Cable production control method and device, computer equipment, medium and program product

Abstract

The invention relates to a cable production control method and device, computer equipment, a medium and a program product, and relates to the field of cable production. Comprising the following steps: in a cable production process, obtaining a quality monitoring signal of a target cable produced by cable production equipment and a periodic operation parameter of the cable production equipment; inputting the quality monitoring signal and the periodic operation parameter into a pre-trained signal decomposition model, and decomposing the quality monitoring signal based on the periodic operation parameter through the signal decomposition model, obtaining a first signal representing the actual production quality of the target cable and a second signal representing the coupling noise associated with the periodic operation parameter; performing feed-forward processing on the second signal to obtain a feed-forward compensation signal; and performing operation state adjustment on the cable production equipment based on a control signal obtained by fusing the first signal and the feed-forward compensation signal. By adopting the method, the cable production quality can be improved.

Description

Technical Field

[0001] This application relates to the field of cable manufacturing, and in particular to a cable manufacturing control method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] In the cable production process, automatic control systems based on online measurement feedback are commonly used to monitor cable production quality.

[0003] However, measurement signals at the cable production site are susceptible to interference, which can mask effective signals and thus limit the correction capability of the control system, ultimately leading to lower cable production quality. Summary of the Invention

[0004] Therefore, it is necessary to provide a cable production control method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the quality of cable production in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a cable production control method, comprising:

[0006] During the cable production process, the quality monitoring signals of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, are acquired.

[0007] The quality monitoring signal and periodic operating parameters are input into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0008] The second signal is processed by feedforward to obtain the feedforward compensation signal;

[0009] The operating status of the cable production equipment is adjusted based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

[0010] In one embodiment, the quality monitoring signal is decomposed based on periodic operating parameters using a signal decomposition model to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters, including:

[0011] The periodic operating parameters are analyzed using a signal decomposition model to extract multiple periodic feature components from the periodic operating parameters.

[0012] Based on the phase correlation between each periodic characteristic component, the noise component in the quality monitoring signal that changes synchronously with the periodic operating parameters is identified, and the noise component is determined as the second signal;

[0013] The second signal is removed from the quality monitoring signal to obtain the first signal.

[0014] In one embodiment, the cable production control method further includes:

[0015] The signal transmission delay and signal processing delay corresponding to the quality monitoring signal are obtained; whereby the transmission delay refers to the time elapsed from the generation of the quality monitoring signal to its acquisition, and the signal processing delay refers to the time consumed in the decomposition process of the quality monitoring signal.

[0016] The second signal is processed by feedforward to obtain a feedforward compensation signal, including:

[0017] Based on the signal transmission delay and signal processing delay, the second signal is subjected to feedforward processing to obtain the feedforward compensation signal.

[0018] In one embodiment, the second signal is fed forward based on the signal transmission delay and signal processing delay to obtain a feedforward compensated signal, including:

[0019] The phase lead factor is determined based on signal transmission delay and signal processing delay.

[0020] The second signal is transformed in the frequency domain to obtain the corresponding frequency domain signal.

[0021] Based on the phase lead factor, the frequency domain signal is phase-leaded to obtain the processed frequency domain signal.

[0022] The processed frequency domain signal is converted into the time domain to obtain the feedforward compensation signal.

[0023] In one embodiment, the operating state of the cable production equipment is adjusted based on the fused signal obtained by fusing the first signal and the feedforward compensation signal, including:

[0024] The compensation component is obtained by multiplying the feedforward compensation signal by the preset feedforward compensation coefficient.

[0025] The first signal and the compensation component are superimposed in opposite phase to obtain the control signal;

[0026] The operating status of cable production equipment is adjusted based on control signals.

[0027] In one embodiment, the cable production control method further includes:

[0028] Acquire historical quality monitoring signals and corresponding periodic historical operating parameters of cable production equipment during historical production processes;

[0029] Based on historical quality monitoring signals and periodic historical operating parameters, a phase correlation relationship is established among multiple periodic characteristic components in the periodic operating parameters;

[0030] Using phase correlation as a constraint, the initial decomposition model is trained until the model training stops, thus obtaining the signal decomposition model.

[0031] Secondly, this application also provides a cable production control device, comprising:

[0032] The data acquisition module is used to acquire quality monitoring signals of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, during the cable production process.

[0033] The signal decomposition module is used to input the quality monitoring signal and periodic operating parameters into the pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0034] The feedforward processing module is used to perform feedforward processing on the second signal to obtain the feedforward compensation signal;

[0035] The adjustment module is used to adjust the operating status of the cable production equipment based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] During the cable production process, the quality monitoring signals of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, are acquired.

[0038] The quality monitoring signal and periodic operating parameters are input into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0039] The second signal is processed by feedforward to obtain the feedforward compensation signal;

[0040] The operating status of the cable production equipment is adjusted based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

[0041] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0042] During the cable production process, the quality monitoring signals of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, are acquired.

