs a high-order adjustment response map based on the historical data before adjustment and the quality response of the production output. This map mainly includes two parts: an adjustment mapping baseline group and a quality comparison node group. The adjustment mapping baseline group is a mapping baseline established through historical data, which represents the ideal response state of each parameter in the production process under different adjustment strategies; the quality comparison node group is generated by comparing the output quality data with the ideal state, and the generated nodes reflect the deviation between the production quality and the theoretical quality.

[0083] For example, in historical data, the traction rate and temperature in a certain production process fluctuate greatly. By comparing the historical data with the quality response, a set of adjustment mapping baselines is generated. Subsequently, based on the quality data extracted from the current production process, the system compares the quality comparison node group with the historical quality to obtain the difference between the current quality and the expected quality. This process constructs a high-order adjustment response map for subsequent adjustment.

[0084] Map the pressure adjustment control vector group to the adjustment mapping baseline group to generate a baseline response displacement group and an adjustment energy distribution vector. Cross-project the melt return rate adjustment sequence with the quality comparison node group to obtain a return quality adaptation factor group and a quality deviation judgment sequence.

[0085] By matching the control vector with the baseline map; specifically, map the pressure adjustment control vector group obtained from the temperature control system to the adjustment mapping baseline group to determine the baseline response displacement during the production process. Through the analysis of these mapping results, a baseline response displacement group and an adjustment energy distribution vector are generated. These results describe the impact of adjustment parameters on quality during the production process. At the same time, cross-project the melt return rate adjustment sequence with the quality comparison node group to generate a return quality adaptation factor group and a quality deviation judgment sequence, which are used to measure the degree of influence of the return rate on quality.

[0086] For example, in a production cycle, after the pressure adjustment control vector group is mapped, the system can identify the baseline response displacement group, indicating the degree of influence of the changes in the traction rate and temperature on the pressure under certain adjustment conditions. At the same time, through the cross-project of the return rate adjustment sequence with the quality comparison node group, a return quality adaptation factor group is generated to help identify which return rate adjustment strategies can better meet the quality requirements.

[0087] Perform a fusion deviation calculation on the baseline response displacement group and the return quality adaptation factor group to generate a deviation correction projection matrix and a return influence section identification set. Extract the rate sensitivity weight matrix and the extrusion efficiency perturbation factor based on the adjustment energy distribution vector and the quality deviation judgment sequence.

[0088] Through fusion deviation calculation and weight extraction; specifically, after generating the baseline response displacement group and the return quality adaptation factor group, the system performs a fusion deviation calculation on the two. By calculating the deviation, the deviation value between the current production process and the historical ideal state is determined, and a deviation correction projection matrix is generated. Then, based on the adjustment energy distribution vector and the quality deviation judgment sequence, the system further extracts the rate sensitivity weight matrix and the extrusion efficiency perturbation factor for further adjustment of the speed and efficiency in the production process.

[0089] For example, in a certain production process, the system identifies, through deviation calculation, that at the current reflux rate, there is a large deviation between the product quality and the ideal quality. Through the deviation correction projection matrix, the system can adjust the control strategy to reduce the deviation. Subsequently, according to the quality deviation judgment sequence, the rate sensitivity weight matrix and the extrusion efficiency perturbation factor are extracted for adjusting the traction rate and the screw rotation speed.

[0090] Perform point - position fusion analysis on the deviation correction projection matrix and the rate sensitivity weight matrix to obtain a traction rate correction factor group, and perform combined mapping on the reflux - influence section identification set and the extrusion efficiency perturbation factor to generate a fine - tuning vector for the extrusion speed.

[0091] Through point - position fusion and mapping; specifically, the system performs point - position fusion analysis on the deviation correction projection matrix and the rate sensitivity weight matrix, and generates a traction rate correction factor group through the matching of each point. At the same time, perform combined mapping on the reflux - influence section identification set and the extrusion efficiency perturbation factor, thereby generating a fine - tuning vector for the extrusion speed to accurately adjust the traction rate and the extrusion speed.

[0092] For example, during application, the system identifies that the traction rate in a certain section is too high, affecting the product quality. Through point - position fusion analysis, the system obtains a traction rate correction factor group for accurately adjusting the traction rate. At the same time, through the combination of the identification of the reflux - influence section and the extrusion efficiency perturbation factor, a fine - tuning vector for the extrusion speed is generated, thereby adjusting the rotation speed of the extruder to maintain stable product quality.

