A method and system for controlling the production process of a puncture-resistant PE film

Abstract

This application relates to the field of process control technology, and provides a method and system for controlling the production process of puncture-resistant PE film. The method includes: acquiring acoustic signals generated during polymer melt flow and extracting characteristic information reflecting the rheological state of the polymer melt from the acoustic signals; acquiring real-time electrical parameters of each heating element in the extrusion die and determining the power output deviation of each heating element based on the real-time electrical parameters; and adjusting the screw speed of the extruder or the heating power of the die based on the characteristic information of the polymer melt rheological state and the power output deviation of each heating element to maintain the uniformity of the polymer melt flow field at the extrusion die outlet. This application can monitor the polymer melt rheological state and the power output of the die heating elements in real time, and dynamically adjust production parameters based on the monitoring results, thereby effectively solving the problem of non-uniform microstructure of the film caused by parameter fluctuations in the prior art, and significantly improving the performance stability of puncture-resistant polyethylene film.

Description

Technical Field

[0001] This application relates to the field of process control technology, and more specifically, to a method and system for controlling the production process of puncture-resistant PE film. Background Technology

[0002] In the daily production of PE film, even with standard-compliant polyethylene raw materials, there are often subtle differences in physical properties such as molecular weight distribution, melt index, and trace additive content between different batches. These differences cause slight but continuous fluctuations in the actual rheological behavior of the polymer melt within the extruder. For example, melt viscosity, sensitivity to shear rate, and flow resistance within the extrusion die can all undergo imperceptible changes. Simultaneously, the local heating elements in the extrusion die used for precise melt temperature control may experience slight aging due to long-term operation, leading to intermittent drift in their power output. This results in small and irregular temperature fluctuations in specific areas of the die lip around the set value.

[0003] These two independent, subtle fluctuations—namely, minute fluctuations in local temperature at the die lip and overall flowability changes caused by batch variations in raw materials—overlap at the extrusion die exit, resulting in a persistent and unpredictable slight non-uniformity in the transverse thickness distribution of the extruded PE melt as it leaves the die. This non-uniformity typically exceeds the detection threshold and response speed of conventional online thickness scanners, causing the system to display acceptable thickness data and fail to reveal potential quality issues. Summary of the Invention

[0004] This application provides a method and system for controlling the production process of puncture-resistant PE film to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, this application discloses a method for controlling the production process of puncture-resistant PE film, including:

[0007] Acoustic signals generated during polymer melt flow are acquired, and characteristic information reflecting the rheological state of the polymer melt is extracted from these acoustic signals.

[0008] The real-time electrical parameters of each heating element in the extrusion die are obtained, and the power output deviation of each heating element is determined based on these real-time electrical parameters.

[0009] Based on the characteristics of the polymer melt rheological state and the deviation of the power output of each heating element, the screw speed of the extruder or the heating power of the die head is adjusted to maintain the uniformity of the polymer melt flow field at the extrusion die outlet.

[0010] Secondly, this application also discloses a puncture-resistant PE film production process control system, which includes:

[0011] The acoustic signal acquisition module is used to acquire the acoustic signals generated during the flow of polymer melt and extract feature information reflecting the rheological state of polymer melt from the acoustic signals.

[0012] The electrical parameter acquisition module is used to acquire the real-time electrical parameters of each heating element in the extrusion die, and to determine the power output deviation of each heating element based on the real-time electrical parameters.

[0013] The parameter adjustment module is used to adjust the screw speed or die heating power of the extruder based on the characteristics of the polymer melt rheological state and the power output deviation of each heating element, so as to maintain the uniformity of the polymer melt flow field at the extrusion die outlet.

[0014] Compared with the prior art, this application has at least the following beneficial effects:

[0015] This application overcomes the shortcomings of existing technologies, such as difficulty in flexibly adapting to production changes and inability to effectively control the uniformity of film microstructure, significantly improving the puncture resistance stability of polyethylene film and ensuring the performance consistency of the product under harsh application scenarios. Attached Figure Description

[0016] Figure 1 A schematic flowchart of a puncture-resistant PE film production process control method provided in this application;

[0017] Figure 2 This is a schematic diagram of a puncture-resistant PE film production process control system provided in this application. Detailed Implementation

[0018] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0019] like Figure 1 As shown in the embodiments of this application, a method for controlling the production process of puncture-resistant PE film is proposed, including:

[0020] Acoustic signals generated during polymer melt flow are acquired, and characteristic information reflecting the rheological state of the polymer melt is extracted from the acoustic signals.

[0021] The real-time electrical parameters of each heating element in the extrusion die are obtained, and the power output deviation of each heating element is determined based on the real-time electrical parameters.

[0022] Based on the characteristics of the polymer melt rheological state and the deviation of the power output of each heating element, the screw speed of the extruder or the heating power of the die head is adjusted to maintain the uniformity of the polymer melt flow field at the extrusion die outlet.

[0023] This application effectively solves the problems of control lag and insufficient precision in traditional methods by real-time monitoring of the rheological state of the polymer melt and the deviation of the power output of the extrusion die heating element, and dynamically adjusting the screw speed of the extruder or the heating power of the die accordingly, thereby significantly improving the stability and consistency of the puncture resistance of PE film.

[0024] The rheological characteristics of the polymer melt mentioned in this application refer to data that reflect the rheological properties of the polymer melt during extrusion, such as viscosity, elasticity, and shear sensitivity, including melt viscosity, shear rate, shear stress, and normal stress difference. This information is crucial for evaluating the flow behavior of the melt within the die. The real-time electrical parameters of each heating element in the extrusion die typically include the voltage, current, and resistance of the heating element. These parameters allow for the calculation of the actual power output of the heating element, thereby determining whether there is a deviation in power output. The control method in this application aims to maintain the uniformity of the polymer melt flow field at the extrusion die exit. This means ensuring that the lateral thickness, temperature, and flow rate distribution of the polymer melt are as consistent as possible when it leaves the die, to avoid inhomogeneities in the microstructure of the film.

[0025] In practical implementation, the first step is to acquire the acoustic signals generated during the flow of the polymer melt and extract characteristic information reflecting the rheological state of the polymer melt. For example, highly sensitive acoustic sensors can be installed inside or near the extrusion die. These sensors can capture the weak sound waves generated by the polymer melt during flow, shearing, and mixing in real time. These acoustic signals contain rich information about the internal structure, viscosity, and flow state of the melt. For instance, when the melt viscosity changes, the frequency and amplitude of the frictional or shearing sounds generated in the flow channel will change accordingly. By performing signal processing techniques such as spectrum analysis, time-domain analysis, or wavelet transform on these raw acoustic signals, characteristic parameters highly correlated with the rheological state of the melt can be extracted, such as energy distribution, peak frequency, bandwidth, sound velocity attenuation, or acoustic impedance changes in specific frequency bands. These characteristic parameters can serve as characteristic information reflecting the rheological state of the polymer melt.

