Production method of chinlon insulating rope

Abstract

The invention provides a production method of a chinlon insulating rope, which comprises the following steps: acquiring production process parameters of the chinlon insulating rope, including viscosity of an impregnating material, heat treatment temperature and cooling speed, determining a formula of the impregnating material and a heat treatment process curve according to the process parameters, and optimizing the formula and the process parameters to obtain the chinlon insulating rope. The optimal viscosity range of the impregnating material and the optimal temperature and cooling speed of heat treatment are obtained; the viscosity of the impregnating material in the impregnating tank is monitored in real time by adopting the online viscosity monitoring system, and if the detected viscosity exceeds the optimal range, the formula of the impregnating material is adjusted through the automatic batching system to ensure that the viscosity of the impregnating material is always in the optimal range, so that the impregnating material has good flowability and permeability; the infrared thermal imaging technology is adopted to monitor the surface temperature distribution of the impregnated chinlon insulating rope in real time, the temperature distribution of a thermal treatment furnace is dynamically adjusted according to monitoring data, it is ensured that all parts of the chinlon insulating rope are evenly heated, and chemical reaction of impregnated materials caused by local overheating is avoided.

Description

Technical Field

[0001] This invention relates to the field of insulating rope preparation, and more particularly to a method for producing nylon insulating rope. Background Technology

[0002] During the impregnation process of nylon insulating rope, the viscosity and flowability of the impregnation material directly affect the uniformity of the material distribution on the nylon insulating rope. If the impregnation material has too high a viscosity and poor flowability, it will be difficult to evenly cover every part of the nylon insulating rope during the impregnation process, resulting in local material accumulation and forming weak points in the insulation. If the impregnation material has too low a viscosity and excessive flowability, material loss is likely to occur during the impregnation process, resulting in uneven insulation layer thickness and affecting the stability of insulation performance.

[0003] Furthermore, controlling the heating temperature and cooling rate during the post-impregnation heat treatment process is crucial. If the heating temperature is too low, the impregnating material lacks fluidity and struggles to penetrate the tiny gaps in the nylon fibers, resulting in a weak bond between the insulation layer and the nylon fibers. If the heating temperature is too high, it may cause a chemical reaction in the impregnating material, affecting its insulation performance. During the cooling process, if the cooling rate is too fast, uneven stress can easily occur within the impregnating material, leading to micro-cracks in the insulation layer and reducing its insulation performance and durability. If the cooling rate is too slow, it will prolong the production cycle and reduce production efficiency. Therefore, ensuring uniform distribution of the impregnating material while precisely controlling the temperature and speed parameters during the heat treatment process is a key technical challenge in producing high-quality nylon insulating rope. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method for producing nylon insulating rope that can precisely control the temperature and speed parameters during the heat treatment process while ensuring uniform distribution of the impregnating material.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is: a method for producing nylon insulating rope, the innovation of which is: including the following steps: S1: Obtain the production process parameters of nylon insulating rope, including the viscosity of the impregnating material, heat treatment temperature, and cooling rate. Determine the impregnating material formula and heat treatment process curve based on the process parameters. Optimize the formula and process parameters to obtain the optimal viscosity range of the impregnating material and the optimal heat treatment temperature and cooling rate. S2: Use an online viscosity monitoring system to monitor the viscosity of the impregnating material in the impregnation tank in real time. If the viscosity exceeds the optimal range, adjust the impregnating material formula through an automatic batching system. S3: Set multiple impregnation rollers in the impregnation tank. The surface of the impregnation rollers has spiral grooves. Control the movement trajectory and impregnation time of the nylon insulating rope in the impregnation tank by adjusting the impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing. S4: Use infrared thermal imaging technology to monitor the surface temperature distribution of the impregnated nylon insulating rope in real time. Dynamically adjust the temperature distribution of the heat treatment furnace based on the monitoring data to ensure uniform heating of all parts of the nylon insulating rope. S5: Multiple independent temperature control zones are set up in the heat treatment furnace. The temperature of each zone is independently controlled according to the movement trajectory of the nylon insulating rope in the furnace. S6: Computer vision technology is used to perform online detection of the surface morphology of the nylon insulating rope after heat treatment. Image processing algorithms are used to analyze whether there are micro-cracks on the surface of the insulation layer. If cracks are found, they are judged as insulation performance defects. Based on the detection results, the cooling speed of the heat treatment is optimized by adjusting the cooling fan speed or cooling water flow rate. S7: A mathematical model is established between the insulation performance of the nylon insulating rope and the production process parameters. Support vector regression algorithm is used to train the model on the production data to obtain a quantitative relationship between process parameters and insulation performance. This model is used to optimize process parameters to improve insulation performance and predict the impact of process parameter fluctuations on insulation performance, guiding the dynamic adjustment of process parameters.

[0006] Furthermore, step S1 specifically includes: Based on the production process requirements of nylon insulating rope, key process parameters such as the viscosity of the impregnation material, heat treatment temperature, and cooling rate were obtained. Based on the obtained process parameters, the initial values ​​of the impregnation material formulation and heat treatment process curve were determined through experiments and data analysis. Using orthogonal experimental design, multiple experimental schemes were designed within the parameter range of the impregnation material formulation and heat treatment process curve; Performance tests were conducted on the nylon insulating rope samples produced by each test scheme to obtain key quality index data such as insulation performance and mechanical strength. Based on the quality index data, a mathematical model was established using response surface methodology to establish the relationship between the impregnation material formulation and heat treatment process parameters and the performance of nylon insulating rope. Based on a mathematical model, the particle swarm optimization algorithm is used to solve for the optimal combination of impregnation material formulation and heat treatment process parameters under constraints. Through verification experiments, the optimized impregnation material formulation and heat treatment process parameters were determined, and the optimal viscosity range, optimal heat treatment temperature, and cooling rate of the impregnation material were obtained to guide the mass production of nylon insulating ropes.