[0093] In step S400, flatten the traction rate correction factor group along the time axis and perform node resampling to obtain a reconstructed time - series vector group and a node - time mapping group.

[0094] Through time - axis flattening and node resampling; specifically, flatten the traction rate correction factor group along the time axis, expand the data in the time series in chronological order to eliminate the interference of any non - linear changes. Then, perform node resampling, that is, uniformly resample the nodes in the time series to ensure the uniformity of the data in time, and obtain a reconstructed time - series vector group and a node - time mapping group. The purpose of resampling is to eliminate the time irregularities existing in the original data, making the data more stable and consistent in subsequent analysis.

[0095] For example, in a production process, the traction rate correction factor group contains rate correction values at different time nodes, and these nodes are uneven due to external factors. After flattening and resampling, the system homogenizes the data to ensure the consistency of the correction factors at each time point. Then, the obtained reconstructed time - series vector group can clearly show the change of the traction rate, while the node - time mapping group can accurately correspond to the time points, facilitating subsequent clustering and analysis.

[0096] Apply a sliding clustering window to perform multi-scale clustering on the reconstructed time series vector group to obtain an abnormal fluctuation node set, and re-locate the abnormal fluctuation node set with the node time mapping group to generate an abnormal adjustment recognition sequence.

[0097] Through multi-scale clustering and sliding window processing; specifically, the system uses the sliding clustering window method to perform multi-scale clustering on the reconstructed time series vector group. The sliding clustering window method slides on the time axis and performs clustering analysis on the data within each window. By adjusting the window size and clustering parameters, the system can identify abnormal fluctuations at different time scales. The obtained abnormal fluctuation node set marks the nodes with significant changes or instability in the time series. Then, the system relocates these abnormal nodes with the node time mapping group to correctly correspond the abnormal nodes in time, thereby generating an abnormal adjustment recognition sequence to identify the abnormal adjustment points that need to be focused on.

[0098] For example, in a certain production process, the traction rate changes greatly and there are abnormal fluctuations. After processing with the sliding clustering window, the system can identify the nodes with significant fluctuations and mark these nodes as abnormal fluctuation nodes. The system relocates these nodes to obtain an accurate abnormal adjustment recognition sequence, which is convenient for subsequent adjustment and correction.

[0099] Align the dimensions of the abnormal adjustment recognition sequence with the extrusion speed fine-tuning vector and perform principal cause mapping to obtain the main adjustment mapping group and the secondary perturbation response group.

[0100] Through dimension alignment and cause mapping; specifically, the system aligns the dimensions of the abnormal adjustment recognition sequence with the extrusion speed fine-tuning vector, converting them to the same data dimension and unit. This process ensures that the two can be compared under the same analysis framework. Then, the system performs principal cause mapping, analyzes the causal relationship between abnormal adjustment and fine-tuning speed, and maps this data into the main adjustment mapping group and the secondary perturbation response group. The main adjustment mapping group shows the relationship between the main adjustment factors (such as the feedback of the traction rate and the temperature control system) and the abnormal adjustment, while the secondary perturbation response group contains the influence of other secondary factors.

[0101] For example, in a certain production, the system identifies that the fluctuation of the traction rate causes the instability of product quality. Through dimension alignment, the abnormal adjustment recognition sequence and the extrusion speed fine-tuning vector are unified to the same data dimension. The system then performs cause mapping and finds that there is a significant relationship between the traction rate fluctuation and the deviation of product quality. Finally, this information is mapped into the main adjustment mapping group and the secondary perturbation response group to generate adjustment instructions.

[0102] Construct an initial traction speed correction instruction sequence framework using the main adjustment mapping group, linearly compensate the secondary disturbance response group and then fuse it into the initial traction speed correction instruction sequence framework to generate a traction speed correction instruction sequence.

[0103] Through constructing an initial correction instruction framework and linear compensation; specifically, the system first constructs an initial traction speed correction instruction sequence framework according to the main adjustment mapping group, and this framework defines the preliminary target of traction rate correction based on the information in the main adjustment mapping group. Then, for the secondary disturbance response group, the system performs linear compensation processing to compensate for the influence of secondary disturbance factors. Finally, the compensated secondary disturbance response group will be fused with the initial instruction framework to generate the final traction speed correction instruction sequence.