[0026] The system acquires real-time electrical parameters of each heating element in the extrusion die and determines the deviation of its power output based on these parameters. This can be achieved by equipping each heating element in the extrusion die with independent voltage and current sensors to monitor its operating voltage and current in real time. Using Ohm's law or power calculation formulas, the actual power output of each heating element can be calculated in real time. These real-time power outputs are then compared with preset ideal power values ​​to determine the deviation of each heating element's power output. For example, if the actual power output of a heating element is consistently lower than the set value, it indicates that the heating element may be aging or malfunctioning, causing its power output deviation. This deviation directly affects the temperature distribution inside the die, thus affecting the uniformity of the polymer melt flow field.

[0027] After acquiring the characteristic information of the polymer melt rheological state and the power output deviation of each heating element, the screw speed of the extruder or the heating power of the die is adjusted based on this information to maintain the uniformity of the polymer melt flow field at the extrusion die exit. For example, if acoustic signal analysis results show that the polymer melt viscosity is too high, it may lead to increased flow resistance inside the die. In this case, the shear heat generation can be reduced by appropriately decreasing the screw speed of the extruder, or the die heating power can be appropriately increased to reduce the melt viscosity, thereby restoring the uniformity of the flow field. If electrical parameter analysis results show that the power output of the heating element in a certain area is too low, resulting in a local temperature drop, the heating power in that area can be increased in a targeted manner to compensate for heat loss and ensure the uniformity of the die lip temperature. This adjustment can be based on a preset control strategy, or it can be based on fuzzy control, PID control, or more advanced machine learning algorithms. By establishing a mapping relationship between the rheological state, power deviation, screw speed, and heating power, precise closed-loop control can be achieved.

[0028] This application overcomes the limitations of single-parameter control in traditional PE film production processes by, for the first time, synergistically analyzing and controlling the real-time rheological state of the polymer melt and the power output deviation of the extrusion die heating element. Traditional methods often focus only on the thickness uniformity at the die exit, neglecting the underlying causes of non-uniformity, namely fluctuations in the internal rheological behavior of the melt and localized failures of the heating element. This application, by introducing acoustic signal analysis technology, can perceive the micro-rheological changes of the polymer melt inside the die in real time and non-invasively, reflecting the true flow state of the melt more sensitively than traditional pressure and temperature sensors. Simultaneously, precise monitoring and determination of the electrical parameters of the heating element enable timely detection and correction of localized temperature field non-uniformity within the die.

[0029] This application, by acquiring real-time information on the rheological state of the polymer melt and the power output deviation of each heating element, can detect potential non-uniformity risks earlier and intervene before they significantly affect film quality. For example, when a slight change in raw material batches causes minor fluctuations in melt viscosity, the acoustic signal acquisition module can immediately capture this change and extract the corresponding rheological characteristics. Simultaneously, if a heating element begins to show slight aging, the electrical parameter acquisition module can also detect a slight deviation in its power output in a timely manner. Based on this real-time information, the parameter adjustment module coordinates the screw speed of the extruder or the die heating power, thereby maintaining the uniformity of the polymer melt flow field at the extrusion die exit from the source. This proactive, real-time control strategy significantly improves the stability and consistency of the puncture resistance of PE films, effectively avoiding quality defects caused by microstructural inhomogeneity, and providing a more reliable and efficient solution for the production of high-end puncture-resistant PE films.

[0030] In some embodiments, the steps of acquiring the acoustic signal generated during polymer melt flow and extracting feature information reflecting the rheological state of the polymer melt from the acoustic signal include:

[0031] Periodically emit ultrasonic signals of known frequency and amplitude into the polymer melt;

[0032] Utilizing an acoustic sensor array to receive ultrasonic signals;

[0033] Analyze the received intensity, frequency response, and phase change of ultrasonic signals by each acoustic sensor in the acoustic sensor array;

[0034] The received intensity, frequency response, and phase change are compared with the response of each acoustic sensor in the initial healthy state to the ultrasonic signal to quantify the attenuation of the acoustic coupling characteristics of each acoustic sensor in the acoustic sensor array.

[0035] Based on the attenuation of the acoustic coupling characteristics of each acoustic sensor, the spectrum of the original acoustic signal of the polymer melt flow collected by the acoustic sensor array is reverse-corrected at each frequency point to eliminate the distortion effect of the drift of each acoustic sensor in the acoustic sensor array on the spectrum of the original acoustic signal of the polymer melt flow, thereby extracting the signal components caused by the real rheological changes of the polymer melt.

[0036] Based on the signal components extracted from the actual rheological changes of the polymer melt, characteristic information reflecting the rheological state of the polymer melt is obtained.

[0037] Specifically, periodically emitting ultrasonic signals of known frequency and amplitude into the polymer melt aims to provide a stable and controllable acoustic excitation source for probing the internal state of the polymer melt and evaluating the response characteristics of an acoustic sensor array. Ultrasonic signals are chosen as the detection medium due to their strong penetrating power and minimal disturbance to the melt flow field. Receiving ultrasonic signals using an acoustic sensor array involves synchronously acquiring the response of the ultrasonic signal after propagation in the polymer melt using multiple acoustic sensors arranged inside or outside the extrusion die. The use of acoustic sensor arrays provides richer spatial information and improves the robustness and accuracy of signal acquisition. In practical applications, analyzing the received intensity, frequency response, and phase change of the ultrasonic signal by each acoustic sensor in the array involves performing time-domain and frequency-domain analysis on the ultrasonic signal received by each sensor to obtain key parameters such as amplitude, frequency shift, and phase delay. These parameters directly reflect the characteristics of ultrasonic signal propagation in the melt and the response characteristics of the sensor itself.