[0007] Furthermore, step S2 specifically includes: The real-time viscosity data of the impregnating material in the impregnation tank is obtained through an online viscosity monitoring system. The obtained viscosity data is compared with the preset optimal viscosity range. If the viscosity is detected to be outside the optimal range, the automatic batching system is triggered. Based on the deviation between the current viscosity of the impregnating material and the optimal viscosity range, a machine learning algorithm is used to calculate the optimal ratio for adjusting the impregnating material formula. The automatic batching system then adds or reduces the corresponding raw materials according to the calculated optimal ratio, thereby achieving automatic adjustment of the impregnating material formula. After the impregnation material formula is adjusted, the viscosity data of the adjusted impregnation material is obtained again through the online viscosity monitoring system to determine whether the adjusted viscosity is within the optimal range. If it is still not within the optimal range, the formula adjustment steps are repeated until the viscosity of the impregnation material is stable within the optimal range. By monitoring and automatically adjusting the viscosity of the impregnation material in real time, the impregnation material is always kept within the optimal viscosity range, thereby ensuring that the impregnation material has good fluidity and can pass smoothly through the conveying pipe in the impregnation tank and penetrate evenly onto the surface of the substrate. Machine vision technology is used to image and analyze the surface of the substrate after impregnation. Image processing algorithms are used to calculate the uniformity of the distribution of the impregnation material on the substrate surface. The permeability of the impregnation material is judged based on the uniformity of distribution. If the permeability does not meet the standard, the process returns to the impregnation material formulation adjustment step to further optimize the formulation. Viscosity monitoring data, formulation adjustment data, and permeation performance analysis data of the impregnating material are uploaded to the industrial internet platform. Big data analysis technology is used to explore the correlation between various parameters, forming a knowledge base for impregnating material formulation optimization, which provides decision support for subsequent formulation optimization. The online viscosity monitoring system, automatic batching system, and machine vision system are integrated and managed to form an intelligent impregnation material performance optimization control system. This system enables full-process monitoring and closed-loop control of impregnation material performance, ensuring the stability of the production process and the consistency of product quality.

[0008] Furthermore, step S3 specifically includes: Based on the diameter of the nylon insulating rope and the viscosity of the impregnation material, determine the initial values ​​of the diameter of the impregnation roller, the depth of the spiral groove, the angle of the spiral groove, and the spacing between the spiral grooves; The real-time position coordinates of the nylon insulating rope in the impregnation tank are obtained. Based on the position coordinates, it is determined whether the nylon insulating rope is moving along the preset trajectory. If it deviates from the preset trajectory, the speed of the impregnation roller is dynamically adjusted to make the nylon insulating rope move along the preset trajectory. The real-time coverage of the impregnating material on the surface of the nylon insulating rope is obtained. Based on the coverage, it is determined whether the impregnating material evenly covers the surface of the nylon insulating rope. If the coverage is uneven, the spiral groove depth and spiral groove spacing are dynamically adjusted to make the impregnating material evenly cover the surface of the nylon insulating rope. The real-time thickness of the insulation layer of the nylon insulated rope is obtained. Based on the thickness, it is determined whether the insulation layer thickness is uniform. If the thickness is not uniform, the spiral groove angle is dynamically adjusted to make the insulation layer thickness uniform. Machine vision technology is used to detect surface defects of nylon insulating rope in real time. Based on the defect type and area, the speed of the impregnation roller, the depth of the spiral groove, the angle of the spiral groove and the spacing of the spiral groove are dynamically adjusted to eliminate defects. Using deep learning algorithms, a correlation model is established between the impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing and the uniformity of the insulation layer thickness of the nylon insulating rope, based on historical process parameters and product quality data. This model is used to guide the dynamic optimization of process parameters. Online measurement data of the insulation layer thickness of nylon insulated rope is obtained. Statistical process control methods are used to determine whether the insulation layer thickness exceeds the control limit. If it does, an alarm is triggered and the cause is analyzed to optimize process parameters such as impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing.

[0009] Furthermore, step S4 specifically includes: Infrared thermal imaging technology is used to acquire temperature data of the surface of nylon insulating rope, and image processing algorithms are used to analyze the temperature distribution map to obtain the accurate temperature distribution. Based on temperature distribution data, the temperature settings inside the heat treatment furnace are adjusted through a control algorithm to achieve the preset temperature uniformity requirements. The surface temperature change of the nylon insulating rope is continuously tracked through a real-time monitoring system. If local overheating is detected, the temperature parameters of the heat treatment furnace are immediately adjusted to prevent chemical reactions from occurring. The temperature control strategy of the heat treatment furnace is dynamically optimized based on the temperature feedback of the nylon insulating rope through the data adjustment module, so as to ensure the temperature uniformity of the entire process. By utilizing temperature monitoring data, the heat treatment process is subjected to quality control. By analyzing the relationship between temperature data and the quality of nylon insulating rope, production parameters are optimized to improve product quality. By establishing a correlation model between temperature and chemical reaction, potential quality problems can be predicted and avoided, ensuring the processing quality of nylon insulating ropes.

[0010] Furthermore, step S5 includes: By setting up sensors to monitor the real-time temperature of each temperature control zone, and by adjusting the output of the heating element through a feedback control system, the temperature of each zone is ensured to reach the preset value. Sensor data will be transmitted to the central control system in real time, and the temperature distribution will be optimized through data analysis software to adjust the temperature setting to adapt to the movement path and speed of the nylon insulated rope. A high-precision flow controller is used to control the supply of impregnation material, ensuring uniform coating of the material on the surface of the nylon insulating rope; The flow controller adjusts the flow based on the movement speed of the nylon insulating rope and the temperature data inside the furnace. The algorithm optimizes the fluidity and permeability of the material to improve the quality of the insulation layer. Machine learning algorithms are used to analyze the temperature data and impregnation effect of nylon insulating rope during the heat treatment process, and the temperature of the temperature control zone and the flow rate of the impregnation material are automatically adjusted. The algorithm models based on historical data to predict the optimal temperature and material supply parameters in order to achieve the best bonding force between the insulation layer and the fiber. By using an integrated software platform, data on temperature control, material supply, and quality analysis can be centrally managed and monitored, thereby improving production efficiency and product quality. The platform supports real-time data visualization, helping operators quickly identify problems and make adjustments. Through the above steps, the heat treatment and material impregnation process of nylon insulating rope will be highly automated and optimized, ensuring that each section of nylon insulating rope is treated under optimal temperature and material conditions, thereby improving the overall performance and reliability of the product.

