A method for preparing high-performance environmentally friendly power cable

Abstract

The present application provides a method for preparing a high-performance and environmentally friendly power cable, which relates to the field of cable processing technology, including: configuring a factor sensor array based on the traction speed influencing factor, and obtaining an influencing data set through fixed-point monitoring; predicting the traction speed change at the first moment according to the influencing data set to obtain a predicted speed fluctuation coefficient; calculating the predicted traction speed; optimizing and correcting the real-time extrusion speed of the real-time extrusion parameter according to the predicted traction speed to obtain an optimized extrusion parameter; at the first moment, iteratively controlling the extruder according to the optimized extrusion parameter. The present application can solve the technical problem in the traditional power cable preparation method that the extrusion speed of the sheath layer is less compatible with the cable traction speed due to the inability to accurately predict the cable traction speed in a complex environment, resulting in poor extrusion quality of the sheath layer, and can reduce the influence of traction speed fluctuations on the extrusion quality of the sheath layer, while reducing waste generation.

Description

Technical Field

[0001] The present application relates to the field of cable processing technology, and in particular to a method for preparing a high-performance and environmentally friendly power cable. Background Art

[0002] In the manufacturing process of power cables, the matching between the pulling speed of the cable conductor and the extrusion speed of the sheath layer is crucial. The sheath layer of the cable not only protects the conductor from the influence of the external environment, but also determines the mechanical strength and insulation performance of the cable. In order to ensure that the sheath layer of the cable can evenly and completely cover the conductor, the speed of the pulling system and the extrusion system must be highly consistent.

[0003] The traditional power cable manufacturing process mainly relies on mechanical control and manual adjustment. Although it can achieve the matching of traction and extrusion speed to a certain extent, when the production environment becomes complicated, such as when external conditions such as temperature and power supply voltage fluctuations change, the operating state of the traction equipment is easily affected.

[0004] At present, the traditional power cable preparation method has the problem that the cable pulling speed cannot be accurately predicted in a complex environment, resulting in a low degree of compatibility between the extrusion speed of the sheath layer and the cable pulling speed, causing problems such as uneven sheath thickness, incomplete coating, and material waste. Summary of the invention

[0005] The purpose of this application is to provide a high-performance and environmentally friendly method for preparing power cables, so as to solve the technical problem that the extrusion speed of the sheath layer is not able to accurately predict the cable pulling speed in a complex environment, resulting in a low degree of compatibility between the extrusion speed of the sheath layer and the cable pulling speed, resulting in poor extrusion quality of the sheath layer.

[0006] In view of the above problems, the present application provides a method for preparing a high-performance and environmentally friendly power cable, including: obtaining a traction speed influencing factor, and configuring a factor sensor array based on the traction speed influencing factor; obtaining an influence data set through fixed-point monitoring of the factor sensor array; predicting the traction speed change at a first moment according to the influence data set to obtain a predicted speed fluctuation coefficient; monitoring and obtaining the real-time traction speed, and calculating the predicted traction speed based on the real-time traction speed and the predicted speed fluctuation coefficient; optimizing and correcting the real-time extrusion speed of the real-time extrusion parameter according to the predicted traction speed to obtain an optimized extrusion parameter; at the first moment, iteratively adaptively controlling the single-screw extruder according to the optimized extrusion parameter.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By configuring the factor sensor array based on the traction speed influencing factor, the influencing data set is acquired through fixed-point monitoring; then, the traction speed change at the first moment is predicted according to the influencing data set to obtain the predicted speed fluctuation coefficient; the predicted traction speed is further calculated based on the real-time traction speed and the predicted speed fluctuation coefficient, and the real-time extrusion speed of the real-time extrusion parameters is optimized and corrected according to the predicted traction speed to obtain the optimized extrusion parameters; finally, at the first moment, the single-screw extruder is iteratively adaptively controlled according to the optimized extrusion parameters; the accuracy of the cable traction speed prediction can be improved, so that the extrusion speed can be quickly and accurately adjusted according to the predicted traction speed, reducing the influence of the traction speed fluctuation on the extrusion quality of the sheath layer, and at the same time reducing waste generation and improving production efficiency.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 A schematic diagram of a process for preparing a high-performance environmentally friendly power cable according to the present application; Figure 2 A schematic diagram of a process for obtaining a predicted speed fluctuation coefficient in a method for preparing a high-performance, environmentally friendly power cable according to the present application. DETAILED DESCRIPTION

