Optical fiber production equipment cooperative control method and system based on Internet of Things

Abstract

The invention discloses an optical fiber production equipment cooperative control method and system based on the Internet of Things, and relates to the field of optical fiber production equipment control. Temperature distribution data and preform material parameters are collected in real time, a real-time temperature gradient and a material change index are determined, and then temperature gradient deviation and inter-equipment influence are analyzed in combination with a distributed calculation framework; and obtaining a temperature gradient deviation value and an influence coefficient between adjacent wire drawing equipment. When the temperature gradient deviation exceeds the standard, the neural network model predicts the influence of the material change on the temperature distribution, generates a heating power parameter and a wire drawing speed adjustment parameter, and implements cooperative regulation to optimize the temperature distribution, so that a production line temperature distribution optimization scheme is generated to perform cooperative control on the production speed of the wire drawing equipment; production stability and optical fiber quality are remarkably improved, and overall stability of production line temperature gradient and wire drawing speed is maintained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optical fiber production equipment control, and in particular to an optical fiber production equipment collaborative control method and system based on the Internet of Things. BACKGROUND

[0002] As a pillar industry in the field of modern communication and information technology, the quality of optical fiber products directly affects the stability and efficiency of data transmission. With the surge in global demand for high-speed networks, the refinement and scaling of optical fiber manufacturing have become the key to industry development. However, existing production equipment control methods often struggle to achieve dynamic coordination among multiple devices in complex production environments, leading to fluctuations in product quality, especially when raw materials change or environmental disturbances occur, resulting in insufficient production stability. This deficiency not only increases waste rates but also can affect the performance of optical fibers in extreme environments, becoming a bottleneck to the efficient development of the industry. In the process of optical fiber drawing, temperature control is a key link to ensure the uniformity of optical fiber diameter and performance stability.

[0003] Traditional methods usually rely on independent adjustment of a single device, lacking the ability to coordinate responses among multiple devices. When the material of the preform changes or the external environmental temperature fluctuates, the temperature distribution of each drawing furnace is difficult to maintain consistency. This inconsistency can cause temperature gradient imbalance, leading to overheating or overcooling of some devices, which in turn affects the matching of drawing speed. The lack of coordination between temperature and speed can directly cause small deviations in the diameter of the optical fiber, which may cause signal attenuation in high-speed communication and seriously affect product quality. The deeper challenge lies in the fact that the running states of multiple drawing devices on the production line affect each other, but existing technologies lack real-time monitoring and dynamic adjustment mechanisms. The unevenness of temperature distribution not only results from the lack of control accuracy of a single device, but also because of the lack of linkage in collaborative regulation among devices.

[0004] For example, when a drawing furnace abnormally increases in temperature due to changes in material, if the adjacent devices fail to adjust the heating power or drawing speed in time, the temperature gradient of the entire production line will deviate from the optimal range. This chain reaction makes it difficult for the production line to maintain stable process parameters, resulting in inconsistencies in optical fiber quality.

[0005] Therefore, how to dynamically adapt to changes in preform material and environmental temperature fluctuations through real-time monitoring and multi-device collaborative regulation to maintain the overall stability of the production line temperature gradient and drawing speed has become a key problem in the field of optical fiber production equipment control. SUMMARY

[0006] The present application provides an optical fiber production equipment collaborative control method and system based on the Internet of Things to achieve real-time monitoring and multi-device collaborative regulation to dynamically adapt to changes in preform material and environmental temperature fluctuations, and maintain the overall stability of the production line temperature gradient and drawing speed.

[0007] The application provides a fiber production equipment collaborative control method based on Internet of Things, which is executed by a computer and comprises the following steps of: determining a real-time temperature gradient based on temperature distribution data of each drawing equipment and determining a material quality change index based on material quality parameter information of each drawing equipment; determining a temperature state of the current production line based on the real-time temperature gradient and determining a material quality adaptation demand value based on the material quality change index; based on the temperature state and the material quality adaptation demand value, processing the temperature data correlation between the drawing equipments by using a distributed computing framework, determining a temperature gradient deviation value and an influence coefficient between adjacent drawing equipments; if the temperature gradient deviation value exceeds a preset deviation threshold value, predicting the potential influence of material quality change on temperature distribution by using a neural network model based on the influence coefficient, and obtaining a heating power parameter and a drawing speed correction parameter; based on the heating power parameter and the drawing speed correction parameter, performing collaborative control optimization on each drawing equipment to obtain a production line temperature distribution optimization scheme; based on the production line temperature distribution optimization scheme, updating the linkage control logic between the drawing equipments to collaboratively control the production speed of the drawing equipment.

[0008] According to the fiber production equipment collaborative control method based on Internet of Things, the temperature state and the material quality adaptation demand value are used to process the temperature data correlation between the drawing equipments by using a distributed computing framework, to determine a temperature gradient deviation value and an influence coefficient between adjacent drawing equipments, which comprises the following steps of: based on the temperature distribution data, determining a standardized temperature data set; based on the standardized temperature data set, performing partition processing by using a distributed computing framework, calculating the temperature difference between the devices, and determining the temperature gradient distribution; if the temperature gradient distribution exceeds a preset gradient threshold value, adjusting the data weight of each temperature gradient by using a weighted average algorithm to obtain a corrected temperature gradient value; based on the corrected temperature gradient value, calculating the temperature correlation between adjacent drawing equipments by using a Pearson correlation coefficient to determine the influence coefficient.

[0009] According to the fiber production equipment collaborative control method based on Internet of Things, if the temperature gradient deviation value exceeds a preset deviation threshold value, the potential influence of material quality change on temperature distribution is predicted by using a neural network model based on the influence coefficient, and a heating power parameter and a drawing speed correction parameter are obtained, which comprises the following steps of: If the temperature gradient deviation exceeds a preset deviation threshold, the temperature gradient deviation and the preform material parameter information are analyzed by a neural network model to obtain a temperature distribution prediction result; Based on the temperature distribution prediction result, the heating power parameter and the adjustment range of the heating power parameter are determined; Based on the adjustment range, an initial correction value of the drawing speed is determined; If the initial correction value does not meet the preset drawing speed value required for production stability, the drawing speed is adjusted by an iterative optimization algorithm to determine the drawing speed correction parameter.

[0010] According to the optical fiber production equipment collaborative control method based on the Internet of Things, the heating power parameter and the drawing speed correction parameter are used to perform collaborative control optimization on each drawing equipment to obtain a production line temperature distribution optimization scheme, which includes: Based on the heating power parameter and the drawing speed correction parameter, the running data of each drawing equipment is collected in real time to obtain a drawing furnace state; The drawing furnace state is compared with a preset production line temperature consistency requirement to determine an abnormal drawing equipment with temperature anomaly; Based on the abnormal drawing equipment, a collaborative control instruction is generated; Based on the collaborative control instruction, the heating power parameter and the drawing speed correction parameter are adjusted to obtain a process parameter adjustment scheme; Based on the process parameter adjustment scheme, the collaborative control instruction is issued to each drawing equipment to obtain a control execution efficiency and production line temperature data corresponding to the control execution efficiency; Based on the production line temperature data, a temperature distribution optimization scheme is generated.