[0011] Furthermore, step S6 includes: A high-resolution camera was used to acquire real-time images of the surface of the heat-treated nylon insulating rope to obtain surface morphology data. Image preprocessing algorithms are used to denoise and enhance the acquired images, thereby improving image quality and facilitating subsequent feature extraction. The preprocessed image was analyzed using an edge detection algorithm to identify the micro-crack features on the surface of the insulating layer; If crack features are detected, it is determined that the section of nylon insulated rope has an insulation performance defect, and the defect location information is recorded; Based on the severity and distribution of crack detection results, calculate the cooling fan speed adjustment coefficient and cooling water flow rate adjustment coefficient; The calculated adjustment coefficients are transmitted to the cooling control system to adjust the cooling fan speed and cooling water flow in real time, thereby optimizing the heat treatment cooling rate. By monitoring the adjusted cooling effect in real time and feeding it back to the image acquisition system, a closed-loop control is formed to continuously optimize the cooling parameters, ensure uniform stress distribution within the insulation layer, and avoid the generation of microcracks.

[0012] Furthermore, step S7 specifically includes: Obtain the process parameters and corresponding insulation performance data during the production of nylon insulating rope, and establish a dataset; The data is preprocessed to remove outliers and then normalized. A mathematical model is trained using the support vector regression algorithm, with process parameters as input and insulation performance as output. The hyperparameters of the model are determined through cross-validation; Based on the trained mathematical model, analyze the quantitative relationship between each process parameter and insulation performance, and determine the key process parameters; For key process parameters, an optimization algorithm is used to search for the optimal parameter combination to obtain the optimized process parameters, which are then verified and adjusted in production. During the production process, process parameter data is collected in real time, input into a mathematical model for prediction, and the impact of process parameter fluctuations on insulation performance is determined. If the predicted insulation performance exceeds the threshold range, an early warning will be triggered. Based on the early warning information, relevant process parameters are dynamically adjusted and controlled within a reasonable range to ensure the stability of the insulation performance of nylon insulated rope; At the same time, production data is fed back to continuously optimize the mathematical model.

[0013] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention discloses a method for producing nylon insulating rope. An online viscosity monitoring system monitors the viscosity of the impregnating material in real time, and an automatic batching system dynamically adjusts the formula to ensure the viscosity of the impregnating material remains within the optimal range. Multiple impregnation rollers with spiral grooves control the movement trajectory of the nylon insulating rope within the impregnation tank, improving the uniformity of the insulation layer thickness. Infrared thermal imaging technology is used to monitor the surface temperature distribution of the nylon insulating rope, combined with a multi-zone independently temperature-controlled heat treatment furnace to achieve precise temperature field control, improving the bonding strength between the insulation layer and the fiber. Computer vision technology is used to detect microcracks on the insulation layer surface, and the cooling process is optimized accordingly. A mathematical model of process parameters and insulation performance is established, and support vector regression algorithm is used for optimization and prediction. This invention, through the integrated application of multiple advanced technologies, achieves comprehensive optimization of the nylon insulating rope production process, significantly improving the stability of insulation layer quality and performance, and providing technical support for the large-scale production of high-performance nylon insulating rope. Attached Figure Description

[0014] Figure 1This is a flowchart of the production method of the nylon insulating rope of the present invention.

[0015] Figure 2 This is a schematic diagram of the production method of the nylon insulating rope of the present invention.

[0016] Figure 3 This is another schematic diagram of the production method of the nylon insulating rope of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and thoroughly described below with reference to the accompanying drawings. The described embodiments are merely some embodiments of the present invention.

[0018] like Figure 1-3 As shown, the method for producing nylon insulating rope of the present invention is specifically implemented through the following steps: Step S101: Obtain the production process parameters for nylon insulating rope, including the viscosity of the impregnating material, heat treatment temperature, and cooling rate. Determine the impregnating material formula and heat treatment process curve based on the process parameters. By optimizing the formula and process parameters, obtain the optimal viscosity range of the impregnating material and the optimal heat treatment temperature and cooling rate.

[0019] Based on the production process requirements of nylon insulating rope, key process parameters such as the viscosity of the impregnating material, heat treatment temperature, and cooling rate were obtained. For these parameters, initial values ​​for the impregnating material formulation and heat treatment process curve were determined through experiments and data analysis. Using orthogonal experimental design, multiple experimental schemes were designed within the parameter range of the impregnating material formulation and heat treatment process curve. Performance tests were conducted on nylon insulating rope samples produced by each experimental scheme to obtain key quality index data such as insulation performance and mechanical strength. Based on the quality index data, a mathematical model was established using response surface methodology to establish the relationship between the impregnating material formulation, heat treatment process parameters, and the performance of the nylon insulating rope. Based on the mathematical model, a particle swarm optimization algorithm was used to solve for the optimal combination of impregnating material formulation and heat treatment process parameters under constraints. Through verification experiments, the optimized impregnating material formulation and heat treatment process parameters were determined, yielding the optimal viscosity range, optimal heat treatment temperature, and optimal cooling rate for the impregnating material, which will guide the mass production of nylon insulating rope.

[0020] For example, by consulting the production process data of nylon insulating rope, key parameters were obtained, including the viscosity of the impregnating material should be controlled at 800-1200 mPa·s, the heat treatment temperature at 150-180℃, and the cooling rate at 20-50 ℃ / min. Based on these parameters, single-factor and orthogonal experiments were conducted to preliminarily determine the impregnating material formula as 100 parts epoxy resin and 20 parts curing agent, with the heat treatment process curve being a heating to 160℃ and holding for 2 hours, followed by cooling to room temperature at a rate of 30 ℃ / min. Based on this, the Box-Behnken experimental design method was used, with the impregnating material formula, heat treatment temperature, and time as independent variables, and insulation resistance and tensile strength as response values, to design 15 sets of experiments. Through regression analysis, a quadratic polynomial mathematical model was established, and combined with particle swarm optimization, the optimal process parameters were obtained as follows: impregnating material viscosity 1000 mPa·s, heat treatment temperature 165℃, time 5 hours, and cooling rate 35 ℃ / min. Verification has shown that under these process conditions, the insulation resistance of the nylon insulated rope is ≥500 MΩ·km and the tensile strength is ≥15 kN, meeting the design requirements and can be used to guide mass production.

[0021] In step S102, an online viscosity monitoring system is used to monitor the viscosity of the impregnation material in the impregnation tank in real time. If the viscosity is detected to be outside the optimal range, the impregnation material formula is adjusted through an automatic batching system to ensure that the viscosity of the impregnation material is always within the optimal range, thereby ensuring that the impregnation material has good fluidity and permeability.