[0012] This application provides a high-performance and environmentally friendly power cable preparation method to solve the technical problem that the extrusion speed of the sheath layer is not compatible with the cable traction speed due to the inability to accurately predict the cable traction speed in a complex environment, resulting in poor extrusion quality of the sheath layer. The accuracy of cable traction speed prediction can be improved, so that the extrusion speed can be quickly and accurately adjusted according to the predicted traction speed, reducing the impact of traction speed fluctuations on the extrusion quality of the sheath layer, while reducing waste generation and improving production efficiency.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] For examples, please see the attached Figure 1 The present application provides a method for preparing a high-performance environmentally friendly power cable, which specifically comprises the following steps:

[0015] Step 1: Obtain the traction speed influencing factor, and configure the factor sensor array based on the traction speed influencing factor.

[0016] Specifically, first, the traction speed influencing factor is obtained, and the traction speed influencing factor refers to the dynamic interference factor that affects the traction speed of the cable conductor. These factors will cause fluctuations in the traction speed during the cable manufacturing process, thereby affecting the stability and consistency of the extrusion speed of the sheath layer, resulting in quality problems such as uneven sheath thickness and incomplete coating. The traction speed influencing factor includes power supply voltage fluctuations, traction equipment lubricating oil temperature, drive motor temperature and inverter temperature, among which the stability of the power supply voltage directly affects the operation of the drive motor; the lubricating oil temperature in the traction equipment affects the friction and operating efficiency of the mechanical parts; the temperature change of the drive motor affects the operating efficiency and stability of the motor; the inverter is responsible for adjusting the frequency and voltage of the drive motor, and the temperature change of the inverter directly affects the speed control accuracy of the motor.

[0017] Then, a factor sensor array is configured according to the traction speed influencing factors. The factor sensor array includes multiple monitoring sensors, and there is a mapping relationship between the monitoring sensors and the traction speed influencing factors. For example, the monitoring sensors corresponding to the power supply voltage fluctuation include the power supply voltage sensor and the production line load sensor. The power supply voltage sensor is used to monitor the voltage fluctuation of the power supply system of the cable production line, and the production line load sensor is used to monitor the electrical load of each device in the production line; the monitoring sensor corresponding to the lubricating oil temperature of the traction equipment is a temperature sensor. By configuring the factor sensor array, real-time monitoring of the traction speed influencing factors (power supply voltage fluctuation, lubricating oil temperature, drive motor temperature and inverter temperature) can be achieved, and dynamic data of each influencing factor can be continuously collected, providing data support for the subsequent prediction of the cable traction speed.

[0018] Step 2: Obtain the impact data set through fixed-point monitoring of the factor sensor array.

[0019] Specifically, the factors affecting the traction speed are monitored at fixed points through the factor sensor array to obtain the impact data set, wherein the time interval of the fixed-point monitoring can be flexibly set by the technicians in this field according to the actual production needs. For example, when the real-time control requirements for the traction speed are high, the monitoring time interval can be set to a shorter time (such as once per second); and when the environment is relatively stable, the monitoring time interval can be extended accordingly. The impact data set includes a voltage data sequence, a production line load data sequence, a lubricating oil temperature sequence, a motor temperature sequence and a frequency converter temperature sequence, wherein the voltage data sequence is collected by the power supply voltage sensor to record the voltage change of the power supply system; the production line load data sequence is collected by the load sensor to reflect the operating load of each device of the cable production line; the lubricating oil temperature data sequence is collected by the lubricating oil temperature sensor to reflect the temperature change of the lubricating oil in the traction equipment; the motor temperature data sequence is collected by the motor temperature sensor to record the temperature change of the drive motor under different load conditions; the frequency converter temperature data sequence is collected by the frequency converter temperature sensor to reflect the temperature change of the frequency converter during operation. Through the fixed-point monitoring of the factor sensor array, a comprehensive traction speed impact data set can be obtained within a flexibly set time interval, providing data support for the prediction and analysis of the traction speed.