[0104] For example, in a certain production process, a preliminary traction rate correction instruction framework is generated through the main adjustment mapping group. If the system detects secondary disturbances (such as equipment wear or load change), it adjusts the value of the secondary disturbance response group through linear compensation to ensure that the final traction speed correction instruction sequence can adapt to the current working conditions, thus ensuring the smooth operation of production.

[0105] Based on the characteristics of the working condition area, perform multi-segment weight analysis on the abnormal adjustment recognition sequence to obtain a screw rotation speed change trend map, and input the screw rotation speed change trend map into a preset correction rule node group to generate a screw rotation speed adjustment instruction sequence.

[0106] Through multi-segment weight analysis; specifically, when processing the abnormal adjustment recognition sequence, the system performs multi-segment weight analysis on the data according to the characteristics of different working condition areas. By assigning different weights to different segments, the system can accurately evaluate the contribution of each segment to the change of the screw rotation speed. The analysis result generates a screw rotation speed change trend map. Then, input this map into the preset correction rule node group to generate a screw rotation speed adjustment instruction sequence, ensuring that the screw rotation speed adjustment can be optimized according to the actual production requirements.

[0107] For example, in a certain production process, the change of the screw rotation speed is affected by different working conditions (such as pressure fluctuation, temperature change). The system evaluates the influence under different working conditions through weight analysis to obtain a screw rotation speed change trend map. Subsequently, by matching this map with the correction rule node group, a screw rotation speed adjustment instruction sequence is generated to ensure the optimized adjustment of the screw rotation speed under various working conditions.

[0108] In step S500, calculate the adjustment amplitude set of the traction execution unit according to the traction speed correction instruction sequence, convert the screw rotation speed adjustment instruction sequence into a torque adjustment strategy set, perform a linkage comparison analysis on the adjustment amplitude set and the torque adjustment strategy set, and generate a synchronous execution matching matrix and a feedback offset monitoring sequence.

[0109] By calculating the adjustment amplitude set of the traction execution unit; specifically, according to the traction speed correction instruction sequence, the amplitude set that the traction execution unit needs to adjust is calculated. Each amplitude value represents the degree of correction of the traction speed by the system according to the current production state. Then, the system converts the screw rotation speed adjustment instruction sequence into a torque adjustment strategy set, and these strategies will adjust the torque applied to the screw according to the change of the screw rotation speed. Through the linkage comparison of these two, the system performs a synchronous execution matching analysis to generate a synchronous execution matching matrix and a feedback offset monitoring sequence for precisely synchronizing the adjustment of traction and screw rotation speed.

[0110] For example, during the production process, when the traction speed needs to be adjusted to adapt to product quality changes, the system calculates the adjustment amplitude of the traction execution unit through the traction speed correction instruction sequence (for example, the traction speed needs to be increased by 5%). At the same time, the system calculates the screw rotation speed adjustment instruction sequence and converts it into the corresponding torque adjustment strategy. Through the linkage comparison, the system generates a synchronous execution matching matrix to ensure that the adjustment of traction speed and screw rotation speed is coordinated within the same time, thus avoiding conflicts or errors.

[0111] Set the PID parameter correction group of the traction unit within the temperature control area according to the synchronous execution matching matrix, and use the feedback offset monitoring sequence to adjust the temperature control weight group of the screw section. Perform section fusion matching on the temperature control weight group of the screw section and the PID parameter correction group of the traction unit to generate a composite execution instruction group.

[0112] By setting the PID parameter correction group and the temperature control weight group; specifically, after obtaining the synchronous execution matching matrix, the system uses this matrix to set the PID parameter correction group of the traction unit. The PID parameter correction group is used to adjust the PID controller of the traction unit to ensure that the traction speed and pressure regulation achieve the expected effect. At the same time, the system uses the feedback offset monitoring sequence to adjust the temperature control weight group of the screw section. By adjusting the temperature control weight, the temperature of the screw section is controlled to optimize the melt fluidity and molding quality. Finally, perform fusion matching on the temperature control weight group of the screw section and the PID parameter correction group of the traction unit to generate a composite execution instruction group, and this composite instruction group will optimize the response of both the traction speed and the temperature control system.

[0113] For example, during the production process, the system adjusts the traction speed through the synchronous execution matching matrix and simultaneously corrects the PID controller to ensure that the traction speed and pressure operate within an appropriate range. In addition, the system adjusts the temperature control weight group of the screw section to ensure that the melt temperature always remains within an appropriate range, avoiding the influence of too high or too low temperature on product quality. By fusing these two, a composite execution instruction group is generated to ensure the coordinated operation of the entire system.