[0043] The quality monitoring signal and periodic operating parameters are input into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0044] The second signal is processed by feedforward to obtain the feedforward compensation signal;

[0045] The operating status of the cable production equipment is adjusted based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

[0046] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0047] During the cable production process, the quality monitoring signals of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, are acquired.

[0048] The quality monitoring signal and periodic operating parameters are input into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0049] The second signal is processed by feedforward to obtain the feedforward compensation signal;

[0050] The operating status of the cable production equipment is adjusted based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

[0051] The aforementioned cable production control method, apparatus, computer equipment, computer-readable storage medium, and computer program product, during the cable production process, first acquire the quality monitoring signal of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, and input them into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters. This decomposition process accurately reveals the true cable quality state, laying a reliable foundation for subsequent precise control. Furthermore, by performing feedforward processing on the separated second signal and generating a feedforward compensation signal, known periodic interference can be proactively canceled, effectively overcoming the problem of insufficient correction capability in traditional feedback control due to the masking of effective signals. Finally, the first signal and the feedforward compensation signal are fused to form a control signal, thereby enabling precise adjustment of the cable production equipment's operating state. Thus, this solution significantly enhances the suppression capability of periodic interference in the cable production equipment and the real-time control accuracy of the cable production process, thereby improving the overall cable production quality. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is an application environment diagram of the cable production control method in one embodiment;

[0054] Figure 2 This is a flowchart illustrating a cable production control method in one embodiment;

[0055] Figure 3 This is a flowchart illustrating the signal decomposition process in one embodiment;

[0056] Figure 4 This is a schematic diagram of the signal feedforward processing flow in one embodiment;

[0057] Figure 5 This is a schematic diagram of the signal feedforward processing flow in another embodiment;

[0058] Figure 6 This is a schematic diagram of the training process of a signal decomposition model in one embodiment;

[0059] Figure 7This is a schematic diagram illustrating the construction of phase correlation relationships in one embodiment;

[0060] Figure 8 This is a schematic diagram illustrating the principle of model signal separation in one embodiment;

[0061] Figure 9 This is a structural block diagram of a cable production control device in one embodiment;

[0062] Figure 10 This is an internal structural diagram of a computer device in one embodiment;

[0063] Figure 11 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0066] The cable production control method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and various sensors on cable production lines. These sensors on cable production lines can include, but are not limited to, at least one type such as X-ray thickness gauges, ultrasonic thickness gauges, and speed sensors. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0067] The embodiments of this application can be derived from... Figure 1The terminal 102 or server 104 can execute independently, or they can be executed interactively. In an exemplary embodiment, such as Figure 2 As shown, the cable production control method provided in the embodiments of this application is applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0068] Step S202: During the cable production process, acquire the quality monitoring signal of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment.

[0069] Cable production equipment refers to devices used for cable manufacturing, such as cable extruders. In practical applications, cables are typically manufactured using a three-layer co-extrusion continuous vulcanization process, especially high-voltage cables. A qualified cable, from the inside out, consists of an inner semiconductive layer, an insulation layer, and an outer semiconductive layer. Co-extrusion refers to the simultaneous extrusion and encapsulation of these three different materials onto a copper conductor in the same extruder head. Vulcanization involves subjecting the extruded plastic (such as polyethylene) to high temperature and pressure, transforming its molecules from a linear structure to a network structure, thereby making it heat-resistant, deformation-resistant, and high-strength. Extrusion and vulcanization are completed continuously on a production line; the cable is extruded while simultaneously entering a closed vulcanization pipeline for chemical reaction and shaping. The target cable refers to the cable product currently being manufactured by the cable production equipment. Quality monitoring signals refer to the raw electrical signals reflecting the quality of cable production. These signals can be measured using X-ray thickness gauges or ultrasonic thickness gauges. The signals carry key geometric parameters for evaluating cable production quality, such as eccentricity and wall thickness uniformity. Eccentricity refers to the degree to which the center of the cable insulation layer and the center of the copper conductor do not coincide. Ideally, they should be perfectly concentric. If the insulation layer is eccentric, the electric field strength will increase sharply in thinner areas, making them the weakest points most susceptible to high-voltage breakdown. Generally, the eccentricity requirement for high-voltage cables is no more than 5%. In one example, the expression for calculating eccentricity is as follows:

[0070]

[0071] in, Indicates the maximum thickness of the insulation layer. This indicates the minimum thickness of the insulation layer. Wall thickness uniformity means that the thickness of the insulation layer at any point on the circumference and along the length of the cable must be consistent. Uneven thickness will also lead to uneven electric field distribution, thus affecting the long-term operational reliability of the cable.