[0038] The received intensity, frequency response, and phase change are compared with the responses of each acoustic sensor in the initial healthy state to the ultrasonic signal to quantify the attenuation of the acoustic coupling characteristics of each sensor in the acoustic sensor array. The responses in the initial healthy state can be the initial calibration data after the sensors are installed and debugged, serving as a benchmark. By comparison, performance drift or attenuation caused by aging, contamination, or damage of the sensors can be accurately identified. Therefore, based on the attenuation of the acoustic coupling characteristics of each acoustic sensor, the spectrum of the original acoustic signal of the polymer melt flow acquired by the acoustic sensor array is reverse-corrected frequency by frequency. The purpose is to eliminate the distortion effect of sensor drift on the original acoustic signal spectrum. Reverse correction can be understood as applying a compensation filter with the opposite attenuation characteristics to the sensor to correct the original spectrum, thereby restoring the signal components caused by the actual rheological changes of the polymer melt. Finally, based on the extracted signal components caused by the actual rheological changes of the polymer melt, characteristic information reflecting the rheological state of the polymer melt is obtained. These characteristics may include, but are not limited to, melt viscosity, elastic modulus, shear rate sensitivity, and potential fluid instability and defect precursor signals.

[0039] This application effectively solves the problem of signal distortion caused by sensor drift or attenuation in acoustic signal acquisition methods by introducing a periodic ultrasonic detection and a self-calibration mechanism for the acoustic sensor array. Specifically, by periodically emitting known ultrasonic signals and analyzing the response of the sensor array, the attenuation of the acoustic coupling characteristics of each acoustic sensor can be monitored and quantified in real time. It is precisely because the drift state of the sensors can be accurately obtained that subsequent frequency-point-by-frequency reverse correction of the original acoustic signal spectrum becomes possible. This correction process separates the sensor's own error from the actual melt flow signal, thereby ensuring that the extracted signal components truly reflect the rheological changes of the polymer melt, rather than sensor artifacts.

[0040] Assume that an acoustic sensor array consisting of five piezoelectric acoustic sensors is arranged in the flow channel inside the extrusion die. Before production starts, the initial health status calibration of the sensor array is first performed: ultrasonic pulse signals with a frequency of 1MHz and an amplitude of 10V are periodically emitted into the polymer melt, and the received intensity, frequency response, and phase change of the ultrasonic signal received by each sensor are recorded as reference data.

[0041] During production, the system automatically transmits the same ultrasonic pulse signal every 5 minutes and collects the response of each sensor in real time. For example, if the signal strength received by a sensor drops by 10% compared to the initial reference value and the phase drifts by 5 degrees, the system will calculate a reverse correction coefficient or compensation function based on these attenuation conditions.

[0042] When the acoustic sensor array acquires the raw acoustic signal of the polymer melt flow, this correction coefficient or compensation function is applied to the spectrum of the raw acoustic signal. Specifically, for each frequency point of the signal, the amplitude and phase are reversed according to a predetermined attenuation. For example, if a frequency point appears to have low energy in the raw signal due to sensor attenuation, the correction process will boost its energy to the true level. Through this frequency-by-frequency reverse correction, the spectral distortion caused by sensor drift can be effectively eliminated, resulting in a pure acoustic signal spectrum that truly reflects the rheological state of the polymer melt.

[0043] Ultimately, specific features are extracted from the corrected spectrum. For example, analyzing energy distribution changes in specific frequency bands can indicate fluctuations in melt viscosity, or monitoring the presence of high-frequency components can provide early warning of fluid instability. These precise rheological features are then used to guide adjustments to the extruder screw speed or die heating power to ensure the stability of the film production process and product quality.

[0044] In some embodiments, the steps of acquiring the acoustic signal generated during polymer melt flow and extracting feature information reflecting the rheological state of the polymer melt from the acoustic signal include:

[0045] Acquire the structural vibration signal of the extrusion die body;

[0046] Analyze structural vibration signals and extract vibration characteristics related to the operating frequency of external mechanical components;

[0047] Acquire the spectrum of the raw acoustic signal of polymer melt flow collected by the acoustic sensor array;

[0048] By comparing the spectrum and vibration characteristics of the original acoustic signal, the noise component caused by external mechanical vibration in the original acoustic signal can be identified.

[0049] The noise component is subtracted from the spectrum of the original acoustic signal to obtain the corrected acoustic signal spectrum of the polymer melt flow.

[0050] Feature information reflecting the rheological state of polymer melt is extracted from the acoustic signal spectrum of the corrected polymer melt flow.

[0051] Specifically, acquiring the structural vibration signal of the extrusion die body refers to monitoring the mechanical vibration of the die body in real time by installing vibration sensors, such as accelerometers or piezoelectric sensors, on the die body. The purpose is to capture the vibration energy generated by internal or external mechanical components of the extruder (such as motors, gearboxes, cooling fans, etc.) that may propagate through the die structure. Analyzing the structural vibration signal and extracting vibration characteristics related to the operating frequencies of external mechanical components can be understood as performing spectral analysis on the acquired structural vibration signal. For example, using Fast Fourier Transform (FFT), the signal's frequency components with significant energy are identified, and these frequency components are compared with known or preset operating frequencies of external mechanical components to determine which vibration characteristics are caused by these components. The aim is to accurately characterize the frequency characteristics of noise sources.

[0052] Obtaining the spectrum of the raw acoustic signal from the polymer melt flow acquired by the acoustic sensor array involves time-frequency conversion of the raw acoustic signal collected by the acoustic sensor array during the polymer melt flow process to obtain its energy distribution at different frequencies. The purpose is to provide basic data for subsequent noise identification and elimination. Specifically, comparing the spectrum of the raw acoustic signal with vibration characteristics to identify the noise component caused by external mechanical vibration in the raw acoustic signal involves cross-analysis of the spectrum of the raw acoustic signal with previously extracted structural vibration characteristics. For example, through frequency matching and correlation analysis, the frequency components in the spectrum of the raw acoustic signal corresponding to the external mechanical vibration characteristics are identified; these components are then determined to be noise. The aim is to accurately distinguish between the melt's own acoustic signal and external noise.

[0053] Subtracting noise components from the spectrum of the original acoustic signal yields the corrected acoustic signal spectrum of the polymer melt flow. Digital filtering techniques, such as notch filters or adaptive noise cancellation algorithms, can be used to remove identified noise components from the original acoustic signal spectrum, resulting in a cleaner spectrum that reflects the true flow of the polymer melt. The aim is to eliminate noise interference and restore the true signal. Therefore, extracting characteristic information reflecting the rheological state of the polymer melt from the corrected acoustic signal spectrum refers to extracting acoustic features related to the rheological state of the polymer melt (such as viscosity, shear rate, molecular chain orientation, etc.) from the corrected spectrum after effective noise removal. These features include energy, peak frequency, bandwidth, or harmonic distribution in specific frequency bands. The goal is to obtain accurate rheological state data.