[0011] According to the optical fiber production equipment collaborative control method based on the Internet of Things, based on the production line temperature distribution optimization scheme, the linkage control logic between each drawing equipment is updated to collaboratively control the production speed of the drawing equipment, which includes: Based on the production line temperature distribution optimization scheme, the linkage control logic between each drawing equipment is updated to determine a dynamic adjustment range of speed matching; If the dynamic adjustment range shows discordance, a support vector machine algorithm is used to analyze the interference factors of environmental fluctuations on speed matching to determine a speed synchronization compensation value between the drawing equipment; Based on the speed synchronization compensation value, the overall calibration of the production line speed is performed to obtain calibrated diameter measurement data, and based on the diameter measurement data, an uniformity index of the optical fiber diameter is determined; Based on the uniformity index, the effectiveness of multi-equipment collaborative response is verified to obtain a production stability confirmation result; If the production stability confirmation result passes, the linkage control logic between each drawing equipment is updated to cooperatively control the production speed of the drawing equipment.

[0012] According to the optical fiber production equipment cooperative control method based on the Internet of Things, the linkage control logic between each drawing equipment is updated based on the production line temperature distribution optimization scheme to determine the dynamic adjustment range of speed matching, which includes: Based on the production line temperature distribution optimization scheme, real-time temperature monitoring data is obtained to determine the environmental temperature value; If the environmental temperature value exceeds the preset temperature threshold, the equipment operating speed is adjusted through the control logic to obtain a speed adjustment parameter; Based on the speed adjustment parameter, a distributed control algorithm is used to update the linkage state of the equipment to determine a cooperative operation mode; Based on the cooperative operation mode, real-time feedback data between the drawing equipment is obtained; If the data consistency index of the real-time feedback data is lower than the preset standard index, the temperature monitoring data is corrected through a data processing module to obtain corrected temperature data; Based on the corrected temperature data, a dynamic programming algorithm is used to optimize the speed matching range to determine the dynamic adjustment range.

[0013] According to the optical fiber production equipment cooperative control method based on the Internet of Things, if the dynamic adjustment range shows uncoordination, a support vector machine algorithm is used to analyze the interference factors of environmental fluctuations on speed matching to determine the speed synchronization compensation value between the drawing equipment, which includes: If the dynamic adjustment range shows uncoordination, environmental fluctuation data is collected to obtain an environmental variable data set, wherein the environmental variable data set includes real-time values of temperature, humidity, and vibration frequency; Based on the environmental variable data set, a mapping relationship between environmental fluctuations and speed synchronization deviation is determined through a support vector machine algorithm to obtain a prediction model and an output deviation of the prediction model; If the output deviation exceeds the preset deviation threshold, the feature weight of the prediction model is adjusted to obtain optimized model parameters; Based on the prediction model corresponding to the optimized model parameters, the interference of real-time environmental variables on speed matching is analyzed to obtain the weight distribution of interference factors; Based on the weight distribution of interference factors, the speed synchronization compensation value between the drawing equipment is determined.

[0014] The application also provides an optical fiber production equipment cooperative control system based on the Internet of Things, which includes: The index determination module is used to determine the real-time temperature gradient based on the temperature distribution data of each wire drawing equipment, and to determine the material change index based on the preform material parameter information of each wire drawing equipment. The status determination module is used to determine the temperature status of the current production line based on the real-time temperature gradient, and to determine the material adaptation requirement value based on the material change index. The influence coefficient determination module is used to process the temperature data correlation between each drawing device based on the temperature state and material adaptation requirements, and to determine the temperature gradient deviation value and the influence coefficient between adjacent drawing devices using a distributed computing framework. The parameter determination module is used to predict the potential impact of material changes on temperature distribution based on the influence coefficient and a neural network model if the temperature gradient deviation value exceeds a preset deviation threshold, thereby obtaining heating power parameters and wire drawing speed correction parameters. The control and optimization module is used to perform coordinated control and optimization on each wire drawing equipment based on the heating power parameters and the wire drawing speed correction parameters, so as to obtain an optimized temperature distribution scheme for the production line. The collaborative control module is used to update the linkage control logic between each wire drawing device based on the temperature distribution optimization scheme of the production line, so as to collaboratively control the production speed of the wire drawing device.

[0015] This invention provides an IoT-based collaborative control method and system for optical fiber production equipment. Addressing the issue of uneven temperature distribution, insufficient material adaptability, and speed synchronization deviations between equipment leading to fiber diameter uniformity problems, the method collects real-time temperature distribution data and preform material parameters to determine real-time temperature gradients and material change indicators. Then, it uses a distributed computing framework to analyze temperature gradient deviations and inter-equipment influences, obtaining temperature gradient deviation values ​​and influence coefficients between adjacent drawing equipment. This allows for accurate assessment of production line stability through temperature gradient deviations and influence coefficients. When the temperature gradient deviation exceeds the limit, a neural network model predicts the impact of material changes on temperature distribution, generating heating power parameters and drawing speed adjustment parameters. Collaborative control is then implemented to optimize temperature distribution, generating a production line temperature distribution optimization scheme. Finally, through the optimized production line temperature distribution scheme, the linkage control logic between each drawing equipment is updated to collaboratively control the production speed of the drawing equipment, significantly improving production stability and optical fiber quality. This solves the problems of complex and inefficient control in traditional production lines, achieving dynamic adaptation to preform material changes and environmental temperature fluctuations through real-time monitoring and multi-equipment collaborative control, maintaining the overall stability of the production line temperature gradient and drawing speed. Attached Figure Description

[0016] Figure 1 This is one of the flowcharts illustrating a collaborative control method for optical fiber production equipment based on the Internet of Things provided in this embodiment of the invention; Figure 2 is a flowchart of a method for collaborative control of optical fiber production equipment based on the Internet of Things according to an embodiment of the present application; Figure 3 is a flowchart of a method for collaborative control of optical fiber production equipment based on the Internet of Things according to an embodiment of the present application; Figure 4 is a flowchart of a method for collaborative control of optical fiber production equipment based on the Internet of Things according to an embodiment of the present application; Figure 5 is a flowchart of a method for collaborative control of optical fiber production equipment based on the Internet of Things according to an embodiment of the present application; Figure 6 is a flowchart of a method for collaborative control of optical fiber production equipment based on the Internet of Things according to an embodiment of the present application; Figure 7 is a flowchart of a method for collaborative control of optical fiber production equipment based on the Internet of Things according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0018] With reference to Figure 1 The embodiment of the present application provides a method for collaborative control of optical fiber production equipment based on the Internet of Things, which comprises the following steps: Step 100, determining a real-time temperature gradient based on temperature distribution data of each drawing equipment, and determining a material quality change index based on preform material quality parameter information of each drawing equipment; The collaborative analysis and dynamic evaluation of the temperature state of the drawing equipment and the material quality characteristics of the preform are performed to determine the real-time temperature gradient of the drawing equipment and the material quality change index. Specifically, first, the distributed temperature sensors deployed on each drawing equipment continuously collect multi-dimensional and high-density temperature field data in the heating furnace to obtain temperature distribution data, wherein the temperature distribution data are used for panoramic temperature sensing of the production environment. For example, the temperature distribution data are converged and fused through the Internet of Things platform, and a dynamic temperature distribution model reflecting the change law of the thermal field in the drawing furnace is constructed. Based on the dynamic temperature distribution model, the current temperature distribution data of the drawing equipment are obtained, and the temperature difference change rate of adjacent sensing areas or along the axial direction of the preform is calculated based on the temperature distribution data to obtain the real-time temperature gradient. The real-time temperature gradient not only represents the characteristics of the heating area in the temperature distribution.