[0072] Periodic operating parameters refer to state signals with significant periodic characteristics generated during the operation of cable production equipment. These mainly include at least one of mechanical periodic parameters and electrical periodic parameters. Mechanical periodic parameters include at least one of the following: real-time rotational speed of the equipment, key-phase pulse signals generated by speed sensors (such as encoders), and vibration waveforms output by accelerometers. These parameters directly determine the fundamental frequency and harmonics of mechanical vibration, causing mechanical vibration noise that propagates through the frame, mold, and cable body, resulting in microscopic displacement of the thickness gauge's measurement area. Electrical periodic parameters are mainly power frequency voltage signals collected from the power grid or equipment power supply, such as 50Hz (Hertz). Power frequency voltage signals are the beat source of mechanical vibration noise, which is directly superimposed on the quality monitoring signal through electromagnetic coupling. In addition, thermal gradient drift noise exists during production, originating from transient temperature gradient fluctuations in parts such as the extruder die head, which can cause zero-point drift in the thickness gauge. These noises exhibit a stable phase dependence due to physical coupling during continuous cable production, forming complex periodic interference. Traditional filtering methods or conventional PID (Proportional-Integral-Derivative) controllers struggle to accurately separate the true quality signal from the disturbed quality monitoring signal, resulting in significant lag in cable production control and limited correction capabilities. Ultimately, this leads to lower cable production accuracy, affecting cable production quality and yield.

[0073] For example, during cable production, sensors such as X-ray thickness gauges continuously scan the cable, converting information such as its eccentricity and wall thickness uniformity into continuous analog or digital electrical signals—quality monitoring signals. Simultaneously, an encoder mounted on the screw drive shaft of the cable production equipment outputs the rotational speed and the key phase pulse per revolution in real time, while a voltage transformer continuously acquires the power frequency voltage waveform. All signals are transmitted to a server, ensuring timestamp alignment to provide a complete, spatiotemporally synchronized data foundation for subsequent processing.

[0074] Step S204: Input the quality monitoring signal and periodic operating parameters into the pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0075] The pre-trained signal decomposition model refers to a pre-trained machine learning model that learns prior physical knowledge about the fixed correlation between periodic operating parameters and coupled noise during the training phase, thus possessing the ability to separate signals online in real time. In a preferred example, the signal decomposition model is a Generative Adversarial Network (GAN). Decomposition refers to the process of mathematically separating the input quality monitoring signal into two independent signals. The first signal is the signal component representing the actual production quality of the target cable obtained after decomposition. Ideally, this signal should only contain the real geometric changes caused by at least one non-periodic factor such as raw materials or process fluctuations, eliminating periodic interference. The second signal is the signal component representing the coupled noise associated with the periodic operating parameters obtained after decomposition. This signal concentrates all interference fluctuations in the quality monitoring signal that change synchronously with periodic characteristic components such as screw speed and power grid frequency, such as the combined effect of noise from mechanical vibration, electromagnetic induction, and thermal gradient drift.

[0076] For example, the server uses real-time acquired quality monitoring signals and periodic operating parameters as joint inputs, feeding them into a pre-trained signal decomposition model. Internally, this model indexes or calculates the corresponding noise coupling patterns based on the input real-time periodic operating parameters. Subsequently, the model uses these patterns as intrinsic constraints to run its neural network algorithm, performing real-time deconvolution on the quality monitoring signals. Understandably, the model has pre-learned the coupling noise patterns associated with the periodic operating parameters. For instance, at a specific rotational speed, there is a stable phase difference between the harmonic frequencies of the screw rotation speed and the harmonic frequencies of the power grid frequency, resulting in mixed noise with a specific time-domain / frequency-domain pattern. Therefore, the model can inversely estimate and extract the noise conforming to this pattern—the second signal—from the mixed signal, and output the remaining portion as the first signal.

[0077] Step S206: Perform feedforward processing on the second signal to obtain the feedforward compensation signal.

[0078] Feedforward processing refers to the process of calculating when the coupling noise will arrive at the measurement point based on the second signal and generating a reverse control action in advance. The feedforward compensation signal is the electrical signal output by this process. This signal is designed to completely cancel out the coupling noise at a future moment when it is about to contaminate the quality monitoring signal, thereby suppressing the impact of periodic interference on quality monitoring.

[0079] For example, after the server completes signal separation and obtains the second signal, it immediately performs feedforward processing on it. The core of this processing is to perform time-series advance reconstruction of the periodic coupling noise represented by the second signal based on the inherent cable production delay. This ensures that when the coupling noise reaches the quality monitoring point, a compensation signal with equal amplitude but opposite phase has also been generated synchronously, thereby achieving a fundamental shift from lag correction to look-ahead cancellation, significantly improving the timeliness and accuracy of cable production control.

[0080] Step S208: Based on the control signal obtained by fusing the first signal and the feedforward compensation signal, adjust the operating status of the cable production equipment.

[0081] Here, fusion refers to the operation of combining the first signal and the feedforward compensation signal into a single command signal. The control signal is the command signal generated after fusion, which is ultimately used to drive the cable production equipment. This signal may carry at least one parameter that changes the operating parameters of key actuators in the cable production equipment, such as the screw speed of an extruder.