[0054] This application ensures that the extracted rheological state characteristics more accurately reflect the actual internal state of the melt by actively identifying and eliminating interference from external mechanical vibrations on the acoustic signals of polymer melt flow. Specifically, by acquiring the structural vibration signals of the extrusion die body, the vibration modes and frequency characteristics generated by external mechanical components (such as extruder motors, gearboxes, etc.) can be accurately captured. Subsequently, by comparing these vibration characteristics with the original acoustic signal spectrum acquired by the acoustic sensor array, noise components caused by external mechanical vibrations can be effectively identified and separated. By subtracting these noise components from the original acoustic signal spectrum, a corrected and purer acoustic signal spectrum of polymer melt flow can be obtained, thereby avoiding interference from noise in subsequent rheological state characteristic extraction. Thus, more reliable polymer melt rheological state characteristics can be extracted based on more accurate acoustic signals, providing a solid data foundation for subsequent process parameter adjustments.

[0055] In some embodiments, the steps of acquiring the acoustic signal generated during polymer melt flow and extracting feature information reflecting the rheological state of the polymer melt from the acoustic signal include:

[0056] Multiple optical sensors are arranged in the internal flow channel of the extrusion die to collect optical signals of the polymer melt at different depths and lateral positions.

[0057] The original acoustic signal of polymer melt flow acquired by the acoustic sensor array is subjected to spectral decomposition to extract the energy distribution, peak frequency and bandwidth of the original acoustic signal in different frequency bands as acoustic feature information;

[0058] The optical signals acquired by the optical sensor are processed to extract the scattering intensity, absorptivity or transmittance of the optical signals under different wavelengths or polarization states as optical feature information.

[0059] Correlation analysis of acoustic and optical feature information;

[0060] Based on the correlation analysis results, acoustic feature patterns corresponding to specific non-uniformity types in acoustic signals, such as differences in molecular chain orientation, local density fluctuations, or uneven dispersion of additives, are identified.

[0061] From the acoustic signal spectrum of the corrected polymer melt flow, acoustic feature patterns corresponding to specific non-uniformity types are extracted as feature information reflecting the rheological state of the polymer melt.

[0062] Specifically, multiple optical sensors are arranged within the flow channels of the extrusion die to acquire, in real time, the optical properties of the polymer melt at different spatial locations (depth and lateral) using non-contact or micro-contact methods. These optical sensors can be fiber optic probes, CCD cameras, or spectrometers, capable of capturing the scattering, absorption, or transmission behavior of the melt under illumination. These behaviors are closely related to the melt's microstructure, component distribution, and flow state. The raw acoustic signals of the polymer melt flow acquired by the acoustic sensor array are then subjected to spectral decomposition using methods such as Fast Fourier Transform to obtain their energy distribution, peak frequency, and bandwidth at different frequency bands. These parameters are fundamental characteristics of the acoustic signals and can preliminarily reflect the macroscopic flow state and internal disturbances of the melt. In practical applications, processing the optical signals acquired by the optical sensors involves analyzing changes in scattering intensity, absorptivity, or transmittance at different wavelengths, as well as variations in polarization state, to obtain the melt's optical characteristics. For example, differences in molecular chain orientation may lead to variations in polarized light scattering; local density fluctuations may affect the scattering intensity; and uneven additive dispersion may result in different absorption or transmission characteristics at specific wavelengths. Furthermore, correlation analysis is performed on acoustic and optical feature information to establish the intrinsic relationship between acoustic and optical signals. This can be achieved through machine learning algorithms or statistical methods to discover the synergistic variation patterns of acoustic and optical features under different rheological states. Based on the correlation analysis results, acoustic feature patterns corresponding to specific inhomogeneities such as differences in molecular chain orientation, local density fluctuations, or uneven additive dispersion are identified in the acoustic signal. This means that the acoustic signal can be calibrated or interpreted using the more direct microstructural information provided by the optical signal, thereby associating ambiguous acoustic features with specific physical inhomogeneities. Finally, acoustic feature patterns corresponding to specific inhomogeneities are extracted from the corrected acoustic signal spectrum of the polymer melt flow as feature information reflecting the rheological state of the polymer melt. This step ensures that the extracted rheological state feature information is not only denoised but also has clear physical meaning, directly pointing to specific inhomogeneities within the melt.

[0063] This application addresses the challenge of accurately distinguishing various specific types of inhomogeneities within polymer melts by introducing optical sensors and combining them with acoustic signal correlation analysis. Specifically, while acoustic signals are sensitive to macroscopic rheological behaviors such as pressure fluctuations and shear stress changes within the melt, their ability to directly characterize microstructural changes is limited. Optical signals, particularly through analysis of scattering intensity, absorptivity or transmittance, and polarization state, can more directly reflect microstructural information such as polymer molecular chain orientation, local density variations, and additive dispersion uniformity. By correlating these two signals based on different physical principles, a mapping relationship between acoustic and optical features can be established. For example, when optical signals indicate specific changes in molecular chain orientation, correlation analysis can identify corresponding specific frequencies or energy distribution patterns in the acoustic signal. This multimodal data fusion and correlation analysis allows previously ambiguous features in acoustic signals to be given clear physical meaning, enabling precise identification of whether the rheological anomaly is caused by differences in molecular chain orientation, local density fluctuations, or uneven additive dispersion.

[0064] In the extrusion production of puncture-resistant polyethylene film, multiple miniature fiber optic probes are arranged as optical sensors within the flow channel of the extrusion die. These probes can acquire real-time information on the intensity and polarization state of transmitted light at different locations in the melt. Simultaneously, an acoustic sensor array continuously acquires the raw acoustic signals of the melt flow. First, the raw acoustic signals are spectrally decomposed to extract acoustic features such as energy distribution, peak frequency, and bandwidth. Second, the optical signals acquired by the fiber optic probes are processed. For example, local density fluctuations can be assessed by analyzing changes in transmitted light intensity at specific wavelengths, or the degree of nematic orientation of molecular chains can be assessed by changes in polarization state, thereby extracting optical feature information. Next, this acoustic and optical feature information is input into a pre-trained deep learning model for correlation analysis. During training, this model has learned the co-variation patterns of acoustic and optical signals under different molecular chain orientation differences, local density fluctuations, or uneven additive dispersion. For example, when the model detects that the optical signal indicates a significant increase in the degree of molecular chain orientation in a local region of the melt, it simultaneously identifies a specific high-frequency vibration mode in the acoustic signal that is highly correlated with it. Finally, based on the results of this correlation analysis, acoustic feature patterns corresponding to the specific non-uniformity type of molecular chain orientation difference were precisely extracted from the acoustic signal spectrum after external mechanical vibration noise correction. These precisely identified feature patterns were then used to guide the adjustment of the extruder screw speed or die heating power to eliminate or mitigate molecular chain orientation non-uniformity, thereby maintaining the uniformity of the polymer melt flow field at the extrusion die exit and ensuring the puncture resistance of the final film.