[0020] Step 3: Predict the traction speed change at the first moment according to the influencing data set to obtain a predicted speed fluctuation coefficient.

[0021] Specifically, first, the first moment is set. The first moment refers to a specific moment with a fixed time interval from the current time node. It can be flexibly set according to production needs, for example, in the next five minutes, to predict the change of traction speed at that moment. Then, the traction speed change analysis at the first moment is performed based on the impact data set. First, the voltage at the first moment is predicted based on the voltage data sequence and the production line load data sequence. The lubricating oil temperature, motor temperature and inverter temperature at the first moment are predicted based on the lubricating oil temperature sequence, motor temperature sequence and inverter temperature sequence, respectively, to obtain the predicted voltage, predicted lubricating oil temperature, predicted motor temperature and predicted inverter temperature.

[0022] BP neural network is a multi-layer feedforward neural network widely used in deep learning and artificial intelligence. A speed change analysis channel is further constructed based on the BP neural network. The speed change analysis channel is a neural network model that can be iteratively optimized in machine learning, and is obtained through supervised training with sample data. Then, through the speed change analysis channel, the traction speed change analysis is performed based on the predicted voltage, predicted lubricating oil temperature, predicted motor temperature, and predicted inverter temperature to obtain the predicted speed fluctuation coefficient, where the speed fluctuation coefficient refers to the fluctuation of the relative real-time traction speed, which is used to measure the change amplitude of the traction speed at the prediction moment.

[0023] Step 4: Monitor and obtain the real-time traction speed, and calculate the predicted traction speed based on the real-time traction speed and the predicted speed fluctuation coefficient.

[0024] Specifically, first, a sensor is used to monitor the current traction speed of the traction device in real time to obtain the real-time traction speed. Then, the product of the real-time traction speed and the predicted speed fluctuation coefficient is calculated, and the calculation result is used as the predicted traction speed. By obtaining the predicted traction speed, a basis is provided for the next step of optimizing and correcting the real-time extrusion speed.

[0025] Step 5: Optimizing and correcting the real-time extrusion speed of the real-time extrusion parameter according to the predicted pulling speed to obtain the optimized extrusion parameter.

[0026] Specifically, firstly, the minimum coating thickness is obtained, and the minimum coating thickness is set based on the expected processing index of the sheath layer; then, the real-time extrusion speed of the real-time extrusion parameter is optimized and corrected according to the predicted traction speed, with the minimum coating thickness being satisfied as a constraint. For example, the cable conductor attribute information, the extruder attribute information and the minimum coating thickness can be used as retrieval constraints, and the cable preparation log is called to obtain a sample optimization data set, wherein the sample optimization data includes a sample traction speed and a sample extrusion speed, and the sample traction speed and the sample extrusion speed correspond one to one; then, based on the decision tree principle, according to the correspondence between the sample traction speed and the sample extrusion speed, the sample traction speed is used as a child node, and the sample extrusion speed is used as a leaf node of the child node, and an optimization correction tree is constructed, and the predicted traction speed is input into the optimization correction tree, and the optimized extrusion speed is output. By constructing an optimization correction tree based on the decision tree principle, the efficiency and accuracy of the extrusion speed optimization correction can be improved.

[0027] Finally, the real-time extrusion parameters are updated according to the optimized extrusion speed to obtain the optimized extrusion parameters. By optimizing and correcting the extrusion speed in the real-time extrusion parameters according to the predicted traction speed, it can ensure that the thickness of the sheath layer meets the minimum coating thickness requirements, and at the same time, the quality of the sheath layer can be kept stable when the traction speed changes, reducing material waste and improving production efficiency.

[0028] Step six: at the first moment, performing iterative adaptive control on the single screw extruder according to the optimized extrusion parameters.