[0082] For example, the server executes two instruction generation tasks in parallel. First, based on the deviation between the first signal and the target setpoint, a feedback control instruction is generated using a closed-loop control algorithm (such as a PID control algorithm). This aims to correct random fluctuations occurring during cable production in real time. The target setpoint refers to the geometric parameter targets required during cable production, such as at least one of the nominal thickness of the insulation layer or the maximum permissible eccentricity. Second, the amplitude of the feedforward compensation signal is adjusted to form a feedforward control instruction, aiming to proactively offset predicted periodic disturbances. Subsequently, the feedback control instruction and the feedforward control instruction are merged to generate the final unified control instruction. This instruction is sent to the actuators of the cable production equipment, such as servo drives, via a high-speed industrial communication network, driving them to produce corresponding adjustment actions, such as adjusting the screw speed, thereby adjusting the operating state of the cable production equipment. It can be understood that the feedback control loop is mainly used to deal with unknown or random disturbances, ensuring the stability of the cable production process; the feedforward control loop, on the other hand, provides advance compensation for predictable periodic disturbances. The two work together to enable the control commands received by the cable production equipment to simultaneously possess the ability to correct random deviations and suppress periodic interference, thereby achieving control accuracy and response speed for cable production quality.

[0083] In this embodiment, during the cable production process, the quality monitoring signal of the target cable produced by the cable production equipment and the periodic operating parameters of the cable production equipment are first acquired and input into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters. This decomposition process accurately reveals the true cable quality state, laying a reliable foundation for subsequent precise control. Furthermore, by performing feedforward processing on the separated second signal and generating a feedforward compensation signal, known periodic interference can be proactively canceled, effectively overcoming the problem of insufficient correction capability in traditional feedback control due to the masking of effective signals. Finally, the first signal and the feedforward compensation signal are fused to form a control signal, thereby enabling precise adjustment of the cable production equipment's operating state. Thus, this embodiment significantly enhances the suppression capability of periodic interference in the cable production equipment and the real-time control accuracy of the cable production process, thereby improving the overall cable production quality.

[0084] In one exemplary embodiment, such as Figure 3 As shown, the quality monitoring signal is decomposed based on periodic operating parameters using a signal decomposition model to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters, including:

[0085] Step S302: Perform feature analysis on the periodic operating parameters using a signal decomposition model to extract multiple periodic feature components from the periodic operating parameters.

[0086] Among them, the periodic characteristic component refers to the characteristic component representing a specific physical meaning extracted from the periodic operating parameters, such as at least one of the harmonic frequencies of the screw speed and the harmonic frequencies of the power grid frequency. The harmonic frequencies of the screw speed refer to the fundamental frequency (corresponding to one revolution of the screw) and its integer multiples of harmonics extracted from the screw speed signal, and the expression is: ,in, This converts revolutions per minute (RPM) to revolutions per second (RPS), i.e., the fundamental frequency (FPM), where k represents the first harmonic, second harmonic, etc. The harmonic frequencies of the power grid refer to the fundamental frequency and its integer multiples of harmonics extracted from the power grid signal, expressed as: Here, 50Hz is the fundamental frequency of the power line, and m represents the first harmonic, second harmonic, etc. Each component represents an independent periodic disturbance source.

[0087] For example, after receiving real-time collected periodic operating parameters, the model analyzes these parameters in real time based on the physical laws and data structures learned during the training phase. For instance, the model identifies the fundamental mechanical vibration frequency corresponding to the current rotational speed and automatically generates or calls a series of associated harmonic frequencies. Simultaneously, the model also identifies the power grid frequency and its main harmonic frequencies, providing accurate frequency and phase information for subsequent noise identification.

[0088] Step S304: Based on the phase correlation between each periodic characteristic component, identify the noise component in the quality monitoring signal that changes synchronously with the periodic operating parameters, and determine the noise component as the second signal.

[0089] Among them, the phase correlation relationship refers to the prior knowledge that exists within the signal decomposition model regarding the stable phase difference (i.e., the time sequence relationship) between different periodic feature components.

[0090] For example, after extracting multiple periodic feature components, the model immediately calls upon its internally stored phase correlation relationships that match the current operating conditions (such as rotational speed). This relationship defines the fixed phase constraints that these feature components should satisfy. Then, the model uses this correlation relationship as a template or filter to scan and match the synchronously input quality monitoring signal. That is, the model searches for signal components in the quality monitoring signal that maintain a specific phase relationship with the known periodic feature components in the time or frequency domain, i.e., the second signal.

[0091] Step S306: Remove the second signal from the quality monitoring signal to obtain the first signal.

[0092] For example, after the model accurately identifies and extracts the second signal, it is subtracted from the original quality monitoring signal. This operation is mathematically represented as a simple vector subtraction, which yields the best estimate of the true quality signal, i.e., the first signal. Through this operation, the server obtains the purified cable quality feedback information, laying the foundation for precise feedback control based on the true deviation.

[0093] In this embodiment, periodic feature components are extracted from periodic operating parameters using a signal decomposition model. By utilizing the fixed phase correlation between these components, periodic coupled noise is accurately separated from the interfered quality monitoring signal, thus obtaining a primary signal characterizing the actual production quality of the cable. This fundamentally solves the control lag and insufficient accuracy problems caused by the inability of traditional methods to distinguish between the actual signal and periodic interference. It provides a clean and reliable feedback information foundation for subsequent implementation of high-response, high-precision composite control, significantly improving the anti-interference capability and accuracy of the entire cable production control.