[0065] In some embodiments, the steps of obtaining the real-time electrical parameters of each heating element in the extrusion die and determining the power output deviation of each heating element based on the real-time electrical parameters include:

[0066] A known and stable reference electrical signal is periodically applied to the electrical parameter sensors of each heating element;

[0067] The reference electrical signal is received by the electrical parameter sensors of each heating element, and the response of each heating element electrical parameter sensor to the reference electrical signal is recorded;

[0068] The response of each heating element electrical parameter sensor to the reference electrical signal is compared with the response of each heating element electrical parameter sensor to the reference electrical signal in the initial healthy state, so as to quantify the measurement drift or fault of each heating element electrical parameter sensor itself.

[0069] When determining the power output deviation of each heating element, the real-time electrical parameters are corrected by combining the measurement drift or fault of the sensor itself, thereby distinguishing between the power output deviation of the heating element itself and the sensor measurement error.

[0070] Specifically, periodically applying a known and stable reference electrical signal to the electrical parameter sensors of each heating element means inputting a preset, stable electrical signal to each electrical parameter sensor at a specific time point in the production process or at a fixed frequency. The purpose is to detect the sensor's own response characteristics and evaluate its operating status.

[0071] Utilizing electrical parameter sensors of each heating element to receive reference electrical signals and recording the responses of each sensor to these signals refers to the process by which the sensors, upon receiving the reference electrical signal, convert it into a processable electrical signal output and record the data. The purpose is to obtain the actual output performance of the sensors under known input conditions.

[0072] The response of each heating element's electrical parameter sensor to a reference electrical signal is compared with the response of each heating element's electrical parameter sensor to the reference electrical signal under initial healthy conditions to quantify the measurement drift or fault condition of each heating element's electrical parameter sensor. The response under initial healthy conditions can be a standard response curve or value recorded during sensor factory calibration or the initial period of use. By comparing these values, it is possible to identify whether the sensor has experienced performance degradation, drift, or complete failure. The purpose is to accurately assess the reliability of the sensor itself.

[0073] When determining the power output deviation of each heating element, the real-time electrical parameters are corrected by considering the measurement drift or malfunction of the sensors for each heating element's electrical parameters. This distinguishes between the power output deviation of the heating element itself and sensor measurement errors. This means that when calculating the actual power output deviation of the heating element, the error component caused by sensor drift or malfunction is first subtracted or corrected from the real-time measured electrical parameters. The purpose is to ensure that the determined power output deviation reflects the true performance change of the heating element, rather than a misleading observation from the sensor.

[0074] This application addresses the problem of inaccurate power output deviation judgments caused by sensor measurement errors by introducing an evaluation and correction mechanism for the sensor's own electrical parameter state. Specifically, by periodically applying a reference electrical signal and comparing the sensor response with its initial health state, the sensor's measurement drift or fault condition can be quantified. This self-diagnostic mechanism allows the system to understand the sensor's health status in real time. When determining a power output deviation of the heating element, the real-time electrical parameters are combined with the quantified sensor measurement drift or fault condition for correction. It is precisely because of this correction that the system can effectively distinguish the true power output deviation of the heating element from the sensor's own measurement error, thereby avoiding misjudgments and improper control caused by sensor errors.

[0075] In some embodiments, the step of correcting the real-time electrical parameters by combining the measurement drift or malfunction of the electrical parameter sensor of each heating element when determining the power output deviation of each heating element, thereby distinguishing between the power output deviation of the heating element itself and the sensor measurement error, includes:

[0076] Obtain local temperature distribution information of each heating element inside the mold head;

[0077] Obtain local flow velocity information of the polymer melt inside the die head;

[0078] Correlation analysis is performed between local temperature distribution information, local flow velocity information and real-time electrical parameters to identify the difference patterns between heating element power output deviation and sensor measurement error in temperature distribution and melt flow velocity.

[0079] When determining the power output deviation of each heating element, the real-time electrical parameters are corrected by combining the measurement drift or fault condition of the sensor itself and the difference mode of the electrical parameters of each heating element, thereby distinguishing the power output deviation of the heating element itself from the sensor measurement error.

[0080] Specifically, obtaining local temperature distribution information of each heating element inside the die head refers to monitoring the temperature field changes in the area surrounding each heating element in real time by arranging multiple temperature sensors at key locations inside the die head. These temperature sensors can be thermocouples, resistance temperature detectors (RTDs), or infrared temperature sensors, and their purpose is to provide direct thermal feedback on the operating status of the heating elements. Obtaining local flow velocity information of the polymer melt inside the die head can be understood as acquiring the flow velocity and streamline distribution of the polymer melt in different regions by placing micro-flow velocity sensors inside the die head flow channels or using image processing-based particle tracing technology. This flow velocity information is crucial for understanding the shear, stretching, and residence time distribution of the melt within the die head, and its purpose is to reflect the dynamic response of the melt's heating and flow state.

[0081] Correlation analysis of local temperature distribution information, local flow velocity information, and real-time electrical parameters refers to the fusion and pattern recognition of data from different sources by establishing a multivariate data model, such as using machine learning algorithms (e.g., support vector machines, neural networks) or statistical regression analysis. The aim is to identify specific and distinguishable patterns that appear in the local temperature and melt flow velocity fields when a heating element experiences power output deviation; however, the patterns may differ when sensor measurement errors occur. For example, a heating element with a decrease in actual power will cause a significant drop in its surrounding temperature and may alter the local melt flow velocity; while a temperature sensor with only a low measurement value may not cause significant changes in the actual temperature and melt flow velocity fields, or its change pattern may differ from that caused by the actual power deviation. Furthermore, when determining the power output deviation of each heating element, the real-time electrical parameters are corrected by combining the sensor's own measurement drift or fault conditions, as well as the difference patterns. This means that after initial correction of the sensor's own errors, a secondary correction is performed using the difference patterns obtained through correlation analysis. This allows for a more precise distinction between deviations in the heating element's own power output and sensor measurement errors, ensuring more accurate diagnosis and control of the mold head heating system.