[0019] Meanwhile, the preform rod material parameter information from the material management unit is processed in parallel. The preform rod material parameter information can include glass system composition, doping ion concentration, geometric size tolerance, and refractive index profile structure, and other key attributes. Therefore, by establishing a mapping relationship between the material parameters and the ideal drawing state, a material variation index can be constructed, which is used to quantify the matching degree of the current preform rod physical and chemical properties with the standard process window, and to reflect the instability risk of the drawing process caused by material fluctuations.

[0020] In step 200, the temperature state of the current production line is determined based on the real-time temperature gradient, and the material adaptation demand value is determined based on the material variation index. After obtaining the real-time temperature gradient and the material variation index, based on the real-time temperature gradient, the temperature state of the current entire production line is comprehensively determined and classified through a preset thermodynamic knowledge model, to obtain the temperature state of the current production line. The temperature state of the production line includes the working state of each drawing equipment and the heating state of the internal optical fiber, so this temperature state determination is a multi-dimensional evaluation process, which is used to describe the health and stability of the drawing equipment. For example, if the temperature gradient is gentle and stable, it means that the working state of the drawing equipment can be determined as an ideal forming state, indicating that the optical fiber is undergoing a uniform and controlled cooling process, and the internal structure integrity of the optical fiber is good. If the temperature gradient has local dramatic changes or deviates from the baseline as a whole, the working state of the drawing equipment can be identified as a thermal stress risk state or a non-optimal energy consumption state. Therefore, the generation of the temperature state enables the conversion of the original physical quantity data into the temperature state of the internal drawing equipment, which has direct production guidance significance, thereby providing a clear target and direction for the adjustment of the control strategy.

[0021] Meanwhile, the material variation index is analyzed to further determine the material adaptation demand value. The calculation of the material adaptation demand value is a dynamic mapping process, which can convert the static index representing the material properties into a dynamic control instruction for guiding the execution of the drawing equipment. Therefore, according to the material variation index indicating specific material properties, such as thermal response sensitivity or viscoelastic threshold, etc. The material adaptation demand value is essentially a quantitative regulation driving force, which can clearly indicate the adaptive changes made by the current production line to the preform rod material variation in terms of temperature setting, pulling speed or cooling rate, etc. For example, when the material variation index indicates that the core layer doping concentration of the preform rod is too high, the system may output a temperature increase adaptation demand value, indicating that the heating furnace needs to provide more energy to overcome the increase of the material softening point.

[0022] At step 300, based on the temperature state and the material adaptation demand value, a distributed computing framework is used to process the temperature data correlation between the drawing equipment, determine the temperature gradient deviation value and the influence coefficient between adjacent drawing equipment. After completing the diagnosis of the overall temperature state of the production line and the quantification of the material adaptation demand value, in order to process the massive data and dynamic correlation across equipment, a distributed computing framework is used to process the temperature state and the material adaptation demand value. It can be understood that the distributed computing framework can be understood as the digital nervous system of the production line, which is used for the edge computing nodes of each drawing equipment to process data while continuously interacting with the central coordination unit and task coordination through efficient communication protocols, thereby optimizing the computing load and improving the response speed.

[0023] The distributed computing framework is actually used to deeply mine and quantify the correlation of temperature data between the drawing equipment. By analyzing the space-time change sequence of the temperature field of adjacent or even all drawing equipment, it can accurately identify how the temperature fluctuation of a drawing equipment caused by process parameter adjustment or its own disturbance affects the temperature stability of its upstream or downstream or adjacent equipment through heat radiation, conduction or shared environmental medium. Therefore, based on the deep correlation analysis of the distributed computing framework, a temperature gradient deviation value is generated. It should be noted that the temperature gradient deviation value reflects the deviation of the real-time temperature gradient of each drawing equipment from the optimal gradient it should have in the current material adaptation demand and overall temperature state. Therefore, the generated temperature gradient deviation value can accurately locate the weak nodes of the drawing equipment in the process consistency on the production line.

[0024] Further, the distributed computing framework can also calculate the influence coefficient between adjacent drawing equipment according to the temperature state and the material adaptation demand value, for example, through complex correlation algorithms and historical running data models. The influence coefficient is a dynamic weight factor that quantifies the strength and direction of the mutual influence between any two adjacent equipment. For example, when the heating power of a drawing equipment changes significantly, the influence coefficient can be used to accurately predict the impact amplitude and phase delay of the change on the temperature field of the downstream drawing equipment.

[0025] At step 400, if the temperature gradient deviation value exceeds the preset deviation threshold, the neural network model is used to predict the potential influence of material change on temperature distribution based on the influence coefficient, and the heating power parameter and the drawing speed correction parameter are obtained. When it is determined that the temperature gradient deviation value of a certain drawing device exceeds the preset deviation threshold, it indicates that the current production state deviates from the ideal process window. Conventional local fine-tuning is not enough to cope with the complex working conditions caused by the combined effects of material changes and equipment coupling. Therefore, the inter-device influence coefficient determined in the previous step is used as one of the key inputs. Since the influence coefficient represents the path and intensity of the disturbance of any node in the production line spreading throughout the production line, it provides a causal relationship diagram for understanding the "chain reaction". Therefore, the neural network model trained on a large amount of historical process data can handle highly nonlinear relationships that are difficult to accurately model in traditional control methods. The neural network model can simulate and predict how the material changes interact with the temperature field in the future based on the current captured material change indicators and the deep integration of the inter-device dynamic correlation described by the influence coefficient. Thus, the influence of material changes on the temperature distribution of the drawing devices in the production line is predicted, and the prediction results include heating power parameters and drawing speed correction parameters.

[0026] The heating power parameters and the drawing speed correction parameters are the results of multi-dimensional optimization and trade-off of the neural network model in a large solution space. For example, in order to compensate for the accelerated thermal process caused by the decrease of the softening point of the material, it is necessary to appropriately reduce the heating power of the current problem device to curb the overheating trend, and to cooperatively fine-tune the drawing speed of the upstream and downstream devices to balance the changes in fiber tension that may be caused by power adjustment, so as to ensure that the fiber diameter stability and structural integrity are maintained while the temperature gradient is corrected.

[0027] Step 500, based on the heating power parameters and the drawing speed correction parameters, performing cooperative control optimization on each drawing device to obtain a production line temperature distribution optimization scheme; After generating the heating power parameter and the drawing speed correction parameter, in order to ensure the parameter adjustment of a single drawing equipment, not only the temperature gradient deviation of the single drawing equipment can be corrected accurately, but also the running state of other equipment on the production line can be positively coordinated, for example, through a multi-objective optimization algorithm, taking the heating power parameter and the drawing speed correction parameter as inputs, and simultaneously considering the dynamic coupling relationship between the equipment described by the influence coefficient, the temperature distribution optimization scheme of the production line can be calculated by simulating the temperature distribution response under different parameter combinations, wherein the temperature distribution optimization scheme of the production line includes the best power setting value and the best drawing speed value that each drawing equipment should execute, that is, the target heating power and the target drawing speed. Therefore, by moderately adjusting the drawing speed of the upstream equipment to match the change of the heating power of the downstream equipment, the stability of the optical fiber tension can be maintained; or, while correcting the power of the problem equipment, the power of the adjacent equipment is slightly pre-adjusted as compensation to actively offset the known inter-equipment influence and prevent corrective intervention from causing new secondary disturbance.