[0094] In one exemplary embodiment, such as Figure 4 As shown, the cable production control method also includes: acquiring the signal transmission delay and signal processing delay corresponding to the quality monitoring signal; wherein, the transmission delay refers to the time elapsed from the generation of the quality monitoring signal to its acquisition, and the signal processing delay refers to the time consumed in the decomposition process of the quality monitoring signal.

[0095] Signal transmission delay refers to the time required for a quality monitoring signal to travel from its generation location (e.g., extruder head) to the location of a measuring sensor (e.g., X-ray thickness gauge) during cable production. It can also be understood as the time required for coupled noise to be generated and collected. This delay is primarily determined by the fixed physical distance on the production line and the real-time production speed. In one example, the expression for signal transmission delay is as follows:

[0096]

[0097] in, For signal transmission delay, This refers to fixed physical distances on the production line, such as the physical distance from the machine head to the thickness gauge. This refers to real-time production speed. Signal processing latency refers to the time consumed from the quality monitoring signal completing signal decomposition.

[0098] For example, during feedforward processing, the server first calculates two key delays: signal transmission delay and signal processing delay. Then, these two are added together to obtain the total delay time used for compensation. The expression is: ,in, This is the total delay time. This is for signal processing latency. In practical applications, the server can also incorporate bus communication time. That is, the time consumed by transmitting the final control command through the high-speed industrial communication interface to the actuator of the cable production equipment, thereby .

[0099] In an exemplary embodiment, the second signal is subjected to feedforward processing to obtain a feedforward compensation signal, including: performing feedforward processing on the second signal based on the signal transmission delay and the signal processing delay to obtain a feedforward compensation signal.

[0100] For example, the server uses the total delay time mentioned above as a key parameter to perform feedforward processing on the second signal, that is, to shift the waveform of the second signal forward by the total delay time on the time axis, thereby theoretically achieving complete cancellation of periodic interference.

[0101] In one exemplary embodiment, reference continues to... Figure 4Based on the signal transmission delay and signal processing delay, a feedforward processing is performed on the second signal to obtain a feedforward compensation signal, including: determining a phase lead factor based on the signal transmission delay and signal processing delay; performing frequency domain transformation on the second signal to obtain a frequency domain signal corresponding to the second signal; performing phase lead processing on the frequency domain signal according to the phase lead factor to obtain a processed frequency domain signal; and performing time domain transformation on the processed frequency domain signal to obtain a feedforward compensation signal.

[0102] The phase lead factor is a complex mathematical operator whose core function is to define a phase rotation amount. In this embodiment, this factor is typically expressed as: ,in, Angular frequency, This represents the total delay time. When this factor is applied to each frequency component of the frequency domain signal, it is equivalent to commanding that component to shift forward on the time axis. Duration. Frequency domain conversion refers to the mathematical process of converting the second signal from its time domain representation to its frequency domain representation. In this embodiment, this can be achieved through a Fast Fourier Transform (FFT). A frequency domain signal is the mathematical representation of the second signal in the frequency domain. It is a complex sequence where each element corresponds to a specific frequency component. The magnitude of the element represents the amplitude of that frequency component, and the argument represents its initial phase. Phase lead processing refers to the operation of multiplying each frequency component of the frequency domain signal by its corresponding phase lead factor in the frequency domain. The result of this operation is a change in the phase angle of each frequency component while maintaining its amplitude. Time domain conversion refers to the process of converting the processed frequency domain signal back from its frequency domain representation to its time domain representation. This can also be achieved through an inverse Fast Fourier Transform (FFT). The feedforward compensation signal is the time domain signal obtained after the complete processing described above. Its waveform has the same shape as the original second signal, but it is advanced overall on the time axis. The duration, and will be used in reverse in subsequent steps to achieve cancellation.

[0103] For example, the server bases its calculations on the total latency. A phase lead factor is constructed for each frequency component. Then, a Fast Fourier Transform (FFT) is performed on the input second signal to convert it into a frequency domain signal. Next, phase lead processing is performed in the frequency domain by multiplying the frequency domain signal by the phase lead factor to obtain the processed frequency domain signal. Finally, an Inverse Fast Fourier Transform (IFFT) is performed on this frequency domain signal to restore it to the time domain waveform, which is the feedforward compensation signal. It can be understood that time shifting the signal in the time domain is equivalent to performing a linear phase rotation on all its frequency components in the frequency domain. By performing phase lead processing in the frequency domain, the precise time advance of the entire complex noise waveform can be achieved in one go without distortion, thereby generating control commands that can achieve spatiotemporal synchronization cancellation with future noise.

[0104] In one exemplary embodiment, such as Figure 5 As shown, based on the fused signal obtained by fusing the first signal and the feedforward compensation signal, the operating status of the cable production equipment is adjusted, including:

[0105] Step S502: Multiply the feedforward compensation signal by the preset feedforward compensation coefficient to obtain the compensation component.