[0082] This application, by introducing local temperature distribution information and local flow velocity information of the polymer melt inside the die, can more comprehensively and multidimensionally characterize the physical state inside the die. It is precisely because deviations in the power output of the heating element and measurement errors in the electrical parameter sensors produce different physical response modes in the temperature field and melt flow field inside the die that this application can identify these differential modes through correlation analysis of this multi-source information. For example, a decrease in the actual power of a heating element will directly lead to a decrease in the temperature of its surrounding area and may affect the viscosity of the nearby melt, thereby changing the local flow velocity; while a deviation in the measurement value of the electrical parameter sensor alone may not cause such a significant or specific change in the actual temperature distribution and melt flow velocity distribution inside the die. Through this multi-physics coupling analysis, the system can understand the true state inside the die at a deeper level, thereby avoiding misjudgments that may arise from relying solely on a single electrical parameter or sensor calibration information, and effectively distinguishing between actual heating element failures and sensor measurement errors.

[0083] In some embodiments, the step of obtaining the local temperature distribution information of each heating element inside the die head includes:

[0084] A known and stable thermal pulse signal is periodically applied to a local temperature sensor;

[0085] A local temperature sensor is used to receive thermal pulse signals, and the response of the local temperature sensor to the thermal pulse signals is recorded.

[0086] The response of the local temperature sensor to the thermal pulse signal is compared with the response of the local temperature sensor to the thermal pulse signal in its initial healthy state to quantify the measurement drift or failure of the local temperature sensor itself.

[0087] By combining the measurement drift or malfunction of the local temperature sensor itself, the local temperature distribution information is corrected, thereby distinguishing the true local temperature distribution of the heating element from the sensor measurement error.

[0088] Specifically, periodically applying a known and stable thermal pulse signal to a local temperature sensor refers to applying a brief and controllable heat input to the area near each local temperature sensor at preset time intervals, using a miniature heater or laser pulse. The frequency and amplitude of this thermal pulse signal are predetermined and remain stable throughout the calibration process to ensure the repeatability and accuracy of the calibration results. The purpose is to evaluate the sensor's operational status by introducing a controllable external heat source to stimulate its response to temperature changes.

[0089] By using a local temperature sensor to receive thermal pulse signals and recording the sensor's response to these signals, it can be understood that after a thermal pulse signal is applied, the local temperature sensor detects a rapid rise and fall in temperature and converts this into an electrical signal output. These electrical signals (such as changes in voltage, resistance, or current) are recorded in real time by a data acquisition system, forming a time-series response curve. This response curve contains information such as the sensor's sensitivity to thermal pulses, response speed, and recovery characteristics.

[0090] By comparing the response of a local temperature sensor to a thermal pulse signal with its response under initial health conditions, the measurement drift or malfunction of the local temperature sensor can be quantified. The initial health response refers to the typical response pattern of the sensor to the same thermal pulse signal during factory calibration or initial installation and confirmation of normal operation. By comparing the differences between the current response and the initial response—such as changes in peak amplitude, rise / fall time, settling time, or overall curve shape—the amount of measurement drift or the presence of a malfunction can be accurately calculated. For example, a decreased response amplitude may indicate decreased sensor sensitivity, while a prolonged response time may indicate a sluggish sensor response.

[0091] By incorporating the measurement drift or malfunction of the local temperature sensor, the local temperature distribution information is corrected to distinguish between the true local temperature distribution of the heating element and the sensor measurement error. This means that when acquiring the actual local temperature distribution information inside the mold head, the previously quantified sensor drift or malfunction data is used to compensate or correct the real-time temperature values ​​measured by the sensor. For example, if a sensor has a drift of +0.5℃, all its real-time measurements will be subtracted by 0.5℃ to obtain a more accurate local temperature. The purpose is to ensure that the obtained local temperature distribution information accurately reflects the actual operating state of the heating element, rather than the sensor's own error.

[0092] This application solves the problem of inaccurate temperature distribution information caused by measurement drift or malfunction of local temperature sensors by introducing periodic thermal pulse signals for self-diagnosis and calibration. By applying a known and stable thermal pulse signal to each local temperature sensor and comparing its response with that in its initial healthy state, the measurement drift or malfunction of the sensor itself can be accurately quantified. This quantification process allows the sensor's own errors to be identified and separated. Based on this, by applying these quantified errors to correct the real-time measured local temperature distribution information, the interference of the sensor's own errors on the true temperature distribution is effectively eliminated. Therefore, it is possible to more accurately distinguish between the true local temperature distribution of the heating element and the sensor measurement error, ensuring the reliability of subsequent judgments on deviations in the heating element's power output.

[0093] The following is a specific example to illustrate this.

[0094] Assume multiple local temperature sensors are arranged inside the extrusion die to monitor the temperature distribution of the heating element. To ensure the accuracy of these sensors, the system performs a calibration procedure periodically. Specifically, a miniature heater is integrated near each local temperature sensor. During calibration, this miniature heater applies a 1-watt thermal pulse signal lasting 5 seconds to its corresponding local temperature sensor. Upon receiving this thermal pulse, the local temperature sensor's temperature reading rises rapidly and gradually recovers after the thermal pulse ends. The system records the sensor's response curve during the thermal pulse, including the peak temperature, the time to reach the peak temperature, and the time to recover to the reference temperature.

[0095] For example, a local temperature sensor, in its initial healthy state, responds to a thermal pulse with a peak temperature increase of 10°C and a recovery time of 10 seconds. After a period of operation, when the system applies the same thermal pulse again, the sensor's current response is a peak temperature increase of only 8°C, and the recovery time is extended to 15 seconds. By comparing these two response curves, the system can calculate that the sensor exhibits a 2°C measurement drift (i.e., its readings are generally 2°C lower) and signs of sluggish response. In subsequent real-time temperature monitoring, all real-time temperature readings of this sensor will be corrected; for example, if its real-time reading is 200°C, the actual temperature will be corrected to 202°C. In this way, even if the sensor itself has drift or malfunction, the system can obtain information closer to the true local temperature distribution, thus more accurately determining whether the heating element truly has a power output deviation, avoiding unnecessary or incorrect adjustments to the heating power due to sensor errors.

[0096] In some embodiments, the step of obtaining local flow velocity information of the polymer melt inside the die head includes:

[0097] A known and stable fluid pulse signal is periodically applied to the polymer melt flow rate sensor;

[0098] A polymer melt flow rate sensor is used to receive fluid pulse signals and to record the response of the polymer melt flow rate sensor to the fluid pulse signals.

[0099] The response of the polymer melt flow rate sensor to the fluid pulse signal is compared with the response of the polymer melt flow rate sensor to the fluid pulse signal in the initial healthy state in order to quantify the measurement drift or wear of the polymer melt flow rate sensor itself.

[0100] By combining the measurement drift or wear of the polymer melt flow rate sensor itself, the local flow rate information is corrected, thereby distinguishing the true local flow rate of the melt from the sensor measurement error.