[0022] Real-time viscosity data of the impregnating material in the impregnation tank is acquired through an online viscosity monitoring system. This data is compared to a preset optimal viscosity range. If the viscosity exceeds the optimal range, an automatic batching system is triggered. Based on the deviation between the current viscosity and the optimal viscosity range, a machine learning algorithm calculates the optimal ratio for adjusting the impregnating material formulation. The automatic batching system then adds or removes the corresponding raw materials according to the calculated optimal ratio, achieving automatic adjustment of the impregnating material formulation. After the formulation adjustment is completed, the adjusted viscosity data is acquired again through the online viscosity monitoring system to determine if the adjusted viscosity is within the optimal range. If it is still not within the optimal range, the formulation adjustment steps are repeated until the viscosity of the impregnating material stabilizes within the optimal range. Through real-time monitoring and automatic adjustment of the impregnating material viscosity, it is ensured that the impregnating material remains within the optimal viscosity range, thereby guaranteeing good fluidity and allowing it to smoothly pass through the conveying pipes in the impregnation tank and evenly penetrate the substrate surface. Machine vision technology is used to image and analyze the surface of the substrate after impregnation. Image processing algorithms are used to calculate the uniformity of the impregnation material distribution on the substrate surface. The penetration performance of the impregnation material is judged based on the uniformity of distribution. If the penetration performance does not meet the standard, the process returns to the impregnation material formulation adjustment step for further optimization. Key parameters such as impregnation material viscosity monitoring data, formulation adjustment data, and penetration performance analysis data are uploaded to an industrial internet platform. Big data analytics are used to uncover the correlation patterns between these parameters, forming a knowledge base for impregnation material formulation optimization and providing decision support for subsequent formulation optimization. The online viscosity monitoring system, automatic batching system, and machine vision system are integrated and managed to form an intelligent impregnation material performance optimization control system. This system enables full-process monitoring and closed-loop control of impregnation material performance, ensuring the stability of the production process and the consistency of product quality.

[0023] For example, the online viscosity monitoring system collects viscosity data of the impregnating material in the impregnation tank every 5 seconds. When the viscosity exceeds the preset optimal range (e.g., 200-250 mPa·s), the automatic dispensing system calculates the required diluent dosage of 120 mL based on the deviation between the current viscosity and the target viscosity using a BP neural network algorithm. After adding the diluent, the viscosity decreases to 235 mPa·s, and the viscosity is retested and found to be acceptable. The machine vision system images the surface of the impregnated substrate and separates the impregnated and unimpregnated areas using an image segmentation algorithm. The calculated uniformity of the impregnated material distribution is 95%, meeting the requirements. The above data is uploaded to the industrial internet platform, and analysis using association rule mining algorithms reveals that when the ambient temperature exceeds 35℃, the viscosity of the impregnating material is prone to exceeding the control range, requiring advance adjustment of the formula. By coordinating the work of various subsystems through the integrated management system, real-time monitoring, automatic adjustment, and optimized control of the impregnating material performance are achieved, ensuring the stability of the production process and improving the product qualification rate by 3%.

[0024] Step S103: Multiple impregnation rollers are set in the impregnation tank. The surface of the impregnation rollers is provided with spiral grooves. By adjusting the speed of the impregnation rollers, the depth of the spiral grooves, the angle of the spiral grooves and the spacing of the spiral grooves, the movement trajectory and impregnation time of the nylon insulating rope in the impregnation tank are controlled to ensure that the impregnation material uniformly covers the surface of the nylon insulating rope and improves the uniformity of the insulation layer thickness.

[0025] Based on the diameter of the nylon insulating rope and the viscosity of the impregnating material, the initial values ​​of the impregnation roller diameter, spiral groove depth, spiral groove angle, and spiral groove spacing are determined. The real-time position coordinates of the nylon insulating rope within the impregnation tank are acquired. Based on these coordinates, it is determined whether the nylon insulating rope moves along the preset trajectory. If it deviates from the preset trajectory, the impregnation roller speed is dynamically adjusted to ensure the nylon insulating rope moves along the preset trajectory. The real-time coverage rate of the impregnating material on the surface of the nylon insulating rope is acquired. Based on the coverage rate, it is determined whether the impregnating material uniformly covers the surface of the nylon insulating rope. If the coverage is uneven, the spiral groove depth and spiral groove spacing are dynamically adjusted to ensure uniform coverage. The real-time thickness of the insulation layer of the nylon insulating rope is acquired. Based on the thickness, it is determined whether the insulation layer thickness is uniform. If the thickness is uneven, the spiral groove angle is dynamically adjusted to ensure uniform insulation layer thickness. Machine vision technology is used to detect surface defects of the nylon insulating rope in real time. Based on the defect type and defect area, the impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing are dynamically adjusted to eliminate defects. Using deep learning algorithms, a correlation model is established between the impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing and the uniformity of the insulation layer thickness of the nylon insulating rope, based on historical process parameters and product quality data. This model guides the dynamic optimization of process parameters. Online measurement data of the nylon insulating rope insulation layer thickness is acquired, and a statistical process control method is used to determine whether the insulation layer thickness exceeds the control limit. If it does, an alarm is triggered, the cause is analyzed, and process parameters such as impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing are optimized.

[0026] For example, based on the nylon insulating rope diameter of 2mm and the impregnation material viscosity of 500mPa·s, the initial values ​​of the impregnation roller diameter of 100mm, spiral groove depth of 5mm, spiral groove angle of 45°, and spiral groove spacing of 2mm were determined through finite element simulation. A laser displacement sensor was used to obtain the real-time position coordinates of the nylon insulating rope within the impregnation tank. A trajectory tracking algorithm was used to determine whether it deviated from the preset trajectory. When the deviation exceeded 1mm, a PID control algorithm dynamically adjusted the impregnation roller speed to keep the deviation within 1mm. Machine vision was used to obtain the impregnation material coverage. When the coverage was less than 95%, a fuzzy control algorithm dynamically adjusted the spiral groove depth and spacing to achieve a coverage of over 98%. An online thickness gauge was used to obtain the insulation layer thickness. When it exceeded the target value by ±0.5mm, a neural network algorithm dynamically adjusted the spiral groove angle to keep the thickness deviation within ±0.3mm. Surface defects were detected in real time using a convolutional neural network; defects with an area exceeding 1mm² were detected. 2 At that time, the genetic algorithm optimized the parameters of the impregnation roller, reducing the defect area to 0.5 mm. 2The following steps were taken: A decision tree algorithm was used to establish a correlation model between process parameters and insulation layer thickness uniformity. After optimization, the insulation layer thickness uniformity improved by 10%. A sigma algorithm was used to determine whether the insulation layer thickness exceeded the control limit. An alarm was triggered when it did, and the cause was analyzed using a fishbone diagram. After optimization, the insulation layer thickness control limit was reduced by 15%.