[0029] Specifically, at the first moment, the single-screw extruder is iteratively adaptively controlled according to the optimized extrusion parameters. The adaptive control method achieves dynamic matching of extrusion speed and traction speed through continuous monitoring and feedback adjustment, thereby improving the overall quality and production efficiency of cable preparation.

[0030] By providing a high-performance and environmentally friendly power cable preparation method, the technical problem that the extrusion speed of the sheath layer is not compatible with the cable traction speed due to the inability to accurately predict the cable traction speed in a complex environment, resulting in poor extrusion quality of the sheath layer, can be solved in the traditional power cable preparation method. By configuring the factor sensor array based on the traction speed influencing factor, the influence data set is obtained by fixed-point monitoring; then the traction speed change at the first moment is predicted according to the influence data set to obtain the predicted speed fluctuation coefficient; further based on the real-time traction speed and the predicted speed fluctuation coefficient, the predicted traction speed is calculated, and the real-time extrusion speed of the real-time extrusion parameter is optimized and corrected according to the predicted traction speed to obtain the optimized extrusion parameters; finally, at the first moment, the single-screw extruder is iteratively adaptively controlled according to the optimized extrusion parameters; the accuracy of the cable traction speed prediction can be improved, so that the extrusion speed can be quickly and accurately adjusted according to the predicted traction speed, reducing the influence of the traction speed fluctuation on the extrusion quality of the sheath layer, and at the same time, it can reduce waste generation and improve production efficiency.

[0031] Furthermore, the present application includes:

[0032] The factors affecting the traction speed include power supply voltage fluctuation, traction equipment lubricating oil temperature, drive motor temperature and inverter temperature. Specifically, the factors affecting the traction speed include power supply voltage fluctuation, traction equipment lubricating oil temperature, drive motor temperature and inverter temperature. Among them, the stability of the power supply voltage directly affects the operation of the drive motor. Voltage fluctuation will cause changes in the motor output power, which in turn affects the traction speed of the cable. If the voltage is too low, the motor output is insufficient and the traction speed is reduced; if the voltage is too high, the motor may be overloaded, resulting in traction speed fluctuations. The lubricating oil temperature in the traction equipment affects the friction and operating efficiency of the mechanical parts. When the lubricating oil temperature is too high, the lubrication effect decreases, the friction increases, the traction equipment does not run smoothly, and the traction speed fluctuates; when the temperature is too low, the viscosity of the lubricating oil increases, the equipment operation resistance increases, and it also affects the stability of the traction speed; the change in the drive motor temperature will affect the operating efficiency and stability of the motor; when the temperature is too high, the motor may enter the protection mode, resulting in a slowdown or even stop in the traction speed; when the temperature is too low, the motor is difficult to start, the operation is unstable, and the traction speed cannot be kept constant. The inverter is responsible for adjusting the frequency and voltage of the drive motor. The temperature change of the inverter directly affects the speed control accuracy of the motor. When the temperature of the inverter is too high, it may enter the overheat protection mode, causing the traction speed to fluctuate or lose control; if the temperature of the inverter is too low, it will affect its working efficiency and cause the traction speed to be unstable.

[0033] Furthermore, the present application includes:

[0034] The impact data set includes a voltage data sequence, a production line load data sequence, a lubricating oil temperature sequence, a motor temperature sequence and a frequency converter temperature sequence.

[0035] Specifically, the influencing data set includes a voltage data sequence, a production line load data sequence, a lubricating oil temperature sequence, a motor temperature sequence and an inverter temperature sequence, wherein the voltage data sequence is used to record the voltage changes of the power supply system, and is constructed by arranging the voltage data of multiple monitoring nodes in the order of collection, reflecting the voltage fluctuations of the cable production line at different time points; the production line load data sequence is collected by the load sensor, reflecting the operating load conditions of each device of the cable production line, and the load fluctuation will directly affect the power supply stability, thereby affecting the traction speed; the lubricating oil temperature data sequence reflects the temperature changes of the lubricating oil in the traction equipment, and the change in the lubricating oil temperature will cause the friction of the equipment to increase or decrease, thereby affecting the stability of the traction speed; the motor temperature data sequence records the temperature changes of the drive motor under different load conditions, and excessive temperature will cause the motor efficiency to decrease, and even overload protection will occur, affecting the traction speed; the inverter temperature data sequence reflects the temperature changes of the inverter during operation, and the fluctuation of the inverter temperature will affect the output voltage and frequency, thereby causing instability in the traction speed.