[0114] Apply the composite execution instruction set to the extrusion master control system and the auxiliary linkage system of the hollow board extrusion production line.

[0115] By applying the composite execution instruction set to the master control and linkage systems; specifically, the generated composite execution instruction set will be input into the extrusion master control system and the auxiliary linkage system of the hollow board extrusion production line in real time. These systems will perform coordinated control according to the composite instructions to ensure the stability and consistency of various parameters such as the traction speed, screw rotation speed, and temperature, maximizing production efficiency and ensuring product quality. The coordinated operation of the master control system and the linkage system ensures that every link in the production process can respond in a timely manner and make precise adjustments.

[0116] For example, in a certain production process, the traction speed and screw rotation speed need to be adjusted to cope with changes in raw materials. After the system generates the composite execution instruction set, this instruction set is input into the master control system and the auxiliary system. The master control system will adjust the traction speed, and the auxiliary system will adjust the screw rotation speed and the temperature control system. Through such coordination, the entire extrusion production process can proceed smoothly, avoiding the impact of a single system malfunction on production quality.

[0117] In this embodiment, by collecting the real-time temperature data sequence, speed change data sequence, and pressure response data sequence during the hollow board extrusion process and performing multi-dimensional feature extraction on these data, the system can accurately capture the dynamic changes of various key parameters. Through the joint analysis of the temperature time-varying characteristic parameter group, speed stability characteristic parameter group, and pressure fluctuation characteristic parameter group, the system can evaluate the change trend of each parameter in real time and optimize the temperature control section to ensure the stability and precise control of the production process. Based on the high-order adjustment response map, the system can finely adjust the traction speed, screw rotation speed, and melt reflux rate, generate a reasonable correction instruction sequence, and perform real-time adjustment through the linkage control system to ensure the coordination and balance of each link in the production process. In addition, based on the fusion of the abnormal adjustment recognition sequence and the extrusion speed fine-tuning vector, the system can effectively identify and correct potential operating conditions abnormalities, thereby improving the consistency of production efficiency and product quality. During the adjustment process, through multi-section weight analysis and non-linear mapping, the system can optimize the adjustment of the traction speed and screw rotation speed, and finally generate a synchronous execution matching matrix and a composite execution instruction set, which are applied to the master control and auxiliary systems of the hollow board extrusion production line to ensure the precise execution of each control instruction and improve the automation level and stability of production. Through these comprehensive means, this embodiment realizes the automatic adjustment and real-time optimization control of the hollow board extrusion production line, significantly improving production efficiency, product quality, and system stability.

[0118] Embodiment 3: Such as Figure 2As shown in the figure, the present application also provides an automatic control system 10 for a hollow board extrusion production line, including an acquisition module 11, an analysis module 12, an input module 13, a mapping module 14, and a control module 15.

[0119] The acquisition module 11 is mainly used to collect real-time temperature data sequences, speed change data sequences, and pressure response data sequences during the hollow board extrusion process, and perform multi-dimensional feature extraction to obtain a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group.

[0120] The analysis module 12 is mainly used to perform response collaborative analysis on the temperature time-varying feature parameter group and the speed stability feature parameter group to obtain a target temperature control section sequence, and perform a time window sliding fusion operation on the pressure fluctuation feature parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence.

[0121] The input module 13 is mainly used to input the pressure regulation control vector group and the melt reflux rate adjustment sequence into a preset high-order regulation response map to obtain a traction speed correction factor group and an extrusion speed fine-tuning vector.

[0122] The mapping module 14 is mainly used to perform time series clustering analysis on the traction speed correction factor group to obtain an abnormal regulation identification sequence, and map the abnormal regulation identification sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw speed adjustment instruction sequence.

[0123] The control module 15 is mainly used to perform linkage control on the hollow board extrusion production line according to the traction speed correction instruction sequence and the screw speed adjustment instruction sequence.