[0028] It should be noted that the target heating power and the target drawing speed are parameter sets after global optimization calculation, which are systematically integrated and packaged to form a complete and executable production line temperature distribution optimization scheme. Further, the production line temperature distribution optimization scheme can be a dynamic and interrelated control instruction set, which includes how each drawing equipment on the production line should adjust its own behavior in step with each other, so that the production line can intelligently and efficiently return to the optimal process track from the non-ideal state caused by material fluctuations or external disturbances, and ensure that the optical fiber product can continuously meet the required physical and optical performance indicators.

[0029] Step 600, based on the production line temperature distribution optimization scheme, updating the linkage control logic between the drawing equipments to cooperatively control the production speed of the drawing equipments.

[0030] After generating the global production line temperature distribution optimization scheme, the production line temperature distribution optimization scheme contains the parameter setting of each wire drawing equipment on the production line, and then the new power and speed matching relationship between each wire drawing equipment analyzed in the production line temperature distribution optimization scheme is refined into the updated cooperative rule and response strategy. The cooperative rule is injected into each device control node under the Internet of Things architecture in real time, thereby refreshing the linkage logic between them, so as to realize the cooperative control of the production speed of each wire drawing equipment on the production line. For example, the new logic may clearly indicate that when it is detected that a wire drawing equipment located in the production line needs to increase the heating power due to the change of the preform material, the two adjacent devices upstream thereof must pre-adjust the speed by a certain proportion of the current wire drawing speed to cope with the change of the glass viscosity caused by the temperature rise, so as to jointly maintain the constant tension of the optical fiber.

[0031] Finally, the updated linkage control logic is used for fine cooperative control of the production speed of all wire drawing equipment. The control system controls the heating power of each wire drawing equipment according to the updated logic as the criterion, more accurately coordinates the wire drawing speed of each wire drawing equipment, and ensures the balance of the entire production line. This makes the production line change from a mechanical set that passively executes instructions to an overall body that can actively maintain internal balance and dynamically damp external disturbances. By updating the linkage control logic in real time according to the material change and temperature change, the optical fiber production system has a self-optimizing intelligence, which can always anchor the process state within the optimal interval under changing production conditions.

[0032] The optical fiber production equipment cooperative control method based on the Internet of Things provided by the application can solve the problem of optical fiber diameter uniformity caused by uneven temperature distribution, insufficient material adaptability and speed synchronization deviation between devices. Real-time temperature distribution data and preform material parameters are collected to determine real-time temperature gradient and material change index. Then, the temperature gradient deviation and the influence between devices are analyzed by combining the distributed computing framework to obtain the temperature gradient deviation value and the influence coefficient between adjacent wire drawing equipment, so that the production line stability can be accurately judged by the temperature gradient deviation and the influence coefficient. When the temperature gradient deviation exceeds the standard, the neural network model predicts the influence of material change on temperature distribution, generates heating power parameters and wire drawing speed adjustment parameters, and implements cooperative control to optimize the temperature distribution, thereby generating a production line temperature distribution optimization scheme. Finally, the linkage control logic between each wire drawing equipment is updated through the production line temperature distribution optimization scheme to cooperatively control the production speed of the wire drawing equipment, significantly improve the production stability and optical fiber quality, solve the problems of complex and low-efficiency control of traditional production lines, and realize dynamic adaptation to preform material changes and environmental temperature fluctuations by real-time monitoring and multi-device cooperative control, thereby maintaining the overall stability of the production line temperature gradient and the wire drawing speed.

[0033] In an embodiment, referring to Figure 2 , the temperature data correlation between the drawing devices is processed by using a distributed computing framework based on the temperature state and the material quality adaptation requirement value, a temperature gradient deviation value and an influence coefficient between adjacent drawing devices are determined, comprising: Step 301, based on the temperature distribution data, a standardized temperature data set is determined; Step 302, based on the standardized temperature data set, a distributed computing framework is used for partition processing, a temperature difference value between devices is calculated, and a temperature gradient distribution is determined; Step 303, if the temperature gradient distribution exceeds a preset gradient threshold, the data weight of each temperature gradient is adjusted by a weighted average algorithm, and a corrected temperature gradient value is obtained; Step 304, based on the corrected temperature gradient value, the temperature correlation between adjacent drawing devices is calculated by using a Pearson correlation coefficient, and the influence coefficient is determined.

[0034] The purpose of this step is to convert the original, heterogeneous temperature data into high-value information that can accurately guide collaborative control. First, the temperature distribution data collected from each drawing device is standardized and preprocessed to eliminate the problem of inconsistent dimensions and benchmarks caused by individual differences of sensors or local environmental fluctuations, thereby forming a pure and comparable standardized temperature data set.

[0035] Then, the generated standardized data set is efficiently partitioned and processed in parallel by using the computing power of the distributed computing framework. In this step, the entire production line is not considered as a chaotic whole, but is intelligently divided into multiple logical temperature influence areas, and the real-time temperature difference between devices in each temperature influence partition is calculated in parallel. By analyzing these spatial differences, a temperature gradient distribution map that accurately depicts the steepness of the thermal field change is constructed. The temperature gradient distribution map reveals the flow trend and concentration of thermal energy on the production line, providing intuitive data visualization for identifying unstable process areas.

[0036] When it is detected that the temperature gradient distribution of a certain area exceeds the preset safe process threshold, it indicates that there may be a risk of thermal stress concentration or energy waste at that place. In order to handle this exception, the historical stability of each temperature data point and its importance in spatial distribution are dynamically adjusted by using a weighted average algorithm to adjust the weight of each data point in the calculation, so that the data points disturbed by instantaneous noise are automatically suppressed, and the data of the true process trend can be strengthened. By adjusting the data weight of each temperature gradient by using the weighted average algorithm, a more reliable corrected temperature gradient value after noise filtering and trend strengthening is output, which significantly improves the robustness of state perception.

[0037] Finally, the corrected temperature gradient value is taken as input, and the Pearson correlation coefficient is used as a statistical tool to analyze the synchronization and directionality of temperature changes between any adjacent wire drawing equipment. The influence coefficient between the equipment can be accurately determined to the extent that the temperature fluctuations of one equipment can be explained by the fluctuations of its adjacent equipment. It should be noted that this influence coefficient is a key indicator that accurately reflects the strength of the thermal dynamic coupling between equipment, which is dynamically calculated based on real-time data.

[0038] For example, in a production line, the temperature state data of each equipment is first collected in real time by Internet of Things sensors, such as the temperature of equipment A being 85.2 degrees, equipment B being 78.5 degrees, and equipment C being 92.1 degrees. These data reflect the thermal stress distribution in a high-temperature processing environment, and also consider the material adaptation requirements, such as the heat resistance threshold of aluminum alloy material being 90 degrees and that of steel material being 95 degrees. By comparing the thresholds, it is determined that the temperatures of equipment A and C have approached or exceeded the aluminum alloy limit, and they need to be adjusted in priority to avoid material deformation. Under the distributed computing framework, these multi-equipment data are distributed to cluster nodes for parallel processing. The MapReduce model is used to correlate the temperature data as a spatio-temporal sequence, such as mapping the temperatures of equipment A, B, and C as the vector [85.2, 78.5, 92.1]. Then, the Pearson correlation coefficient is used to calculate the correlation strength between the temperatures, resulting in a correlation coefficient of 0.87 between equipment A and B, 0.92 between A and C, and 0.78 between B and C, indicating that the high-temperature propagation path mainly spreads from C to A. Subsequently, the finite difference method is used to calculate the temperature gradient deviation value, and the calculation formula is as follows: wherein, is the distance between equipment, and when is 1 meter, the gradient from A to B is calculated as 6.7 degrees / meter, and the gradient from B to C is calculated as -13.6 degrees / meter. The deviation value is calculated as 8.4 degrees / meter by the root mean square error with the ideal gradient of 3 degrees / meter, revealing the risk of local overheating. At the same time, the principal component analysis method is used to extract the influence coefficient of adjacent equipment, and the correlation matrix is decomposed into principal components. The influence coefficient of equipment C on A is 0.65, and the influence coefficient of A on B is 0.42, quantifying the influence of heat conduction to optimize the cooling strategy. Finally, based on these parameters, a stability index model is constructed, and the weighted summation method is used for calculation, and the formula is as follows: wherein, the weight = 0.6, = 0.4, and the stability index = 0.72 is calculated, indicating that the overall stability is at a medium level, and the automatic air cooling system needs to be activated to reduce the temperature of C to 88 degrees to improve S to 0.85, ensuring the continuous operation of the production line without interruption.