[0036] Further, as attached Figure 2 As shown, this application includes:

[0037] The voltage fluctuation at the first moment is predicted according to the voltage data sequence and the production line load data sequence to obtain the predicted voltage; the lubricating oil temperature at the first moment is predicted according to the lubricating oil temperature sequence to obtain the predicted lubricating oil temperature; the motor temperature at the first moment is predicted according to the motor temperature sequence to obtain the predicted motor temperature; the inverter temperature at the first moment is predicted according to the inverter temperature sequence to obtain the predicted inverter temperature; the traction speed change analysis is performed according to the predicted voltage, the predicted lubricating oil temperature, the predicted motor temperature and the predicted inverter temperature, and the predicted speed fluctuation coefficient is output.

[0038] Specifically, first, voltage fluctuation trend analysis and load fluctuation trend analysis are performed according to the voltage data sequence and the production line load data sequence, respectively, to obtain voltage fluctuation trend and load fluctuation trend. Then, a long short-term memory network is used to predict voltage fluctuation at the first moment according to the terminal voltage data, voltage fluctuation trend, terminal load data and load fluctuation trend, to obtain the predicted voltage at the first moment, wherein the terminal voltage data refers to the voltage data of the last monitoring node in the voltage data sequence, and the terminal load data refers to the load data of the last monitoring node in the production line load data sequence.

[0039] The temperature change trend analysis is performed according to the lubricating oil temperature sequence to obtain the lubricating oil temperature change curve, and then the lubricating oil temperature at the first moment is predicted according to the lubricating oil temperature change curve and the terminal lubricating oil temperature to obtain the predicted lubricating oil temperature; on the other hand, the motor temperature is predicted at the first moment according to the motor temperature sequence to obtain the predicted motor temperature, and the inverter temperature is predicted at the first moment according to the inverter temperature sequence to obtain the predicted inverter temperature. Then, through the speed change analysis channel, the traction speed change analysis is performed based on the predicted voltage, predicted lubricating oil temperature, predicted motor temperature and predicted inverter temperature to obtain the predicted speed fluctuation coefficient, where the speed fluctuation coefficient refers to the fluctuation of the relative real-time traction speed, which is used to measure the change amplitude of the traction speed at the predicted moment.

[0040] Furthermore, the present application includes:

[0041] Perform voltage fluctuation trend analysis based on the voltage data sequence to determine the voltage fluctuation trend; perform load fluctuation trend analysis based on the production line load data sequence to determine the load fluctuation trend; obtain terminal voltage data of the voltage data sequence and terminal load data of the production line load data sequence; predict the voltage fluctuation at the first moment based on the terminal voltage data, voltage fluctuation trend, terminal load data and load fluctuation trend, and output the predicted voltage.

[0042] Specifically, first, according to the voltage data sequence, the voltage fluctuation trend analysis is performed. By calculating the moving average of the voltage data, short-term fluctuations are smoothed, the long-term trend of the voltage is obtained, and the voltage fluctuation trend is determined, wherein the voltage fluctuation trend includes the fluctuation direction and the fluctuation amplitude; on the other hand, according to the production line load data sequence, the load fluctuation trend analysis is performed. The linear regression method can be used to perform trend analysis on the production line load data sequence to obtain the load change trend over time and determine the load fluctuation trend. The terminal voltage data of the voltage data sequence and the terminal load data of the production line load data sequence are obtained, wherein the terminal voltage data refers to the voltage data of the last monitoring node in the voltage data sequence, and the terminal load data refers to the load data of the last monitoring node in the production line load data sequence. The long short-term memory network is a special recursive neural network (RNN) that can effectively process and predict time series-based data and is particularly suitable for learning long series data. A voltage fluctuation prediction model is constructed based on the long short-term memory network, wherein the voltage fluctuation prediction model includes an input layer, an LSTM layer, a fully connected layer, and an output layer, wherein the LSTM layer has a memory function and can process long-term dependencies in time series data, and capture the dynamic changes of voltage and load fluctuations by using multiple hidden units. Then, the historical voltage fluctuation and load fluctuation data are used to train the model, the error between the predicted result and the actual result is evaluated by calculating the loss function, and the model weight is updated by back propagation to obtain the trained voltage fluctuation prediction model. Finally, the voltage fluctuation prediction model is used to predict the voltage fluctuation at the first moment according to the terminal voltage data, voltage fluctuation trend, terminal load data and load fluctuation trend, and the predicted voltage is output.