[0027] Step S104: Infrared thermal imaging technology is used to monitor the surface temperature distribution of the impregnated nylon insulating rope in real time. The temperature distribution of the heat treatment furnace is dynamically adjusted according to the monitoring data to ensure that all parts of the nylon insulating rope are heated evenly and to avoid local overheating that could cause a chemical reaction in the impregnating material.

[0028] Infrared thermal imaging technology is used to acquire temperature data of the nylon insulating rope surface. Image processing algorithms are then used to analyze the temperature distribution map, resulting in a precise temperature distribution. Based on this temperature distribution data, a control algorithm adjusts the temperature settings inside the heat treatment furnace to achieve the preset temperature uniformity requirements. A real-time monitoring system continuously tracks changes in the surface temperature of the nylon insulating rope. If localized overheating is detected, the furnace temperature parameters are immediately adjusted to prevent chemical reactions. A data adjustment module dynamically optimizes the furnace temperature control strategy based on temperature feedback from the nylon insulating rope, ensuring temperature uniformity throughout the entire process. Temperature monitoring data is used for quality control of the heat treatment process. By analyzing the relationship between temperature data and the quality of the nylon insulating rope, production parameters are optimized to improve product quality. A correlation model between temperature and chemical reactions is established to predict and avoid potential quality problems, ensuring the quality of the processed nylon insulating rope.

[0029] For example, an infrared thermal imager is used to scan the surface of the nylon insulating rope to obtain its temperature distribution image. An image segmentation algorithm is used to process the image, extracting the areas of the nylon insulating rope and calculating its average temperature to be 80℃ with a temperature difference range of ±2℃. Based on a preset target temperature of 85℃, a PID control algorithm calculates a temperature adjustment value of +5℃ for the heat treatment furnace and sends it to the furnace temperature control system. The real-time monitoring system samples the surface temperature of the nylon insulating rope every 5 seconds. When a local temperature exceeds 90℃, an alarm is immediately triggered, and the furnace temperature is lowered by 3℃. The data adjustment module uses a Kalman filter algorithm to filter the temperature data, eliminating interference factors, and dynamically adjusts the parameters of the PID controller according to the temperature change trend of the nylon insulating rope, making the furnace temperature control more stable. Statistical analysis of temperature monitoring data from 100 batches of nylon insulating rope shows a correlation coefficient of 8 between temperature uniformity and the tensile strength of the nylon insulating rope, based on which the heat treatment process parameters are optimized. Based on the chemical reaction kinetic model, the probability of nylon insulating rope undergoing degradation reaction above 100℃ is calculated to be 2%. Therefore, the overheat alarm temperature is set to 95℃ to prevent quality problems from occurring.

[0030] Step S105: Multiple independent temperature control zones are set up in the heat treatment furnace. The temperature of each temperature control zone is independently controlled according to the movement trajectory of the nylon insulating rope in the furnace. This achieves precise control of the temperature field of the nylon insulating rope in the furnace, allowing the impregnating material to flow fully on the surface of the nylon insulating rope and penetrate into the tiny gaps in the nylon fibers, thereby improving the bonding strength between the insulation layer and the nylon fibers.

[0031] Sensors monitor the real-time temperature of each temperature-controlled zone, and a feedback control system adjusts the output of heating elements to ensure that the temperature in each zone reaches the preset value. Sensor data is transmitted in real-time to the central control system, where data analysis software optimizes the temperature distribution, adjusting the temperature settings to accommodate the movement path and speed of the nylon insulation rope. A high-precision flow controller controls the supply of impregnating material, ensuring uniform coating on the nylon insulation rope surface. The flow controller's adjustment is based on the nylon insulation rope's movement speed and furnace temperature data, using algorithms to optimize material flowability and permeability, improving insulation layer quality. Machine learning algorithms analyze temperature data and impregnation effects during the heat treatment process, automatically adjusting the temperature of the temperature-controlled zones and the flow rate of the impregnating material. This algorithm, based on historical data modeling, predicts optimal temperature and material supply parameters to achieve optimal bonding strength between the insulation layer and the fiber. An integrated software platform centrally manages and monitors data from temperature control, material supply, and quality analysis, improving production efficiency and product quality. The platform supports real-time data visualization, helping operators quickly identify and address problems. Through the above steps, the heat treatment and material impregnation process of nylon insulating rope will be highly automated and optimized, ensuring that each section of nylon insulating rope is treated under optimal temperature and material conditions, thereby improving the overall performance and reliability of the product.

[0032] For example, during the heat treatment and material impregnation process of nylon insulating rope, temperature sensors are installed to monitor the temperature of each temperature-controlled zone in real time. If the real-time temperature of a certain zone is 230℃ and it falls below the set temperature of 240℃, the central control system adjusts the output power of the heating elements using a PID algorithm to quickly raise the temperature back to the set value. Simultaneously, sensor data is transmitted to the central control system in real time. Data analysis software, such as using K-means clustering, analyzes the temperature distribution, identifies abnormal temperature areas, and automatically adjusts the temperature setting to adapt to changes in the movement path and speed of the nylon insulating rope on the production line. For instance, when the nylon insulating rope accelerates through the heat treatment furnace, the system automatically increases the temperature setting of the preceding zone to ensure uniform heating of the material. A high-precision flow controller is used to adjust the supply of impregnation material based on the movement speed of the nylon insulating rope and the furnace temperature data. For example, for every 10m / min increase in the speed of the nylon insulating rope, the flow controller automatically increases the supply of impregnation material by 5%. Machine learning algorithms, such as Support Vector Machines (SVM), are used to analyze temperature data and impregnation effects during the heat treatment of nylon insulating rope. This allows for the automatic adjustment of temperature control zones and impregnation material flow rates to optimize the bonding force between the insulation layer and the fibers. The algorithm models historical data to predict optimal temperature and material supply parameters; for example, the model indicates that the bonding force between the insulation layer and fibers is optimal at 250°C and a material flow rate of 20 L / min. An integrated software platform centrally manages and monitors data related to temperature control, material supply, and quality analysis, improving production efficiency and product quality. The platform supports real-time data visualization, helping operators quickly identify and address problems. For instance, if a temperature distribution map shows a persistently low temperature in a certain area, the operator can quickly identify the cause and adjust the heating strategy. These highly automated and optimized measures ensure that every section of nylon insulating rope is processed under optimal temperature and material conditions, thereby improving the overall performance and reliability of the product.