[0039] In this embodiment, the global complex computing task is decomposed into distributed parallel processing, which greatly improves the processing efficiency of massive temperature data and the real-time response speed of the system. The correlation analysis is dynamically applied to the quantification of the influence coefficient between devices, so that the collaborative control strategy can be constructed based on the real and time-varying interaction relationship between devices, thereby improving the adaptive and collaborative optimization ability of the entire production line in response to complex working conditions.

[0040] In one embodiment, please refer to Figure 3 , if the temperature gradient deviation value exceeds the preset deviation threshold, the potential influence of material change on temperature distribution is predicted based on the influence coefficient through a neural network model to obtain a heating power parameter and a wire drawing speed correction parameter, including: Step 401, if the temperature gradient deviation exceeds the preset deviation threshold, the temperature gradient deviation and the preform material parameter information are analyzed through a neural network model to obtain a temperature distribution prediction result; Step 402, based on the temperature distribution prediction result, the heating power parameter and the adjustment amplitude of the heating power parameter are determined; Step 403, based on the adjustment amplitude, an initial correction value of the wire drawing speed is determined; Step 404, if the initial correction value does not meet the preset wire drawing speed value required for production stability, the wire drawing speed is adjusted through an iterative optimization algorithm to determine the wire drawing speed correction parameter.

[0041] When it is determined that the temperature gradient deviation exceeds the preset threshold, the intelligent control process of deep fusion prediction and optimization is started. First, the temperature gradient deviation representing the abnormal current running state and the preform material parameter information are input into a well-trained neural network model. The neural network model can simulate how the current temperature deviation realizes the evolution of the temperature distribution of the entire production line in the future period under the existing material conditions, thereby generating a high-precision temperature distribution prediction result, thanks to its powerful nonlinear mapping capability. Then, based on the temperature distribution prediction result, the parameter decision stage is entered. According to the difference between the predicted temperature distribution and the ideal process window, the heating power parameter of each wire drawing device required to guide the heat field to return to stability is calculated. At the same time, the adjustment amplitude of the power parameter is determined. The adjustment amplitude is not a fixed value, but a dynamic variable that comprehensively considers the urgency of correction effect, device response characteristics and energy efficiency After determining the adjustment range of the heating power parameter, considering the strong coupling relationship between temperature and speed in the drawing process, the change of the heating power will inevitably affect the viscosity of the optical fiber and the forming process. Therefore, based on the calculated power adjustment range, the initial correction value of the drawing speed corresponding to the new thermal field state is derived through the embedded process knowledge model. However, this initial value may not meet the stringent requirements of overall dynamic stability of the production line, as it is only based on temperature balance. Therefore, a key verification and optimization link is introduced: if the initial correction value of the drawing speed deviates from the preset speed range required to ensure production stability, an iterative optimization algorithm is started, taking the initial correction value as the starting point. Under multiple constraint conditions such as temperature control target, constant fiber tension, and equipment physical limits, a global optimal drawing speed correction parameter is finally output, which can unify temperature control and production speed stability requirements.

[0042] In this embodiment, the neural network model realizes the ability to foresee and avoid potential quality risks, and the iterative optimization algorithm makes collaborative decisions on the heating power and drawing speed, ensuring that any control instruction is the optimal solution under multiple production goals, thereby enhancing the robustness and adaptability of the production line in response to material fluctuations and improving the quality consistency of high-end optical fiber products.

[0043] In one embodiment, referring to Figure 4 , the collaborative control optimization of each drawing equipment based on the heating power parameter and the drawing speed correction parameter is performed to obtain a production line temperature distribution optimization scheme, including: Step 501, based on the heating power parameter and the drawing speed correction parameter, real-time collection of running data of each drawing equipment is performed to obtain a drawing furnace state; Step 502, comparing the drawing furnace state with the preset production line temperature consistency requirement to determine an abnormal drawing equipment with temperature abnormality; Step 503, generating a collaborative control instruction based on the abnormal drawing equipment; Step 504, adjusting the heating power parameter and the drawing speed correction parameter based on the collaborative control instruction to obtain a process parameter adjustment scheme; Step 505, based on the process parameter adjustment scheme, the collaborative control instruction is issued to each drawing equipment to obtain a control execution efficiency and production line temperature data corresponding to the control execution efficiency; Step 506, generating a temperature distribution optimization scheme based on the production line temperature data.

[0044] Based on the determined heating power parameter and the drawing speed correction parameter, real-time operation data distributed in each drawing equipment is collected, including but not limited to the current power of the heating element, the real-time drawing speed of the optical fiber, the pressure in the furnace and the temperature at the key point. These multi-source data are fused and processed to obtain the drawing furnace state. Then, the real-time drawing furnace state is compared with the preset production line temperature consistency requirement. This comparison process is a mode recognition process based on process rules, which is used to locate the abnormal drawing equipment that deviates from the expected value and may cause quality problems from the temperature field.

[0045] Based on the identified abnormal drawing equipment, the system does not adjust it in isolation, but generates a corresponding collaborative control instruction according to the collaborative relationship of the production network. The generation of the collaborative control instruction integrates the previously determined influence coefficients between the equipment, ensuring that the adjustment strategy for a single equipment has already taken into account its cascading effect on upstream and downstream equipment. Subsequently, according to the collaborative control instruction, the initial heating power parameter and the drawing speed correction parameter are optimized and fine-tuned, and finally a comprehensive and executable process parameter adjustment scheme is formed, which can restore the overall temperature consistency at the minimum system disturbance cost. With the issuance of the process parameter adjustment scheme, the execution efficiency of the real-time instruction is obtained, and the production line temperature data changes caused thereby are collected. Based on these real-time production line temperature data reflecting the control effect, a new round of analysis and optimization is performed to dynamically generate and iterate the temperature distribution optimization scheme, thereby driving the entire control system into an intelligent cycle of self-learning and continuous improvement.