[0043] Furthermore, the present application includes:

[0044] Deviation calculations are performed on the terminal voltage and the predicted voltage, the terminal lubricating oil temperature and the predicted lubricating oil temperature, the terminal motor temperature and the predicted motor temperature, and the terminal inverter temperature and the predicted inverter temperature to obtain the predicted voltage difference, the predicted lubricating oil temperature difference, the predicted motor temperature difference, and the predicted inverter temperature difference; the predicted voltage difference, the predicted lubricating oil temperature difference, the predicted motor temperature difference, and the predicted inverter temperature difference are input into the speed change analysis channel for prediction, and the predicted speed fluctuation coefficient is output.

[0045] Specifically, first, the terminal voltage and the predicted voltage, the terminal lubricating oil temperature and the predicted lubricating oil temperature, the terminal motor temperature and the predicted motor temperature, the terminal inverter temperature and the predicted inverter temperature are respectively calculated to obtain the predicted voltage difference, the predicted lubricating oil temperature difference, the predicted motor temperature difference and the predicted inverter temperature difference, wherein the predicted voltage difference is the voltage difference value of the predicted voltage minus the terminal voltage. Then, a speed change analysis channel is constructed based on the BP neural network, and the predicted voltage difference, the predicted lubricating oil temperature difference, the predicted motor temperature difference and the predicted inverter temperature difference are input into the speed change analysis channel for prediction, and the predicted speed fluctuation coefficient is output. By constructing a speed change analysis channel based on the BP neural network to predict the traction speed fluctuation, the efficiency and accuracy of the speed fluctuation prediction can be improved, thereby improving the efficiency and accuracy of the extrusion speed optimization correction.

[0046] Furthermore, the present application includes:

[0047] The cable preparation log is called, and a sample prediction data set is obtained based on the cable preparation log, wherein the sample prediction data includes a sample voltage difference, a sample lubricating oil temperature difference, a sample motor temperature difference, a sample inverter temperature difference and a sample speed fluctuation coefficient; the sample prediction data set is divided into K equal parts, and K parts are selected with replacement K times to obtain a first sample set, and K sample sets are selected iteratively K times to obtain K sample sets; with the sample voltage difference, the sample lubricating oil temperature difference, the sample motor temperature difference and the sample inverter temperature difference as input data, and the sample speed fluctuation coefficient as supervision data, the K sample sets are used to perform supervised training and cross-validation training on the BP neural network respectively, to obtain K convergence change analysis units; the speed change analysis channel is constructed based on the K convergence change analysis units, wherein the output of the speed change analysis channel is the mean of the output results of the K convergence change analysis units.

[0048] Specifically, the cable preparation log is called, where the cable preparation log records various parameters in the cable preparation process, and then the sample prediction data set is obtained based on the cable preparation log, where the sample prediction data includes sample voltage difference, sample lubricating oil temperature difference, sample motor temperature difference, sample inverter temperature difference and sample speed fluctuation coefficient. The speed fluctuation coefficient refers to the fluctuation of the relative real-time traction speed, which is used to measure the change range of the traction speed at the prediction time. The sample prediction data set is further divided into K parts to obtain K data sets, and K data sets are selected with replacement K times in the K data sets to obtain the first sample set, and the same method is used to iteratively select K times to obtain K sample sets.