[0101] Specifically, periodically applying a known and stable fluid pulse signal to a polymer melt flow rate sensor refers to injecting or extracting a small amount of melt into or from the polymer melt flow channel region where the sensor is located at preset time intervals using a specific excitation device, such as a micro-pump or piezoelectric actuator, thus creating a controllable fluid disturbance. The frequency and amplitude of this fluid pulse signal are predetermined, and its purpose is to simulate the fluid changes that the sensor may encounter under normal operating conditions, and to use this as a benchmark to evaluate the sensor's response characteristics.

[0102] By using a polymer melt flow rate sensor to receive fluid pulse signals and recording the sensor's response to these signals, it can be understood that upon receiving the fluid pulse signal, the sensor generates a corresponding electrical signal output. These output signals contain information such as the intensity and duration of the fluid pulse, as well as the sensor's dynamic response to the pulse. This response data is acquired and stored in real time, serving as the basis for subsequent analysis.

[0103] Comparing the response of a polymer melt flow rate sensor to a fluid pulse signal with its response under initial healthy conditions quantifies the sensor's measurement drift or wear. This involves comparing the currently acquired sensor response data with the ideal response curve recorded during factory calibration or initial installation. Various signal processing techniques, such as correlation analysis, spectral analysis, or eigenvector matching, can be employed to identify any deviations in the sensor response, such as signal amplitude attenuation, response time delay, or increased noise levels. These deviations can be quantified as the degree of measurement drift or wear of the sensor.

[0104] By incorporating the measurement drift or wear of the polymer melt flow rate sensor, local flow rate information is corrected to distinguish between the true local flow rate of the melt and the sensor measurement error. This involves adjusting the measured value after obtaining the current local flow rate measurement from the sensor, based on the previously quantified sensor measurement drift or wear, using a corresponding correction algorithm. For example, if the sensor exhibits linear drift, it can be corrected by subtracting an offset or multiplying by a correction coefficient; if a nonlinear response exists, a lookup table or nonlinear model can be used for correction. This correction effectively eliminates the influence of sensor defects on the measurement results, thereby obtaining more accurate local flow rate information for the polymer melt.

[0105] This application effectively addresses the impact of sensor drift or wear on the accuracy of local flow velocity information by introducing a periodic evaluation and correction mechanism for the state of the polymer melt flow velocity sensor itself. Because the sensor's own drift or wear is quantified and used to correct real-time measurements, the acquired local flow velocity information more accurately reflects the actual flow state of the polymer melt inside the die. This correction mechanism ensures that the local flow velocity data relied upon for distinguishing between heating element power output deviations and electrical parameter sensor measurement errors is reliable, thus avoiding misjudgments or inaccurate corrections caused by errors in the flow velocity sensor itself.

[0106] The following is a specific example to illustrate this.

[0107] Suppose that during the production of puncture-resistant polyethylene film, a polymer melt flow rate sensor located inside the extrusion die experiences a slight attenuation in its measurement response due to wear of its internal sensing element after several months of continuous operation. Specifically, when the actual melt flow rate is 10 cm / s, the sensor reports a flow rate of 9.5 cm / s, exhibiting a negative drift of 0.5 cm / s.

[0108] To correct for this error, the control system periodically applies a known and stable fluid pulse signal to the flow channel region where the flow velocity sensor is located. For example, a pulse lasting 1 second with a peak flow velocity of 12 cm / s is generated by a miniature piezoelectric pump. The system records the sensor's response to this pulse and compares it with the sensor's response to the same pulse in its initial healthy state. Through signal processing, such as calculating the integral area or peak amplitude of the response curve, the system quantifies that the current sensor has a negative measurement drift of 0.5 cm / s.

[0109] In subsequent real-time production, when the flow rate sensor reports a local flow rate of 9.5 cm / s, the control system corrects this measurement by incorporating a quantified negative drift of 0.5 cm / s, arriving at a true local flow rate of 10 cm / s. This corrected local flow rate information is then used for correlation analysis with local temperature distribution information and real-time electrical parameters. This allows for a more accurate distinction between the actual power output deviation of the heating element and the measurement error of the electrical parameter sensor, ensuring that adjustments to the extrusion die heating power or screw speed are based on precise melt flow field data. Ultimately, this maintains the stability of the film production process and product quality.

[0110] like Figure 2 As shown in the embodiments, this application also discloses a puncture-resistant PE film production process control system, including:

[0111] Acoustic signal acquisition module 1 is used to acquire acoustic signals generated during polymer melt flow and extract characteristic information reflecting the rheological state of polymer melt from the acoustic signals.

[0112] Electrical parameter acquisition module 2 is used to acquire the real-time electrical parameters of each heating element in the extrusion die, and determine the power output deviation of each heating element based on the real-time electrical parameters.

[0113] The parameter adjustment module 3 is used to adjust the screw speed or die heating power of the extruder according to the characteristic information of the rheological state of the polymer melt and the deviation of the power output of each heating element, so as to maintain the uniformity of the polymer melt flow field at the extrusion die outlet.

[0114] The system provided in this application enables intelligent, closed-loop control of the polyethylene film production process, effectively solving the problem that existing production lines are unable to adapt to differences in raw materials and equipment aging, and significantly improving the puncture resistance and production stability of the film.

[0115] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for controlling the production process of puncture-resistant PE film, characterized in that, include: Acoustic signals generated during polymer melt flow are acquired, and characteristic information reflecting the rheological state of the polymer melt is extracted from the acoustic signals. The real-time electrical parameters of each heating element in the extrusion die are obtained, and the power output deviation of each heating element is determined based on the real-time electrical parameters. Based on the characteristics of the polymer melt rheological state and the deviation of the power output of each heating element, the screw speed of the extruder or the heating power of the die head is adjusted to maintain the uniformity of the polymer melt flow field at the extrusion die outlet.

2. The method for controlling the production process of puncture-resistant PE film according to claim 1, characterized in that, The steps of acquiring the acoustic signal generated during polymer melt flow and extracting feature information reflecting the rheological state of the polymer melt from the acoustic signal include: Periodically emit ultrasonic signals of known frequency and amplitude into the polymer melt; Utilizing an acoustic sensor array to receive ultrasonic signals; Analyze the received intensity, frequency response, and phase change of ultrasonic signals by each acoustic sensor in the acoustic sensor array; The received intensity, frequency response, and phase change are compared with the response of each acoustic sensor in the initial healthy state to the ultrasonic signal to quantify the attenuation of the acoustic coupling characteristics of each acoustic sensor in the acoustic sensor array. Based on the attenuation of the acoustic coupling characteristics of each acoustic sensor, the spectrum of the original acoustic signal of the polymer melt flow collected by the acoustic sensor array is reverse-corrected at each frequency point, thereby extracting the signal components caused by the real rheological changes of the polymer melt. Based on the signal components extracted from the actual rheological changes of the polymer melt, characteristic information reflecting the rheological state of the polymer melt is obtained.