[0033] Step S106: Computer vision technology is used to perform online inspection of the surface morphology of the heat-treated nylon insulating rope. Image processing algorithms are used to analyze whether there are microcracks on the surface of the insulation layer. If cracks are found, they are judged to be insulation performance defects. Based on the inspection results, the cooling rate of the heat treatment is optimized by adjusting the cooling fan speed or cooling water flow rate to avoid uneven stress in the insulation layer that could lead to microcracks.

[0034] A high-resolution camera is used to acquire real-time images of the surface of the heat-treated nylon insulating rope, obtaining surface morphology data. Image preprocessing algorithms are used to denoise and enhance the acquired images, improving image quality and facilitating subsequent feature extraction. Edge detection algorithms are then used to analyze the preprocessed images, identifying micro-cracks on the insulation surface. If a crack is detected, the section of nylon insulating rope is determined to have an insulation performance defect, and the defect location is recorded. Based on the severity and distribution of the crack detection results, cooling fan speed adjustment coefficients and cooling water flow rate adjustment coefficients are calculated. These calculated adjustment coefficients are transmitted to the cooling control system, which adjusts the cooling fan speed and cooling water flow rate in real time to optimize the heat treatment cooling rate. By monitoring the adjusted cooling effect in real time, feedback is sent to the image acquisition system, forming a closed-loop control system to continuously optimize cooling parameters, ensuring uniform stress distribution within the insulation layer and preventing the formation of micro-cracks.

[0035] For example, a high-resolution camera (12K resolution, 60fps) is used to acquire real-time images of the surface of the heat-treated nylon insulating rope to obtain surface morphology data. The image preprocessing algorithm uses adaptive median filtering to denoise the image, effectively removing random noise, and histogram equalization to enhance image contrast and improve image quality, facilitating subsequent feature extraction. The Canny edge detection algorithm is used to analyze the preprocessed image, setting a low threshold of 30 and a high threshold of 70 to accurately identify minute crack features on the insulation layer surface. If a crack feature is detected, it is determined that the nylon insulating rope section has an insulation performance defect, and the defect location information (such as crack length, width, and coordinate position) is recorded. Based on the severity and distribution of the crack detection results, the cooling fan speed adjustment coefficient and cooling water flow adjustment coefficient are calculated. The specific calculation process is as follows: First, the crack length and width are quantified into values ​​between 0 and 1, and the weighted average method is used to calculate the Comprehensive Crack Severity Index (CSI), with the formula: CSI = 6 * Length Index + 4 * Width Index. Then, adjustment coefficients are set in segments according to the CSI value. For example, when CSI is in the range of 0-3, the speed adjustment coefficient is 0, and the flow rate adjustment coefficient is 0; when CSI is in the range of 3-6, the speed adjustment coefficient is 2, and the flow rate adjustment coefficient is 1; when CSI is in the range of 6-0, the speed adjustment coefficient is 4, and the flow rate adjustment coefficient is 2. The calculated adjustment coefficients are transmitted to the cooling control system via the Modbus protocol to adjust the cooling fan speed (e.g., from 1000 rpm to 1200 rpm) and cooling water flow rate (e.g., from 10 L / min to 11 L / min) in real time, optimizing the heat treatment cooling rate. The adjusted cooling effect is monitored in real time by installing temperature sensors and infrared thermal imagers, collecting temperature data during the cooling process, and comparing it with the preset ideal cooling curve to calculate the temperature difference and cooling rate deviation. If the temperature difference exceeds ±5℃ or the cooling rate deviation exceeds 10%, the cooling parameters are further fine-tuned to ensure uniform stress distribution within the insulation layer and avoid microcrack formation. The system transmits real-time monitoring data and analysis results to the image acquisition system, forming a closed-loop control to continuously optimize cooling parameters and ensure the stability of the heat treatment process and product quality.

[0036] Step S107: Establish a mathematical model between the insulation performance of nylon insulating rope and production process parameters. Use a support vector regression algorithm to train the model on the production data to obtain a quantitative relationship between process parameters and insulation performance. Optimize process parameters using this model to improve insulation performance, and simultaneously predict the impact of process parameter fluctuations on insulation performance, guiding the dynamic adjustment of process parameters and ensuring the stability of insulation performance.

[0037] A dataset was created by acquiring process parameters and corresponding insulation performance data during the production of nylon insulated rope. The data was preprocessed to remove outliers and normalized. A mathematical model was trained using support vector regression, with process parameters as input and insulation performance as output. Hyperparameters of the model were determined through cross-validation. Based on the trained mathematical model, the quantitative relationship between each process parameter and insulation performance was analyzed to identify key process parameters. For these key process parameters, an optimization algorithm was used to search for the optimal parameter combination, resulting in optimized process parameters, which were then validated and adjusted in production. Process parameter data was collected in real-time during production and input into the mathematical model for prediction, assessing the impact of process parameter fluctuations on insulation performance. If the predicted insulation performance exceeded a threshold range, an early warning was triggered. Based on the early warning information, relevant process parameters were dynamically adjusted to control them within a reasonable range, ensuring the stability of the nylon insulated rope's insulation performance. Simultaneously, production data was fed back to continuously optimize the mathematical model.