[0049] K initial change analysis units are constructed based on the BP neural network, with sample voltage difference, sample lubricating oil temperature difference, sample motor temperature difference, and sample inverter temperature difference as input data, and sample speed fluctuation coefficient as supervision data. The K sample sets are used to perform supervised training on the K initial change analysis units, wherein each sample set corresponds to an initial change analysis unit, that is, supervised training is performed using the back propagation algorithm, and the gradient of the error is calculated using the BP algorithm according to the error between the predicted value and the true value, and the weight in the network is adjusted by the gradient descent method to gradually reduce the error; through multiple rounds of iterative training, the BP neural network will gradually converge and find the best mapping relationship between the input data and the output data; and obtain K change analysis units that meet the preset number of training times. Then, the K sample sets are crossed, and the K change analysis units are verified and trained through different sample sets to obtain K converged change analysis units that meet the preset convergence constraints.

[0050] Finally, the speed change analysis channel is constructed based on the K convergence change analysis units, wherein the output of the speed change analysis channel is the mean of the output results of the K convergence change analysis units. By constructing the speed change analysis channel based on the K convergence change analysis units based on the principle of ensemble learning, the prediction error of a single model can be reduced, and the accuracy and stability of the speed change analysis channel prediction can be improved.

[0051] Furthermore, the present application includes:

[0052] Taking the minimum coating thickness as a constraint, the real-time extrusion speed is optimized and analyzed based on the predicted traction speed to obtain an optimized extrusion speed; the real-time extrusion parameters are updated according to the optimized extrusion speed, and the optimized extrusion parameters are output.

[0053] Specifically, the minimum coating thickness of the cable is obtained, and then the cable conductor attribute information, extruder attribute information and the minimum coating thickness are used as search constraints, the cable preparation log is called, and the sample optimization data set is obtained, wherein the sample optimization data includes the sample traction speed and the sample extrusion speed, and the sample traction speed and the sample extrusion speed correspond to each other; then based on the decision tree principle, according to the correspondence between the sample traction speed and the sample extrusion speed, the sample traction speed is used as the child node, and the sample extrusion speed is used as the leaf node of the child node, and the predicted traction speed is input into the optimization correction tree, and the optimized extrusion speed is output. Finally, the real-time extrusion parameters are updated according to the optimized extrusion speed, and the optimized extrusion parameters are output.

[0054] In summary, the method for preparing a high-performance environmentally friendly power cable provided in this application has the following technical effects:

[0055] By configuring the factor sensor array based on the traction speed influencing factor, the influencing data set is acquired through fixed-point monitoring; then, the traction speed change at the first moment is predicted according to the influencing data set to obtain the predicted speed fluctuation coefficient; the predicted traction speed is further calculated based on the real-time traction speed and the predicted speed fluctuation coefficient, and the real-time extrusion speed of the real-time extrusion parameters is optimized and corrected according to the predicted traction speed to obtain the optimized extrusion parameters; finally, at the first moment, the single-screw extruder is iteratively adaptively controlled according to the optimized extrusion parameters; the accuracy of the cable traction speed prediction can be improved, so that the extrusion speed can be quickly and accurately adjusted according to the predicted traction speed, reducing the influence of the traction speed fluctuation on the extrusion quality of the sheath layer, and at the same time reducing waste generation and improving production efficiency.