[0106] The feedforward compensation coefficient is a pre-set or online-adjustable proportional coefficient. Its function is to scale the intensity of the feedforward compensation signal to calibrate the gain difference between the theoretically predicted interference amplitude and the actual physical system response, ensuring that the cancellation effect is appropriate. The compensation component refers to the final feedforward control command obtained after adjusting the feedforward compensation signal with the feedforward compensation coefficient. It retains the waveform and phase characteristics of the feedforward signal, but its amplitude has been adjusted to match the actual interference force to be canceled.

[0107] For example, the server takes the generated feedforward compensation signal as input and performs a scalar multiplication operation with the feedforward compensation coefficients stored in the system parameters to obtain the compensation component. It is understandable that in actual operation, due to possible minor changes in equipment status, material properties, etc., the intensity of the actual interference may deviate. Therefore, by multiplying by an adjustable coefficient, the intensity of the feedforward control action can be calibrated and fine-tuned online, allowing the generated compensation component to more accurately correspond to the actual interference energy that needs to be canceled, thereby improving the final accuracy and robustness of the feedforward compensation.

[0108] Step S504: The first signal and the compensation component are superimposed in opposite phase to obtain the control signal.

[0109] In this context, "inverse superposition" refers to the operation of combining the first signal and the compensation component using algebraic subtraction. In this embodiment, it specifically refers to subtracting the compensation component from the first signal. The physical meaning is that the compensation component is designed to cancel a positive interference, therefore it needs to be injected into the control loop in a reverse (i.e., negative) manner.

[0110] For example, the server calculates the feedback control quantity based on the deviation between the first signal and the target setpoint using a closed-loop control algorithm, and generates a feedback control command containing the feedback control quantity. On the other hand, it superimposes the first signal and the compensation component in opposite phase, that is, it fuses the feedback control command and the feedforward control command to generate the final unified control signal.

[0111] In one example, the expression for generating the control signal is as follows:

[0112]

[0113] in, For control signals, As the first signal, Forward compensation coefficient, This is the feedforward compensation signal.

[0114] Step S506: Adjust the operating status of the cable production equipment based on the control signal.

[0115] For example, the controller sends the generated control signals to the corresponding servo drives or frequency converters in the cable production equipment via a high-speed industrial communication network. These drives, upon receiving the control signals, convert them into precise motor torque or speed through internal high-performance current and speed loops. For extruders, changes in motor torque directly regulate the screw speed. The final closed-loop control achieves precise and stable control of cable geometry (such as eccentricity and wall thickness uniformity).

[0116] In one exemplary embodiment, such as Figure 6 As shown, the cable production control method further includes: acquiring historical quality monitoring signals and corresponding periodic historical operating parameters of the cable production equipment during the historical production process; establishing phase correlation relationships between multiple periodic feature components in the periodic operating parameters based on the historical quality monitoring signals and periodic historical operating parameters; and training the initial decomposition model using the phase correlation relationships as constraints until the model training stop condition is met, thereby obtaining the signal decomposition model.

[0117] Historical quality monitoring signals refer to the quality monitoring signals recorded by cable production equipment during past production processes, collected during the model training phase. These signals are mixed signals containing real production fluctuations and various historical interferences, serving as the raw material for model learning signals. Periodic historical operating parameters refer to equipment operating parameters collected synchronously with historical quality monitoring signals and strictly time-aligned, such as at least one of historical screw speeds or power grid frequency signals. Phase correlation refers to the stable and unchanging phase difference relationship between periodic characteristic components of different frequencies in periodic historical operating parameters, discovered through analysis of historical data. The initial decomposition model refers to the original machine learning model structure built before training begins, possessing signal separation capabilities but not yet learning specific knowledge, such as an untrained generative adversarial network. Model training termination conditions refer to the criteria used to end the training process, typically including but not limited to reaching the preset maximum number of training iterations, or the model's performance indicators (such as signal separation error) on the validation dataset no longer showing significant improvement.

[0118] For example, this embodiment describes the offline training and construction process of the signal decomposition model. First, under various steady-state and variable operating conditions of the equipment, the server synchronously collects a large amount of historical quality monitoring signals and periodic historical operating parameters, forming a training dataset. By performing spectral analysis on the periodic historical operating parameters, key periodic feature components can be extracted, such as at least one of the harmonic frequencies of the screw rotation speed and the power grid frequency. Subsequently, these data are analyzed using signal processing techniques such as Hilbert transform to establish phase correlation relationships. That is, the recurring and stable phase differences between periodic components from different sources, such as the harmonic frequencies of the screw rotation speed and the power grid frequency, under different operating parameters (such as different rotation speeds), are accurately calculated and formalized, such as by constructing a phase difference matrix related to rotation speed. Next, the constrained training phase begins. Based on the initial decomposition model, such as a GAN with a generator and discriminator structure, the training data is input into the model, and the established phase correlation relationships are used as hard constraints, implemented through at least one loss function, such as phase consistency loss, expressed as:

[0119]

[0120] in, It is the generator (G) prediction value, which is the phase difference between each periodic component calculated by the generator after performing phase analysis on the predicted coupled noise signal when attempting to separate the signal. It represents the phase relationship of the noise as perceived or fabricated by the generator. This represents the absolute error between the phase difference predicted by the generator and the actual phase difference matrix. This value measures the degree to which the generator deviates from physical reality. The larger the difference, the less the separated noise conforms to the physical coupling law. It is a weighting coefficient used to adjust the importance of the phase difference matrix, a physical constraint, throughout the model training process. A larger setting indicates that the model training focuses on physical consistency; conversely, if... If the setting is too small, the physical constraints will be weaker.