[0046] Specifically, on the drawing production line, first, the temperature sensor data and power meter readings of each drawing furnace are collected through the real-time monitoring system, and the target heating power is calculated using the PID control algorithm. For example, based on the current production line speed of 15 meters / minute, the temperature fluctuation amplitude is found to be 2.5 degrees Celsius by analyzing historical data, so the proportional gain Kp is adjusted to 0.8, the integral time Ti is 120 seconds, and the differential time Td is 25 seconds. Iterative calculation gives an optimized power of 85 kilowatts to ensure uniform heating of the molten glass. Subsequently, for the acquisition of the drawing speed correction parameter, a machine learning model such as a support vector machine is used to perform regression analysis on the correlation between speed and tension. The input data set includes the speed deviation value of the past 1000 production cycles. After model training, the correction coefficient is predicted to be 1.12. When the actual speed deviates from the target by 2 meters / minute, the correction formula is calculated by the least squares method. The calculation formula of the corrected speed is as follows: The corrected speed is 17.12 meters per minute calculated by the above formula, so that the fiber diameter is stabilized within the range of 125 microns ± 0.5 microns. Then, using the obtained heating power target of 85 kilowatts and the drawing speed correction parameter of 1.12, a coordinated control instruction is executed for each drawing furnace, and the instruction is broadcast to furnace 1 to furnace 5 by the distributed control system. The algorithm integrates a genetic algorithm to optimize a multi-objective function, and the objective function is as follows: Objective function = wherein, is the heating temperature, is the drawing speed, is the weight 0.7, the initial population size is 50, and the calculation converges after 20 generations of iteration. The temperature settings of each furnace are calculated as 1450 degrees Celsius, 1448 degrees Celsius, 1452 degrees Celsius, 1449 degrees Celsius, and 1451 degrees Celsius, respectively, ensuring that the thermal gradient does not exceed 1 degree Celsius per meter. Finally, based on the coordinated control results, a unified production line temperature distribution optimization scheme is obtained. The heat flow distribution is analyzed by finite element simulation software, and the boundary conditions are input as the optimized temperature and speed. The simulation shows that the overall temperature uniformity is improved by 15%, and the standard deviation is reduced from 3.2 degrees Celsius to 0.8 degrees Celsius.

[0047] In this embodiment, an adaptive optimization process based on real-time performance feedback is proposed, which can accurately locate the source of the anomaly and realize the ability to verify and continuously optimize the control strategy by introducing real-time evaluation of the control execution efficiency, thereby improving the quality uniformity and production efficiency of optical fiber manufacturing.

[0048] In one embodiment, referring to Figure 5 , based on the production line temperature distribution optimization scheme, the linkage control logic between each drawing equipment is updated to cooperatively control the production speed of the drawing equipment, including: Step 601, based on the production line temperature distribution optimization scheme, updating the linkage control logic between each drawing equipment to determine the dynamic adjustment range of speed matching; Step 602, if the dynamic adjustment range shows discordance, then using a support vector machine algorithm to analyze the interference factors of environmental fluctuations on speed matching to determine the speed synchronization compensation value between the drawing equipment; Step 603, based on the speed synchronization compensation value, the overall calibration of the production line speed is performed, the calibrated diameter measurement data is obtained, and the uniformity index of the optical fiber diameter is determined based on the diameter measurement data; Step 604, based on the uniformity index, verifying the effectiveness of the multi-device coordinated response to obtain a production stability confirmation result; If the production stability confirmation result is passed, the linkage control logic between each drawing equipment is updated to cooperatively control the production speed of the drawing equipment.

[0049] Based on the production line temperature distribution optimization scheme, the dynamic update of the linkage control logic is started, and the macro temperature regulation strategy is converted into accurate guidance for the cooperative production speed. First, according to the thermal coupling relationship between the equipment implied in the production line temperature distribution optimization scheme, the dynamic adjustment range of the speed matching of each drawing equipment is recalculated and determined. The dynamic adjustment range is not a fixed value, but a working interval that floats with the process state of the drawing equipment, which provides a clear boundary and space for the speed fine-tuning of the production line under the premise of maintaining stability.

[0050] When the actual speed matching relationship between the equipment is found to be uncoordinated, that is, it falls into or approaches the edge of the dynamic range, it indicates that there may be unmodeled environmental disturbance. Therefore, the pattern recognition algorithm of support vector machine is introduced to analyze the collected environmental parameters and speed deviation data, which can sensitively identify the specific influence mode of non-linear factors such as environmental temperature fluctuations and cooling air flow disturbances on the speed synchronization, and quantify the speed synchronization compensation value for each pair of adjacent equipment required to offset these disturbances. Then, according to the calculated speed synchronization compensation value, the drawing speed of the production line is calibrated overall and accurately. The effect of the calibration can be verified by a high-precision online diameter measuring instrument. The diameter measurement data of the optical fiber after calibration are obtained, and the uniformity index of the fiber diameter representing the core of the product quality is extracted from the diameter measurement data. The uniformity index is a manifestation of the cooperative control effect of the production line, and its advantages and disadvantages directly reflect the effect of the speed and temperature cooperative control.

[0051] Then, the uniformity index is used to finally verify the effectiveness of the multi-equipment cooperative response. By analyzing the improvement degree of the uniformity index before and after the speed calibration, whether the cooperative control has truly reached the expected goal can be objectively evaluated, and a quantitative production stability confirmation result is generated. If the confirmation result is passed, it indicates that the entire cooperative control logic is effective, so the speed matching rule and compensation mechanism that have passed the successful verification are solidified and updated to the linkage control logic between each drawing equipment.

[0052] In this embodiment, an adaptive intelligent scheme capable of actively identifying and compensating for unknown environmental disturbances is proposed, which significantly enhances the robustness and stability of the production line under complex working conditions.

[0053] In one embodiment, referring to Figure 6 , the linkage control logic between each drawing equipment is updated based on the production line temperature distribution optimization scheme, and the dynamic adjustment range of the speed matching is determined, which includes: Step 6011, based on the production line temperature distribution optimization scheme, real-time temperature monitoring data is obtained to determine the ambient temperature value; Step 6012, if the ambient temperature value exceeds the preset temperature threshold, the device running speed is adjusted through the control logic to obtain the speed adjustment parameter; Step 6013, based on the speed adjustment parameter, a distributed control algorithm is used to update the device linkage state to determine the cooperative operation mode; Step 6014, based on the cooperative operation mode, real-time feedback data between the drawing equipment is obtained; Step 6015, if the data consistency index of the real-time feedback data is lower than the preset standard index, the temperature monitoring data is corrected through the data processing module to obtain the corrected temperature data; Step 6016, based on the corrected temperature data, a dynamic programming algorithm is used to optimize the speed matching range to determine the dynamic adjustment range.

[0054] First, based on the established production line temperature distribution optimization scheme, high-frequency real-time temperature monitoring data is continuously obtained, which reflects the heating state inside the equipment and is used to accurately perceive the macro temperature conditions of the production environment, so that the environmental temperature value that has potential impact on the drawing process can be determined according to the real-time temperature monitoring data. When it is found through comparison that the environmental temperature value exceeds the preset process safety threshold, it means that the external environment has quantifiable interference on the production stability. Therefore, through its embedded control logic, the pre-adaptive adjustment of the device running speed is started to generate the initial speed adjustment parameter, aiming to compensate for the influence of environmental temperature change on the material thermodynamics process from the source.

[0055] Then, a distributed control algorithm is used to process the chain reaction caused by speed adjustment, which takes the generated speed adjustment parameter as input, efficiently negotiates and reallocates tasks among the control nodes of each device, dynamically updates the linkage state of the entire device group, and establishes a coordinated operation mode. Among them, the coordinated operation mode ensures that the production line can respond as a whole when dealing with environmental disturbances, rather than isolated behavior of individual devices.