[0056] The above description of the disclosed embodiments enables professionals and technicians in the field to implement or use the present application. Various modifications to these embodiments will be apparent to professionals and technicians in the field, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features disclosed herein. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for preparing a high-performance environmentally friendly power cable, characterized in that: include: Acquire a traction speed influencing factor, and configure a factor sensing array based on the traction speed influencing factor; Acquiring an impact data set through fixed-point monitoring of the factor sensor array; Predicting the change of traction speed at a first moment according to the influencing data set to obtain a predicted speed fluctuation coefficient; Monitoring and acquiring a real-time traction speed, and calculating a predicted traction speed based on the real-time traction speed and a predicted speed fluctuation coefficient; According to the predicted pulling speed, the real-time extrusion speed of the real-time extrusion parameter is optimized and corrected to obtain the optimized extrusion parameter; At the first moment, performing iterative adaptive control on the single screw extruder according to the optimized extrusion parameters; The factors affecting the traction speed include power supply voltage fluctuation, traction equipment lubricating oil temperature, drive motor temperature and inverter temperature; The impact data set includes a voltage data sequence, a production line load data sequence, a lubricating oil temperature sequence, a motor temperature sequence and a frequency converter temperature sequence; The prediction of the traction speed change at the first moment according to the influencing data set to obtain the predicted speed fluctuation coefficient includes: Predicting voltage fluctuation at a first moment according to the voltage data sequence and the production line load data sequence to obtain a predicted voltage; Predicting the lubricating oil temperature at a first moment according to the lubricating oil temperature sequence to obtain a predicted lubricating oil temperature; Predicting the motor temperature at a first moment according to the motor temperature sequence to obtain a predicted motor temperature; Predicting the inverter temperature at a first moment according to the inverter temperature sequence to obtain a predicted inverter temperature; A traction speed variation analysis is performed based on the predicted voltage, predicted lubricating oil temperature, predicted motor temperature and predicted inverter temperature, and the predicted speed fluctuation coefficient is output.

2. A method for preparing a high-performance environmentally friendly power cable according to claim 1, characterized in that: Predicting voltage fluctuation at a first moment according to the voltage data sequence and the production line load data sequence to obtain a predicted voltage includes: Performing voltage fluctuation trend analysis according to the voltage data sequence to determine the voltage fluctuation trend; Performing load fluctuation trend analysis according to the production line load data sequence to determine the load fluctuation trend; Acquire the terminal voltage data of the voltage data sequence and the terminal load data of the production line load data sequence; The voltage fluctuation at the first moment is predicted based on the terminal voltage data, the voltage fluctuation trend, the terminal load data and the load fluctuation trend, and the predicted voltage is output.

3. The method for preparing a high-performance environmentally friendly power cable according to claim 1, characterized in that: The traction speed variation analysis is performed according to the predicted voltage, the predicted lubricating oil temperature, the predicted motor temperature and the predicted inverter temperature, and the predicted speed fluctuation coefficient is output, including: Deviation calculations are performed on the terminal voltage and the predicted voltage, the terminal lubricating oil temperature and the predicted lubricating oil temperature, the terminal motor temperature and the predicted motor temperature, and the terminal inverter temperature and the predicted inverter temperature to obtain the predicted voltage difference, the predicted lubricating oil temperature difference, the predicted motor temperature difference, and the predicted inverter temperature difference; The predicted voltage difference, predicted lubricating oil temperature difference, predicted motor temperature difference and predicted inverter temperature difference are input into a speed change analysis channel for prediction, and the predicted speed fluctuation coefficient is output.

4. A method for preparing a high-performance environmentally friendly power cable according to claim 3, characterized in that: Construct a speed change analysis channel, including: Calling a cable preparation log, and filtering and acquiring a sample prediction data set based on the cable preparation log, wherein the sample prediction data includes a sample voltage difference, a sample lubricating oil temperature difference, a sample motor temperature difference, a sample inverter temperature difference, and a sample speed fluctuation coefficient; Divide the sample prediction data set into K equal parts, select K parts with replacement to obtain a first sample set, and iterate K times to obtain K sample sets; Using sample voltage difference, sample lubricating oil temperature difference, sample motor temperature difference, and sample inverter temperature difference as input data, and sample speed fluctuation coefficient as supervision data, the K sample sets are used to perform supervised training and cross-validation training on the BP neural network, respectively, to obtain K convergence change analysis units; The speed change analysis channel is integrated and constructed based on the K convergence change analysis units, wherein the output of the speed change analysis channel is the average of the output results of the K convergence change analysis units.

5. The method for preparing a high-performance environmentally friendly power cable according to claim 1, characterized in that: The real-time extrusion speed of the real-time extrusion parameter is optimized and corrected according to the predicted pulling speed, including: Taking the minimum coating thickness as a constraint, optimizing and analyzing the real-time extrusion speed based on the predicted traction speed to obtain an optimized extrusion speed; The real-time extrusion parameters are updated according to the optimized extrusion speed, and the optimized extrusion parameters are output.

Images