[0121] Through iterative optimization, the signal decomposition model is obtained until the model training stopping condition is met. At this point, the model internalizes the physical law of the stable and unchanging phase difference between each periodic component, and has the ability to accurately separate physically real periodic noise (second signal) and clean signal (first signal) from a mixed signal based on real-time operating parameters during online applications.

[0122] In some embodiments, Figure 7A schematic diagram illustrating the construction of the phase correlation relationship is provided. First, the periodic historical operating parameters are processed using a Hanning window and Fast Fourier Transform (FFT) to extract key periodic feature components. Then, the instantaneous phase is calculated using Hilbert transform. For the screw speed harmonic component, its instantaneous phase accurately describes the precise angular position of the mechanical component (such as the screw or gear) at time t, indicating its k-th order periodic motion. For the power grid frequency harmonic component, its instantaneous phase accurately describes the precise angular position of the power grid electromagnetic field at time t, indicating its m-th order periodic disturbance. Next, the two instantaneous phases are subtracted to obtain the phase difference, which generates the phase difference matrix M(RPM) related to the speed. Further, the server determines whether the equipment speed change ΔRPM exceeds a threshold, such as whether it is greater than or equal to 5. ΔRPM represents the amount or difference in speed change; more specifically, it is the absolute change in the speed value obtained between two consecutive calculations or two time points. If the threshold is exceeded, a smooth update is performed using an interpolation algorithm such as B-spline interpolation, and the dynamically updated M(RPM) is finally output to the initial decomposition model for model training.

[0123] In some embodiments, Figure 8 The diagram illustrates the signal separation principle of the model. Input and constraints: The historical quality monitoring signal obtained from actual sampling, along with periodic historical operating parameters, are input into the generator G. Generator G employs a hybrid structure combining a U-Net convolutional neural network and a bidirectional LSTM (Long Short-Term Memory) network. Simultaneously, physical constraints M(RPM) are applied to the discriminator D. The generator and discriminator undergo adversarial training. Generator G outputs a generated sample (i.e., the initially separated signal), which, along with the actual sampled data, is fed into discriminator D. Discriminator D determines whether the signal is genuine or not and backpropagates the calculated gradient of the determination result back to generator G to update G's parameters, enabling it to generate a more realistic signal. The total loss function of the entire network can be composed of a weighted sum of adversarial loss, reconstruction loss, and phase consistency loss. The reconstruction loss requires that the generated signal generally approximate the original input signal. The calculated total loss updates the parameters of both generator G and discriminator D through gradient feedback, driving the optimization of the entire network. After adversarial training optimization, the generator G finally separates the input historical quality monitoring signal and outputs it as two parts: a denoised clean signal (first signal) and a noisy signal (second signal).

[0124] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0125] Based on the same inventive concept, this application also provides a cable production control device for implementing the cable production control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more cable production control device embodiments provided below can be found in the limitations of the cable production control method described above, and will not be repeated here.

[0126] In one exemplary embodiment, such as Figure 9 As shown, a cable production control device is provided, comprising:

[0127] The data acquisition module 902 is used to acquire the quality monitoring signal of the target cable produced by the cable production equipment and the periodic operating parameters of the cable production equipment during the cable production process.

[0128] The signal decomposition module 904 is used to input the quality monitoring signal and periodic operating parameters into the pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters.

[0129] The feedforward processing module 906 is used to perform feedforward processing on the second signal to obtain a feedforward compensation signal;

[0130] The adjustment module 908 is used to adjust the operating status of the cable production equipment based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

[0131] In one embodiment, the signal decomposition module 904 is further configured to:

[0132] The periodic operating parameters are analyzed using a signal decomposition model to extract multiple periodic feature components from the periodic operating parameters.

[0133] Based on the phase correlation between each periodic characteristic component, the noise component in the quality monitoring signal that changes synchronously with the periodic operating parameters is identified, and the noise component is determined as the second signal;

[0134] The second signal is removed from the quality monitoring signal to obtain the first signal.

[0135] In one embodiment, the cable production control device is further configured to:

[0136] The signal transmission delay and signal processing delay corresponding to the quality monitoring signal are obtained; whereby the transmission delay refers to the time it takes for the quality monitoring signal to be generated and acquired, and the signal processing delay refers to the time consumed by the decomposition process of the quality monitoring signal.

[0137] In one embodiment, the feedforward processing module 906 is further configured to:

[0138] Based on the signal transmission delay and signal processing delay, the second signal is subjected to feedforward processing to obtain the feedforward compensation signal.