[0056] In order to verify the effectiveness of this cooperative mode, real-time feedback data from each drawing equipment is collected. When the data analysis module detects that the data consistency index of the real-time feedback data is lower than the preset precision standard, it indicates that there may be noise or bias in the monitoring system. At this time, the advanced data processing module is started to filter and correct the original temperature monitoring data, eliminate outliers and compensate for system errors, and finally output more true and reliable corrected temperature data.

[0057] Finally, based on this batch of high-confidence corrected temperature data, a dynamic programming algorithm is used for optimization calculation, considering device performance constraints and overall process objectives, among multiple possible speed configuration schemes, to find a path that can ensure long-term stability and efficiency optimization, thus accurately defining the dynamic adjustment range that each device should follow in the next stage to maintain synergy.

[0058] For example, in a smart home system, the linkage control logic between multiple devices is optimized through Internet of Things protocols such as MQTT. First, real-time state data of air conditioners, heaters, and sensor nodes is collected, and a device dependency graph is constructed using graph theory algorithms, where nodes represent devices and edges represent interaction relationships, such as an air conditioner node connected to a temperature sensor node with a weight of 0.8 indicating strong dependency. Then, Dijkstra's algorithm is applied to calculate the shortest path delay, ensuring that the linkage response time is less than 50 milliseconds. When the user sets the living room temperature to 24.5°C, the system automatically evaluates the path and adjusts the air conditioner speed to medium to match the heater output power, avoiding energy waste of about 15%. On this basis, real-time feedback temperature monitoring data is obtained using a wireless sensor network with multiple nodes, each equipped with a DHT22 sensor to sample temperature at a frequency of 1 Hz. The data is fused and processed using a Kalman filter algorithm, such as an initial measurement of 25.2°C and a noise covariance of 0.1, with the filtered estimate being 24.8°C, reducing the error to 0.2°C. A linear regression model is used to analyze trends, such as where, is the number of minutes, predicting the temperature deviation in the next 5 minutes. If it exceeds 0.5°C, an alarm is triggered to upload to the cloud database to support remote monitoring. Further, the dynamic adjustment range of speed matching is determined, and the PID control algorithm is used to calculate the actuator speed, such as the proportional gain =2.0, integral =0.5, and differential =0.1, adjusting the fan speed according to the following formula: where the error e(t) = 24.5 - 24.8 = -0.3°C, and after iteration, the speed is dynamically increased from the initial 1200 rpm to 1350 rpm, with the range limited to 1000 to 1500 rpm to match the heat load changes. Simulation analysis shows that this adjustment can control the steady-state error within 0.1°C, ensuring a 12% improvement in system energy efficiency, thus forming a closed-loop control chain from optimized linkage to real-time monitoring to dynamic adjustment, achieving high efficiency and energy saving.

[0059] In this embodiment, external environmental fluctuations are input as a key input variable into the speed synergy control, enabling proactive compensation against environmental disturbances. At the same time, by introducing data consistency indicators and correction mechanisms, the reliability of the decision basis is ensured.

[0060] In an embodiment, referring to Figure 7 , if the dynamic adjustment range shows disharmony, a support vector machine algorithm is used to analyze the interference factors of environmental fluctuations on speed matching, and a speed synchronization compensation value between the wire drawing equipment is determined, comprising: Step 6021, if the dynamic adjustment range shows disharmony, environmental fluctuation data is collected to obtain an environmental variable data set, wherein the environmental variable data set includes real-time values of temperature, humidity, and vibration frequency; Step 6022, based on the environmental variable data set, a mapping relationship between environmental fluctuations and speed synchronization deviation is determined by a support vector machine algorithm to obtain a prediction model and an output deviation of the prediction model; Step 6023, if the output deviation exceeds a preset deviation threshold, the feature weight of the prediction model is adjusted to obtain an optimized model parameter; Step 6024, based on the prediction model corresponding to the optimized model parameter, the interference of real-time environmental variables on speed matching is analyzed to obtain a weight distribution of interference factors; Step 6025, based on the weight distribution of the interference factors, a speed synchronization compensation value between the wire drawing equipment is determined.

[0061] When it is detected that the dynamic adjustment range is out of harmony, a refined environmental interference analysis and compensation process is started. First, multi-dimensional fluctuation data in the production environment is comprehensively collected to build an environmental variable data set including key parameters such as temperature, humidity, and vibration frequency, thereby realizing a panoramic depiction of external conditions affecting device synchronization. Based on the environmental variable data set, a support vector machine algorithm is used to reveal the complex nonlinear mapping relationship between environmental fluctuations and device speed synchronization deviation. The support vector machine algorithm can accurately extract the core mode affecting synchronization accuracy from seemingly disordered environmental variables through the construction and segmentation of high-dimensional feature space, and then train a highly reliable prediction model. At the same time, the output deviation of the prediction model is continuously monitored, and the output deviation is a key indicator for evaluating the adaptability of the prediction model in the actual operating environment.

[0062] When the model output deviation exceeds the preset fault tolerance threshold, it indicates that the initial model is mismatched with the current actual process condition. Then the online self-learning mechanism of the model is started, and the model is fine-tuned and optimized by dynamically adjusting its feature weights. This process enables the prediction model to adapt to changes in environmental fluctuation characteristics, and ultimately produces a set of optimized model parameters. Through the optimized prediction model, the real-time collected environmental variables are analyzed to quantify the contribution of various interference factors to speed matching, thereby obtaining a weight distribution map of the interference factors. Finally, according to the generated weight distribution, the speed synchronization compensation value for each drawing equipment is calculated and distributed. The speed synchronization compensation value is not uniform adjustment, but customized instructions according to the intensity and characteristics of the interference received by each device, so as to realize precise interference cancellation and speed synchronization recovery at the system level.

[0063] In this embodiment, a differentiated compensation mechanism based on weight distribution is proposed, which enables the speed synchronization control to enter a precise on-demand allocation mode, effectively improving the resilience and adaptive ability of high-end optical fibers in the face of complex environmental disturbances during production.

[0064] The fiber production equipment collaborative control system based on the Internet of Things provided by the present application is described below. The fiber production equipment collaborative control system based on the Internet of Things described below can be mutually corresponding and referred to with the fiber production equipment collaborative control method based on the Internet of Things described above.

[0065] The present application also provides a fiber production equipment collaborative control system based on the Internet of Things, comprising: An index determination module is configured to determine a real-time temperature gradient based on temperature distribution data of each drawing equipment, and determine a material change index based on preform material parameter information of each drawing equipment. A state determination module is configured to determine a temperature state of the current production line based on the real-time temperature gradient, and determine a material adaptation demand value based on the material change index. An influence coefficient determination module is configured to determine a temperature gradient deviation value and an influence coefficient between adjacent drawing equipment by processing the temperature data correlation between the drawing equipment based on the temperature state and the material adaptation demand value using a distributed computing framework. A parameter determination module is configured to predict the potential impact of material change on temperature distribution based on the influence coefficient through a neural network model if the temperature gradient deviation value exceeds a preset deviation threshold, to obtain a heating power parameter and a drawing speed correction parameter. A regulation and optimization module is configured to perform collaborative regulation and optimization of each drawing equipment based on the heating power parameter and the drawing speed correction parameter, to obtain a production line temperature distribution optimization scheme. A cooperative control module is configured to update linkage control logic between each drawing device based on the production line temperature distribution optimization scheme, so as to cooperatively control the production speed of the drawing device.