3. The method for controlling the production process of puncture-resistant PE film according to claim 1, characterized in that, The steps of acquiring the acoustic signal generated during polymer melt flow and extracting feature information reflecting the rheological state of the polymer melt from the acoustic signal include: Acquire the structural vibration signal of the extrusion die body; Analyze structural vibration signals and extract vibration characteristics related to the operating frequency of external mechanical components; Acquire the spectrum of the raw acoustic signal of polymer melt flow collected by the acoustic sensor array; By comparing the spectrum and vibration characteristics of the original acoustic signal, the noise component caused by external mechanical vibration in the original acoustic signal can be identified. The noise component is subtracted from the spectrum of the original acoustic signal to obtain the corrected acoustic signal spectrum of the polymer melt flow. Feature information reflecting the rheological state of polymer melt is extracted from the acoustic signal spectrum of the corrected polymer melt flow.

4. The method for controlling the production process of puncture-resistant PE film according to claim 3, characterized in that, The steps of acquiring the acoustic signal generated during polymer melt flow and extracting feature information reflecting the rheological state of the polymer melt from the acoustic signal include: Multiple optical sensors are arranged in the internal flow channel of the extrusion die to collect optical signals of the polymer melt at different depths and lateral positions. The original acoustic signal of polymer melt flow acquired by the acoustic sensor array is subjected to spectral decomposition to extract the energy distribution, peak frequency and bandwidth of the original acoustic signal in different frequency bands as acoustic feature information; The optical signals acquired by the optical sensor are processed to extract the scattering intensity, absorptivity or transmittance of the optical signals under different wavelengths or polarization states as optical feature information. Correlation analysis of acoustic and optical feature information; Based on the correlation analysis results, acoustic feature patterns in acoustic signals corresponding to specific types of inhomogeneities are identified; From the acoustic signal spectrum of the corrected polymer melt flow, acoustic feature patterns corresponding to specific non-uniformity types are extracted as feature information reflecting the rheological state of the polymer melt.

5. The method for controlling the production process of puncture-resistant PE film according to claim 1, characterized in that, The steps of acquiring the real-time electrical parameters of each heating element in the extrusion die and determining the power output deviation of each heating element based on the real-time electrical parameters include: A known and stable reference electrical signal is periodically applied to the electrical parameter sensors of each heating element; The reference electrical signal is received by the electrical parameter sensors of each heating element, and the response of each heating element electrical parameter sensor to the reference electrical signal is recorded; The response of each heating element electrical parameter sensor to the reference electrical signal is compared with the response of each heating element electrical parameter sensor to the reference electrical signal in the initial healthy state, so as to quantify the measurement drift or fault of each heating element electrical parameter sensor itself. When determining the power output deviation of each heating element, the real-time electrical parameters are corrected by combining the measurement drift or fault of the sensor itself, thereby distinguishing between the power output deviation of the heating element itself and the sensor measurement error.

6. The method for controlling the production process of puncture-resistant PE film according to claim 5, characterized in that, The step of determining the power output deviation of each heating element, and correcting the real-time electrical parameters by considering the measurement drift or malfunction of the electrical parameter sensors of each heating element, thereby distinguishing between the power output deviation of the heating element itself and the sensor measurement error, includes: Obtain local temperature distribution information of each heating element inside the mold head; Obtain local flow velocity information of the polymer melt inside the die head; Correlation analysis is performed between local temperature distribution information, local flow velocity information and real-time electrical parameters to identify the difference patterns between heating element power output deviation and sensor measurement error in temperature distribution and melt flow velocity. When determining the power output deviation of each heating element, the real-time electrical parameters are corrected by combining the measurement drift or fault condition of the sensor itself and the difference mode of the electrical parameters of each heating element, thereby distinguishing the power output deviation of the heating element itself from the sensor measurement error.

7. The method for controlling the production process of puncture-resistant PE film according to claim 6, characterized in that, The step of obtaining the local temperature distribution information of each heating element inside the die head includes: A known and stable thermal pulse signal is periodically applied to a local temperature sensor; A local temperature sensor is used to receive thermal pulse signals, and the response of the local temperature sensor to the thermal pulse signals is recorded. The response of the local temperature sensor to the thermal pulse signal is compared with the response of the local temperature sensor to the thermal pulse signal in its initial healthy state to quantify the measurement drift or failure of the local temperature sensor itself. By combining the measurement drift or malfunction of the local temperature sensor itself, the local temperature distribution information is corrected, thereby distinguishing the true local temperature distribution of the heating element from the sensor measurement error.

8. The method for controlling the production process of puncture-resistant PE film according to claim 6, characterized in that, The step of obtaining the local flow velocity information of the polymer melt inside the die head includes: A known and stable fluid pulse signal is periodically applied to the polymer melt flow rate sensor; A polymer melt flow rate sensor is used to receive fluid pulse signals and to record the response of the polymer melt flow rate sensor to the fluid pulse signals. The response of the polymer melt flow rate sensor to the fluid pulse signal is compared with the response of the polymer melt flow rate sensor to the fluid pulse signal in the initial healthy state in order to quantify the measurement drift or wear of the polymer melt flow rate sensor itself. By combining the measurement drift or wear of the polymer melt flow rate sensor itself, the local flow rate information is corrected, thereby distinguishing the true local flow rate of the melt from the sensor measurement error.

9. The method for controlling the production process of puncture-resistant PE film according to claim 4, characterized in that, The specific types of inhomogeneity include differences in molecular chain orientation, local density fluctuations, and uneven dispersion of additives.

10. A puncture-resistant PE film production process control system, characterized in that, include: The acoustic signal acquisition module is used to acquire the acoustic signals generated during the flow of polymer melt and extract characteristic information reflecting the rheological state of polymer melt from the acoustic signals. The electrical parameter acquisition module is used to acquire the real-time electrical parameters of each heating element in the extrusion die and determine the power output deviation of each heating element based on the real-time electrical parameters. The parameter adjustment module is used to adjust the screw speed or die heating power of the extruder based on the characteristics of the polymer melt rheological state and the power output deviation of each heating element, so as to maintain the uniformity of the polymer melt flow field at the extrusion die outlet.

Images