[0124] In this embodiment, an efficient automatic control system for a hollow board extrusion production line is constructed by combining the collaborative work of the acquisition module 11, the analysis module 12, the input module 13, the mapping module 14, and the control module 15. The acquisition module 11 is responsible for collecting temperature, speed, and pressure data during the production process in real time, and generating a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group through multi-dimensional feature extraction technology, providing accurate data support for subsequent analysis. The analysis module 12 identifies the target temperature control section through the collaborative analysis of the responses of the temperature and speed feature parameters, and performs fusion operations on the pressure fluctuation feature parameter group according to this section, generating a pressure regulation control vector group and a melt reflux rate adjustment sequence. The input module 13 inputs these adjustment sequences into a preset high-order regulation response map, further generating a traction rate correction factor group and an extrusion speed fine-tuning vector. The mapping module 14 performs time series clustering analysis on the traction rate correction factor group, identifies an abnormal regulation identification sequence, and maps it to the extrusion speed fine-tuning vector, finally obtaining a traction speed correction instruction sequence and a screw speed adjustment instruction sequence. The control module 15 performs linkage control on the production line according to these instructions, thereby optimizing the coordination between the traction rate and the screw speed, ensuring the stability of the production process and the consistency of product quality. Through this comprehensive automatic control system, this embodiment can effectively improve the automation level and production efficiency of the hollow board extrusion production line, while ensuring the high-quality output of products.

[0125] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described system and each module can refer to the corresponding processes in the foregoing Embodiment 1, and will not be repeated here.

[0126] The structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the limiting conditions under which the present invention can be implemented. Therefore, they do not have a substantial technical meaning. Any modification of the structure, change of the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed by the present invention.

[0127] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic control method for a hollow board extrusion production line, characterized in that, Including: Collecting real-time temperature data sequence, speed change data sequence and pressure response data sequence during the hollow plate extrusion process, and performing multi-dimensional feature extraction to obtain a time-varying temperature feature parameter group, a speed stability feature parameter group and a pressure fluctuation feature parameter group; Performing response collaborative analysis on the time-varying temperature feature parameter group and the speed stability feature parameter group to obtain a target temperature control section sequence, and performing a time window sliding fusion operation on the pressure fluctuation feature parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt return rate adjustment sequence; Inputting the pressure regulation control vector group and the melt return rate adjustment sequence into a preset high-order regulation response map to obtain a traction speed correction factor group and an extrusion speed fine-tuning vector; Performing time series clustering analysis on the traction speed correction factor group to obtain an abnormal regulation identification sequence, and mapping the abnormal regulation identification sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw speed adjustment instruction sequence; Performing linkage control on the hollow plate extrusion production line according to the traction speed correction instruction sequence and the screw speed adjustment instruction sequence.

2. The automatic control method of the hollow board extrusion production line according to claim 1, characterized in that, The step of collecting real-time temperature data sequence, speed change data sequence and pressure response data sequence during the hollow plate extrusion process, and performing multi-dimensional feature extraction to obtain a time-varying temperature feature parameter group, a speed stability feature parameter group and a pressure fluctuation feature parameter group includes: Respectively obtaining a real-time temperature data sequence, a speed change data sequence and a pressure response data sequence through a multi-point temperature sensing unit, a traction motor speed recording unit and a pressure sensor set in a temperature control area; Performing section segmentation processing and amplitude normalization analysis on the temperature data sequence to obtain a temperature section dynamic amplitude parameter group and a temperature gradient change parameter group, performing interval weighted difference operation and steady-state stability section identification processing on the speed change data sequence to obtain a traction speed fluctuation section distribution group and a speed steady-state average vector group, and performing joint analysis on the pressure response data sequence based on the time-domain response mean deviation and kurtosis coefficient to obtain a pressure dynamic discrete factor group and a pressure trend response mapping vector; Performing cross-dimensional mapping construction on the temperature gradient change parameter group and the traction speed fluctuation section distribution group to construct a temperature-speed response coupling feature group, performing point-to-region fusion processing on the pressure dynamic discrete factor group and the temperature section dynamic amplitude parameter group to obtain a pressure-temperature cross feature factor set, and performing a connected graph mapping structure construction on the speed steady-state average vector group and the pressure trend response mapping vector to obtain a voltage stabilization relationship map; Merging the temperature-speed response coupling feature group, the pressure-temperature cross feature factor set and the voltage stabilization relationship map to generate a multi-dimensional feature integration map, and performing dimension regularization and redundant factor pruning processing on the multi-dimensional feature integration map to extract a time-varying temperature feature parameter group, a speed stability feature parameter group and a pressure fluctuation feature parameter group.