[0139] In one embodiment, the feedforward processing module 906 is further configured to:

[0140] The phase lead factor is determined based on signal transmission delay and signal processing delay.

[0141] The second signal is transformed in the frequency domain to obtain the corresponding frequency domain signal.

[0142] Based on the phase lead factor, the frequency domain signal is phase-leaded to obtain the processed frequency domain signal.

[0143] The processed frequency domain signal is converted into the time domain to obtain the feedforward compensation signal.

[0144] In one embodiment, the adjustment module 908 is further configured to:

[0145] The compensation component is obtained by multiplying the feedforward compensation signal by the preset feedforward compensation coefficient.

[0146] The first signal and the compensation component are superimposed in opposite phase to obtain the control signal;

[0147] The operating status of cable production equipment is adjusted based on control signals.

[0148] In one embodiment, the cable production control device is further configured to:

[0149] Acquire historical quality monitoring signals and corresponding periodic historical operating parameters of cable production equipment during historical production processes;

[0150] Based on historical quality monitoring signals and periodic historical operating parameters, a phase correlation relationship is established among multiple periodic characteristic components in the periodic operating parameters;

[0151] Using phase correlation as a constraint, the initial decomposition model is trained until the model training stops, thus obtaining the signal decomposition model.

[0152] Each module in the aforementioned cable production control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0153] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores cable production control data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a cable production control method.

[0154] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a cable production control method.

[0155] Those skilled in the art will understand that Figure 10 or Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0156] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0157] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0158] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0161] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0162] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A cable production control method, characterized in that, The method includes: During the cable production process, the quality monitoring signals of the target cable produced by the cable production equipment, as well as the periodic operating parameters of the cable production equipment, are acquired. The quality monitoring signal and the periodic operating parameters are input into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters. The second signal is processed by feedforward to obtain a feedforward compensation signal; The operating status of the cable production equipment is adjusted based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

2. The method according to claim 1, characterized in that, The process of decomposing the quality monitoring signal based on the periodic operating parameters using the signal decomposition model to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters includes: The periodic operating parameters are analyzed using the signal decomposition model to extract multiple periodic feature components from the periodic operating parameters. Based on the phase correlation between each of the periodic characteristic components, noise components that change synchronously with the periodic operating parameters in the quality monitoring signal are identified, and the noise components are determined as the second signal. The second signal is removed from the quality monitoring signal to obtain the first signal.

3. The method according to claim 1, characterized in that, The method further includes: The signal transmission delay and signal processing delay corresponding to the quality monitoring signal are obtained; wherein, the transmission delay refers to the time elapsed from the generation of the quality monitoring signal to its acquisition, and the signal processing delay refers to the time consumed by the decomposition process of the quality monitoring signal; The step of performing feedforward processing on the second signal to obtain a feedforward compensation signal includes: Based on the signal transmission delay and the signal processing delay, the second signal is subjected to feedforward processing to obtain the feedforward compensation signal.

4. The method according to claim 3, characterized in that, The step of performing feedforward processing on the second signal based on the signal transmission delay and the signal processing delay to obtain the feedforward compensated signal includes: The phase lead factor is determined based on the signal transmission delay and the signal processing delay; The second signal is frequency-domain converted to obtain the frequency domain signal corresponding to the second signal; Based on the phase lead factor, the frequency domain signal is subjected to phase lead processing to obtain the processed frequency domain signal; The processed frequency domain signal is converted into the time domain to obtain the feedforward compensation signal.

5. The method according to claim 1, characterized in that, The step of adjusting the operating status of the cable production equipment based on the fused signal obtained by fusing the first signal and the feedforward compensation signal includes: The compensation component is obtained by multiplying the feedforward compensation signal by a preset feedforward compensation coefficient. The first signal and the compensation component are superimposed in opposite phase to obtain the control signal; Based on the control signal, the operating status of the cable production equipment is adjusted.

6. The method according to claim 1, characterized in that, The method further includes: Acquire historical quality monitoring signals and corresponding periodic historical operating parameters of the cable production equipment during the historical production process; Based on the historical quality monitoring signals and the periodic historical operating parameters, a phase correlation relationship is established between multiple periodic feature components in the periodic operating parameters; Using the phase correlation relationship as a constraint, the initial decomposition model is trained until the model training stops, thus obtaining the signal decomposition model.

7. A cable production control device, characterized in that, The device includes: The data acquisition module is used to acquire the quality monitoring signals of the target cable produced by the cable production equipment and the periodic operating parameters of the cable production equipment during the cable production process. The signal decomposition module is used to input the quality monitoring signal and the periodic operating parameters into a pre-trained signal decomposition model. Based on the periodic operating parameters, the signal decomposition model decomposes the quality monitoring signal to obtain a first signal characterizing the actual production quality of the target cable and a second signal characterizing the coupling noise associated with the periodic operating parameters. The feedforward processing module is used to perform feedforward processing on the second signal to obtain a feedforward compensation signal; The adjustment module is used to adjust the operating status of the cable production equipment based on the control signal obtained by fusing the first signal and the feedforward compensation signal.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images