[0038] For example, process parameter data and insulation performance data were first collected from the nylon insulating rope production line, including process parameters such as extrusion temperature, draw ratio, and cooling temperature, as well as performance indicators such as insulation resistance and withstand voltage, totaling 1000 sets of data. The data was cleaned using the 3σ criterion to remove outliers outside the normal range, and the data was mapped to the [0,1] interval using the maximum-minimum normalization method. A mathematical model was constructed using the support vector regression algorithm, with the normalized process parameters as input and insulation performance as output. The optimal hyperparameters C=10 and γ=1 were determined through grid search and 5-fold cross-validation, and the regression model was trained. Based on the model, the weight coefficients of each parameter were analyzed, revealing that extrusion temperature and cooling temperature are key factors affecting insulation performance. The particle swarm optimization algorithm was used to search for the optimal combination of these two key parameters, finding that when the extrusion temperature was 220℃ and the cooling temperature was 60℃, the model predicted an insulation resistance of over 100GΩ. In actual production, the process parameters were adjusted to this optimized combination, and testing showed a significant improvement in insulation performance, with the error compared to the model prediction within 5%. Simultaneously, an online monitoring system was deployed, collecting data every 5 minutes to input into the model for prediction. If the predicted insulation resistance was below 90 GΩ or the withstand voltage was below 5 kV, an early warning was issued. The automatic control system dynamically adjusted the extrusion and cooling temperatures, pulling the deviated parameters back to near the optimal operating point to ensure stable product performance. After one month of continuous operation, 500 sets of new production data were collected, supplementing the original dataset and retraining and optimizing the mathematical model. The entire process achieved data-driven intelligent production and quality control.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for producing nylon insulating rope, characterized in that: Includes the following steps: S1: Obtain the production process parameters of nylon insulating rope, including the viscosity of the impregnating material, heat treatment temperature, and cooling rate. Determine the impregnating material formula and heat treatment process curve based on the process parameters. Optimize the formula and process parameters to obtain the optimal viscosity range of the impregnating material and the optimal heat treatment temperature and cooling rate. S2: Use an online viscosity monitoring system to monitor the viscosity of the impregnating material in the impregnation tank in real time. If the viscosity exceeds the optimal range, adjust the impregnating material formula through an automatic batching system. S3: Set multiple impregnation rollers in the impregnation tank. The surface of the impregnation rollers has spiral grooves. By adjusting the impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing, control the movement trajectory and impregnation time of the nylon insulating rope in the impregnation tank. S4: Infrared thermal imaging technology is used to monitor the surface temperature distribution of the impregnated nylon insulation rope in real time, and the temperature distribution of the heat treatment furnace is dynamically adjusted according to the monitoring data to ensure that all parts of the nylon insulation rope are heated evenly. S5: Multiple independent temperature control zones are set up in the heat treatment furnace. The temperature of each zone is independently controlled according to the movement trajectory of the nylon insulating rope in the furnace. S6: Computer vision technology is used to perform online detection of the surface morphology of the nylon insulating rope after heat treatment. Image processing algorithms are used to analyze whether there are micro-cracks on the surface of the insulation layer. If cracks are found, they are judged as insulation performance defects. Based on the detection results, the cooling speed of the heat treatment is optimized by adjusting the cooling fan speed or cooling water flow rate. S7: A mathematical model is established between the insulation performance of the nylon insulating rope and the production process parameters. Support vector regression algorithm is used to train the model on the production data to obtain a quantitative relationship between process parameters and insulation performance. This model is used to optimize process parameters to improve insulation performance and predict the impact of process parameter fluctuations on insulation performance, guiding the dynamic adjustment of process parameters.

2. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S1 specifically includes: Based on the production process requirements of nylon insulating rope, key process parameters such as the viscosity of the impregnation material, heat treatment temperature, and cooling rate were obtained. Based on the obtained process parameters, the initial values ​​of the impregnation material formulation and heat treatment process curve were determined through experiments and data analysis. Using orthogonal experimental design, multiple experimental schemes were designed within the parameter range of the impregnation material formulation and heat treatment process curve; Performance tests were conducted on the nylon insulating rope samples produced by each test scheme to obtain key quality index data such as insulation performance and mechanical strength. Based on the quality index data, a mathematical model was established using response surface methodology to establish the relationship between the impregnation material formulation and heat treatment process parameters and the performance of nylon insulating rope. Based on a mathematical model, the particle swarm optimization algorithm is used to solve for the optimal combination of impregnation material formulation and heat treatment process parameters under constraints. Through verification experiments, the optimized impregnation material formulation and heat treatment process parameters were determined, and the optimal viscosity range, optimal heat treatment temperature, and cooling rate of the impregnation material were obtained to guide the mass production of nylon insulating ropes.

3. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S2 specifically includes: The real-time viscosity data of the impregnating material in the impregnation tank is obtained through an online viscosity monitoring system. The obtained viscosity data is compared with the preset optimal viscosity range. If the viscosity is detected to be outside the optimal range, the automatic batching system is triggered. Based on the deviation between the current viscosity of the impregnating material and the optimal viscosity range, a machine learning algorithm is used to calculate the optimal ratio for adjusting the impregnating material formula. The automatic batching system then adds or reduces the corresponding raw materials according to the calculated optimal ratio, thereby achieving automatic adjustment of the impregnating material formula. After the impregnation material formula is adjusted, the viscosity data of the adjusted impregnation material is obtained again through the online viscosity monitoring system to determine whether the adjusted viscosity is within the optimal range. If it is still not within the optimal range, the formula adjustment steps are repeated until the viscosity of the impregnation material is stable within the optimal range. By monitoring and automatically adjusting the viscosity of the impregnation material in real time, the impregnation material is always kept within the optimal viscosity range, thereby ensuring that the impregnation material has good fluidity and can pass smoothly through the conveying pipe in the impregnation tank and penetrate evenly onto the surface of the substrate. Machine vision technology is used to image and analyze the surface of the substrate after impregnation. Image processing algorithms are used to calculate the uniformity of the distribution of the impregnation material on the substrate surface. The permeability of the impregnation material is judged based on the uniformity of distribution. If the permeability does not meet the standard, the process returns to the impregnation material formulation adjustment step to further optimize the formulation. Viscosity monitoring data, formulation adjustment data, and permeation performance analysis data of the impregnating material are uploaded to the industrial internet platform. Big data analysis technology is used to explore the correlation between various parameters, forming a knowledge base for impregnating material formulation optimization, which provides decision support for subsequent formulation optimization. The online viscosity monitoring system, automatic batching system, and machine vision system are integrated and managed to form an intelligent impregnation material performance optimization control system. This system enables full-process monitoring and closed-loop control of impregnation material performance, ensuring the stability of the production process and the consistency of product quality.

4. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S3 specifically includes: Based on the diameter of the nylon insulating rope and the viscosity of the impregnation material, determine the initial values ​​of the diameter of the impregnation roller, the depth of the spiral groove, the angle of the spiral groove, and the spacing between the spiral grooves; The real-time position coordinates of the nylon insulating rope in the impregnation tank are obtained. Based on the position coordinates, it is determined whether the nylon insulating rope is moving along the preset trajectory. If it deviates from the preset trajectory, the speed of the impregnation roller is dynamically adjusted to make the nylon insulating rope move along the preset trajectory. The real-time coverage of the impregnating material on the surface of the nylon insulating rope is obtained. Based on the coverage, it is determined whether the impregnating material evenly covers the surface of the nylon insulating rope. If the coverage is uneven, the spiral groove depth and spiral groove spacing are dynamically adjusted to make the impregnating material evenly cover the surface of the nylon insulating rope. The real-time thickness of the insulation layer of the nylon insulated rope is obtained. Based on the thickness, it is determined whether the insulation layer thickness is uniform. If the thickness is not uniform, the spiral groove angle is dynamically adjusted to make the insulation layer thickness uniform. Machine vision technology is used to detect surface defects of nylon insulating rope in real time. Based on the defect type and area, the speed of the impregnation roller, the depth of the spiral groove, the angle of the spiral groove and the spacing of the spiral groove are dynamically adjusted to eliminate defects. Using deep learning algorithms, a correlation model is established between the impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing and the uniformity of the insulation layer thickness of the nylon insulating rope, based on historical process parameters and product quality data. This model is used to guide the dynamic optimization of process parameters. Online measurement data of the insulation layer thickness of nylon insulated rope is obtained. Statistical process control methods are used to determine whether the insulation layer thickness exceeds the control limit. If it does, an alarm is triggered and the cause is analyzed to optimize process parameters such as impregnation roller speed, spiral groove depth, spiral groove angle, and spiral groove spacing.

5. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S4 specifically includes: Infrared thermal imaging technology is used to acquire temperature data of the surface of nylon insulating rope, and image processing algorithms are used to analyze the temperature distribution map to obtain the accurate temperature distribution. Based on temperature distribution data, the temperature settings inside the heat treatment furnace are adjusted through a control algorithm to achieve the preset temperature uniformity requirements. The surface temperature change of the nylon insulating rope is continuously tracked through a real-time monitoring system. If local overheating is detected, the temperature parameters of the heat treatment furnace are immediately adjusted to prevent chemical reactions from occurring. The temperature control strategy of the heat treatment furnace is dynamically optimized based on the temperature feedback of the nylon insulating rope through the data adjustment module, so as to ensure the temperature uniformity of the entire process. By utilizing temperature monitoring data, the heat treatment process is subjected to quality control. By analyzing the relationship between temperature data and the quality of nylon insulating rope, production parameters are optimized to improve product quality. By establishing a correlation model between temperature and chemical reaction, potential quality problems can be predicted and avoided, ensuring the processing quality of nylon insulating ropes.

6. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S5 includes: By setting up sensors to monitor the real-time temperature of each temperature control zone, and by adjusting the output of the heating element through a feedback control system, the temperature of each zone is ensured to reach the preset value. Sensor data will be transmitted to the central control system in real time, and the temperature distribution will be optimized through data analysis software to adjust the temperature setting to adapt to the movement path and speed of the nylon insulated rope. A high-precision flow controller is used to control the supply of impregnation material, ensuring uniform coating of the material on the surface of the nylon insulating rope; The flow controller adjusts the flow based on the movement speed of the nylon insulating rope and the temperature data inside the furnace. The algorithm optimizes the fluidity and permeability of the material to improve the quality of the insulation layer. Machine learning algorithms are used to analyze the temperature data and impregnation effect of nylon insulating rope during the heat treatment process, and the temperature of the temperature control zone and the flow rate of the impregnation material are automatically adjusted. The algorithm models based on historical data to predict the optimal temperature and material supply parameters in order to achieve the best bonding force between the insulation layer and the fiber. By using an integrated software platform, data on temperature control, material supply, and quality analysis can be centrally managed and monitored, thereby improving production efficiency and product quality. The platform supports real-time data visualization, helping operators quickly identify problems and make adjustments. Through the above steps, the heat treatment and material impregnation process of nylon insulating rope will be highly automated and optimized, ensuring that each section of nylon insulating rope is treated under optimal temperature and material conditions, thereby improving the overall performance and reliability of the product.

7. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S6 includes: A high-resolution camera was used to acquire real-time images of the surface of the heat-treated nylon insulating rope to obtain surface morphology data. Image preprocessing algorithms are used to denoise and enhance the acquired images, thereby improving image quality and facilitating subsequent feature extraction. The preprocessed image was analyzed using an edge detection algorithm to identify the micro-crack features on the surface of the insulating layer; If crack features are detected, it is determined that the section of nylon insulated rope has an insulation performance defect, and the defect location information is recorded; Based on the severity and distribution of crack detection results, calculate the cooling fan speed adjustment coefficient and cooling water flow rate adjustment coefficient; The calculated adjustment coefficients are transmitted to the cooling control system to adjust the cooling fan speed and cooling water flow in real time, thereby optimizing the heat treatment cooling rate. By monitoring the adjusted cooling effect in real time and feeding it back to the image acquisition system, a closed-loop control is formed to continuously optimize the cooling parameters, ensure uniform stress distribution within the insulation layer, and avoid the generation of microcracks.

8. The method for producing nylon insulating rope according to claim 1, characterized in that: Step S7 specifically includes: Obtain the process parameters and corresponding insulation performance data during the production of nylon insulating rope, and establish a dataset; The data is preprocessed to remove outliers and then normalized. A mathematical model is trained using the support vector regression algorithm, with process parameters as input and insulation performance as output. The hyperparameters of the model are determined through cross-validation; Based on the trained mathematical model, analyze the quantitative relationship between each process parameter and insulation performance, and determine the key process parameters; For key process parameters, an optimization algorithm is used to search for the optimal parameter combination to obtain the optimized process parameters, which are then verified and adjusted in production. During the production process, process parameter data is collected in real time, input into a mathematical model for prediction, and the impact of process parameter fluctuations on insulation performance is determined. If the predicted insulation performance exceeds the threshold range, an early warning will be triggered. Based on the early warning information, relevant process parameters are dynamically adjusted and controlled within a reasonable range to ensure the stability of the insulation performance of nylon insulated rope; At the same time, production data is fed back to continuously optimize the mathematical model.

Images