3. The automatic control method of the hollow board extrusion production line according to claim 2, characterized in that, The steps of performing section segmentation processing and amplitude normalization analysis on the temperature data sequence to obtain a temperature section dynamic amplitude parameter group and a temperature gradient change parameter group, performing interval weighted difference operation and steady-state stability section identification processing on the speed change data sequence to obtain a traction speed fluctuation section distribution group and a speed steady-state average vector group, and performing joint analysis on the pressure response data sequence based on the time-domain response mean deviation and kurtosis coefficient to obtain a pressure dynamic discrete factor group and a pressure trend response mapping vector include: Continuously segment the temperature data sequence through a preset sliding time window to obtain multiple temperature time sections, perform maximum value normalization and interval difference amplitude calculation on the temperature data within each temperature time section to obtain a temperature dynamic amplitude index group; Perform adjacent section difference calculation on the temperature dynamic amplitude index group and archive it as a temperature change rate index, construct a temperature gradient trend curve based on the temperature change rate index, and extract the rising section and falling section of the temperature gradient trend curve to generate a temperature gradient change parameter group; Slide the window of the speed change data sequence at a fixed time granularity, perform weighted difference calculation on the speed values within each window to obtain a speed local fluctuation factor group, compare the speed local fluctuation factor group with the historical standard steady-state speed reference vector, and identify relatively stable sections and fluctuation sections to generate a speed steady-state average vector group and a traction speed fluctuation section distribution group; Apply the mean deviation calculation and asymmetric kurtosis measurement method to jointly process the pressure response data sequence, extract abnormal amplitude points and buffer response steady intervals, establish a distribution density map of the pressure dynamic response sequence based on the abnormal amplitude points, and calculate the discrete rate and deviation factor for different density sections of the distribution density map to generate a pressure dynamic discrete factor group; Perform linear regression modeling on the pressure change trend in the buffer response steady interval, compare the linear regression result with the pressure change trend data in the historical process state database, and extract the correlation relationship between the directionality and amplitude of the pressure change based on the comparison result to generate a pressure trend response mapping vector.

4. The automatic control method of the hollow board extrusion production line according to claim 1, characterized in that The steps of performing response collaborative analysis on the temperature time-varying characteristic parameter group and the speed stability characteristic parameter group to obtain a target temperature control section sequence, and performing time window sliding fusion operation on the pressure fluctuation characteristic parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt reflux rate adjustment sequence include: Extract temperature interval mutation points and section stability factors from the temperature time-varying characteristic parameter group to generate a temperature node group and a temperature steady-state distribution group, and perform response collaborative analysis on the temperature node group and the speed stability characteristic parameter group to obtain a temperature-speed coupling section map; Extract the traction rate sensitivity distribution map based on the temperature-speed coupling section map, perform node reconstruction processing on the traction rate sensitivity distribution map and the temperature steady-state distribution group to obtain the target temperature control section sequence, and perform time window sliding fusion operation on the target temperature control section sequence and the pressure fluctuation characteristic parameter group to obtain the press area dynamic response sequence and the feedback buffer section map; Perform asymmetric difference smoothing processing on the press area dynamic response sequence, perform sliding window fitting and regional weight backprojection on the smoothed press area dynamic response sequence and the feedback buffer section map to obtain the press area disturbance response fitting surface and the section abnormal offset set, and identify and perform hierarchical aggregation analysis on the main disturbance sources based on the intersection area of the press area disturbance response fitting surface and the section abnormal offset set to extract the local disturbance compensation factor group and the pressure extreme value distribution area group; Perform feature transformation and quantization on the local disturbance compensation factor group to obtain the pressure regulation control vector group, and convert the pressure extreme value distribution area group into a melt reflux rate adjustment sequence according to the non-linear mapping relationship between the pressure extreme value and the reflux rate.

5. The automatic control method of the hollow board extrusion production line according to claim 1, characterized in that, The step of inputting the pressure regulation control vector group and the melt reflux rate adjustment sequence into a preset high-order regulation response map to obtain the traction rate correction factor group and the extrusion speed fine-tuning vector includes: Construct a high-order regulation response map based on the historical data before regulation and the output quality response, where the high-order regulation response map includes a regulation mapping baseline group and a quality comparison node group; Map the pressure regulation control vector group to the regulation mapping baseline group to generate a baseline response displacement group and a regulation energy distribution vector, and perform cross-projection on the melt reflux rate adjustment sequence and the quality comparison node group to obtain a reflux quality adaptation factor group and a quality deviation judgment sequence; Perform fusion deviation calculation on the baseline response displacement group and the reflux quality adaptation factor group to generate a deviation correction projection matrix and a reflux influence section identification set, and extract the rate sensitivity weight matrix and the extrusion efficiency disturbance factor according to the regulation energy distribution vector and the quality deviation judgment sequence; Perform point position fusion analysis on the deviation correction projection matrix and the rate sensitivity weight matrix to obtain the traction rate correction factor group, and perform combined mapping on the reflux influence section identification set and the extrusion efficiency disturbance factor to generate the extrusion speed fine-tuning vector.

6. The automatic control method of the hollow board extrusion production line according to claim 1, characterized in that, The step of performing time series clustering analysis on the traction rate correction factor group to obtain an abnormal regulation identification sequence, and mapping the abnormal regulation identification sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw speed adjustment instruction sequence includes: Flatten the traction rate correction factor group along the time axis and resample the nodes to obtain a reconstructed time series vector group and a node time mapping group, perform multi-scale clustering processing on the reconstructed time series vector group using a sliding clustering window to obtain an abnormal fluctuation node set, and perform sequence repositioning on the abnormal fluctuation node set and the node time mapping group to generate an abnormal regulation identification sequence; Perform dimensional alignment and principal cause mapping on the abnormal adjustment recognition sequence and the extrusion speed fine-tuning vector to obtain a principal adjustment mapping group and a secondary perturbation response group; Use the principal adjustment mapping group to construct a framework for the initial traction speed correction instruction sequence, and fuse the secondary perturbation response group into the framework of the initial traction speed correction instruction sequence after linear compensation processing to generate a traction speed correction instruction sequence; Based on the characteristics of the working condition area, perform multi-segment weight analysis on the abnormal adjustment recognition sequence to obtain a map of the change trend of the screw speed. Input the map of the change trend of the screw speed into a preset correction rule node group to generate a screw speed adjustment instruction sequence.

7. The automatic control method of the hollow board extrusion production line according to claim 1, characterized in that, The step of performing coordinated control on the hollow plate extrusion production line according to the traction speed correction instruction sequence and the screw speed adjustment instruction sequence includes: Calculate an adjustment amplitude set of the traction execution unit according to the traction speed correction instruction sequence, convert the screw speed adjustment instruction sequence into a torque adjustment strategy set, perform coordinated comparison and analysis on the adjustment amplitude set and the torque adjustment strategy set, and generate a synchronous execution matching matrix and a feedback offset monitoring sequence; Set a correction group of PID parameters of the traction unit in the temperature control area according to the synchronous execution matching matrix, use the feedback offset monitoring sequence to adjust the temperature control weight group of the screw section, and perform section fusion matching on the temperature control weight group of the screw section and the correction group of PID parameters of the traction unit to generate a composite execution instruction group; Apply the composite execution instruction group to the extrusion main control system and the auxiliary linkage system of the hollow plate extrusion production line.

8. An automatic control system for a hollow board extrusion production line, characterized in that, Including: An acquisition module for acquiring real-time temperature data sequences, speed change data sequences, and pressure response data sequences during the hollow plate extrusion process, and performing multi-dimensional feature extraction to obtain a temperature time-varying feature parameter group, a speed stability feature parameter group, and a pressure fluctuation feature parameter group; An analysis module for performing response collaborative analysis on the temperature time-varying feature parameter group and the speed stability feature parameter group to obtain a target temperature control section sequence, and performing time window sliding fusion operation on the pressure fluctuation feature parameter group according to the target temperature control section sequence to generate a pressure regulation control vector group and a melt return rate adjustment sequence; An input module for inputting the pressure regulation control vector group and the melt return rate adjustment sequence into a preset high-order regulation response map to obtain a traction rate correction factor group and an extrusion speed fine-tuning vector; A mapping module for performing time series clustering analysis on the traction rate correction factor group to obtain an abnormal adjustment recognition sequence, and mapping the abnormal adjustment recognition sequence and the extrusion speed fine-tuning vector to obtain a traction speed correction instruction sequence and a screw speed adjustment instruction sequence; A control module for performing coordinated control on the hollow plate extrusion production line according to the traction speed correction instruction sequence and the screw speed adjustment instruction sequence.

Images