[0066] It should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same. Although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features. Such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A collaborative control method for optical fiber production equipment based on the Internet of Things, characterized in that, Executed by a computer, including: The real-time temperature gradient is determined based on the temperature distribution data of each wire drawing equipment, and the material change index is determined based on the preform material parameter information of each wire drawing equipment. The temperature status of the current production line is determined based on the real-time temperature gradient, and the material adaptation requirement value is determined based on the material change index. Based on the temperature conditions and material adaptation requirements, a distributed computing framework is used to process the temperature data correlation between each drawing device, and to determine the temperature gradient deviation value and the influence coefficient between adjacent drawing devices. If the temperature gradient deviation value exceeds the preset deviation threshold, then based on the influence coefficient, the potential impact of material change on temperature distribution is predicted by a neural network model to obtain heating power parameters and wire drawing speed correction parameters. Based on the heating power parameters and the drawing speed correction parameters, collaborative control and optimization are performed on each drawing device to obtain an optimized temperature distribution scheme for the production line. Based on the temperature distribution optimization scheme of the production line, the linkage control logic between each wire drawing equipment is updated to coordinate the production speed of the wire drawing equipment.

2. The collaborative control method for optical fiber production equipment based on the Internet of Things according to claim 1, characterized in that, Based on the temperature state and material adaptation requirements, a distributed computing framework is used to process the temperature data correlation between various drawing devices, determine the temperature gradient deviation value and the influence coefficient between adjacent drawing devices, including: Based on the temperature distribution data, a standardized temperature dataset is determined; Based on the standardized temperature dataset, a distributed computing framework is used for partitioning to calculate the temperature difference between devices and determine the temperature gradient distribution. If the temperature gradient distribution exceeds a preset gradient threshold, the data weights of each temperature gradient are adjusted by a weighted average algorithm to obtain the corrected temperature gradient value. Based on the corrected temperature gradient value, the temperature correlation between adjacent wire drawing equipment is calculated using the Pearson correlation coefficient to determine the influence coefficient.

3. The collaborative control method for optical fiber production equipment based on the Internet of Things according to claim 1, characterized in that, If the temperature gradient deviation value exceeds a preset deviation threshold, then based on the influence coefficient, a neural network model is used to predict the potential impact of material changes on the temperature distribution, and heating power parameters and drawing speed correction parameters are obtained, including: If the temperature gradient deviation exceeds a preset deviation threshold, the temperature gradient deviation and the material parameter information of the preform are analyzed by a neural network model to obtain the temperature distribution prediction result. Based on the temperature distribution prediction results, the heating power parameters and the adjustment range of the heating power parameters are determined; Based on the adjustment range, an initial correction value for the wire drawing speed is determined; If the initial correction value does not meet the preset wire drawing speed value required for stable production, the wire drawing speed is adjusted through an iterative optimization algorithm to determine the wire drawing speed correction parameter.

4. The collaborative control method for optical fiber production equipment based on the Internet of Things according to claim 1, characterized in that, The process of performing coordinated control and optimization on each wire drawing device based on the heating power parameters and the wire drawing speed correction parameters yields an optimized temperature distribution scheme for the production line, including: Based on the heating power parameters and the wire drawing speed correction parameters, the operating data of each wire drawing device is collected in real time to obtain the status of the wire drawing furnace. The state of the drawing furnace is compared with the preset production line temperature consistency requirements to identify abnormal drawing equipment with abnormal temperature. Based on the abnormal wire drawing equipment, generate collaborative control commands; Based on the aforementioned coordinated control command, the heating power parameter and the drawing speed correction parameter are adjusted to obtain a process parameter adjustment scheme. Based on the process parameter adjustment scheme, the coordinated control command is sent to each wire drawing equipment to obtain the control execution efficiency and the production line temperature data corresponding to the control execution efficiency. Based on the temperature data of the production line, a temperature distribution optimization scheme is generated.

5. The collaborative control method for optical fiber production equipment based on the Internet of Things according to claim 1, characterized in that, The step of updating the linkage control logic between each wire drawing device based on the production line temperature distribution optimization scheme to coordinate the production speed of the wire drawing device includes: Based on the temperature distribution optimization scheme of the production line, the linkage control logic between each wire drawing equipment is updated to determine the dynamic adjustment range of speed matching; If the dynamic adjustment range is inconsistent, a support vector machine algorithm is used to analyze the interference factors of environmental fluctuations on speed matching and determine the speed synchronization compensation value between the wire drawing equipment. The production line speed is calibrated as a whole based on the speed synchronization compensation value, the calibrated diameter measurement data is obtained, and the uniformity index of the fiber diameter is determined based on the diameter measurement data. The effectiveness of the multi-device collaborative response is verified based on the uniformity index, and the production stability confirmation result is obtained. If the production stability confirmation result is passed, the linkage control logic between each wire drawing device is updated to coordinate the production speed of the wire drawing device.

6. The collaborative control method for optical fiber production equipment based on the Internet of Things according to claim 5, characterized in that, The step of updating the linkage control logic between each wire drawing device based on the production line temperature distribution optimization scheme and determining the dynamic adjustment range of speed matching includes: Based on the production line temperature distribution optimization scheme, real-time temperature monitoring data is obtained to determine the ambient temperature value. If the ambient temperature value exceeds the preset temperature threshold, the operating speed of the equipment is adjusted through control logic to obtain speed adjustment parameters; Based on the speed adjustment parameters, a distributed control algorithm is used to update the device linkage status and determine the cooperative operation mode; Based on the aforementioned collaborative operation mode, real-time feedback data between the wire drawing devices is obtained; If the data consistency index of the real-time feedback data is lower than the preset standard index, the temperature monitoring data is corrected by the data processing module to obtain the corrected temperature data. Based on the corrected temperature data, a dynamic programming algorithm is used to optimize the speed matching range and determine the dynamic adjustment range.

7. The collaborative control method for optical fiber production equipment based on the Internet of Things according to claim 5, characterized in that, If the dynamic adjustment range shows inconsistency, a support vector machine algorithm is used to analyze the interference factors of environmental fluctuations on speed matching, and to determine the speed synchronization compensation value between the wire drawing equipment, including: If the dynamic adjustment range is inconsistent, environmental fluctuation data is collected to obtain an environmental variable dataset, wherein the environmental variable dataset includes real-time values ​​of temperature, humidity, and vibration frequency. Based on the environmental variable dataset, the mapping relationship between environmental fluctuations and speed synchronization deviation is determined by the support vector machine algorithm, and the prediction model and the output deviation of the prediction model are obtained. If the output deviation exceeds a preset deviation threshold, the feature weights of the prediction model are adjusted to obtain optimized model parameters. Based on the prediction model corresponding to the optimized model parameters, the interference of real-time environmental variables on speed matching is analyzed, and the weight distribution of interference factors is obtained. Based on the weight distribution of the interference factors, the speed synchronization compensation value between the wire drawing equipment is determined.

8. A collaborative control system for fiber optic production equipment based on the Internet of Things, characterized in that, include: The index determination module is used to determine the real-time temperature gradient based on the temperature distribution data of each wire drawing equipment, and to determine the material change index based on the preform material parameter information of each wire drawing equipment. The status determination module is used to determine the temperature status of the current production line based on the real-time temperature gradient, and to determine the material adaptation requirement value based on the material change index. The influence coefficient determination module is used to process the temperature data correlation between each drawing device based on the temperature state and material adaptation requirements, and to determine the temperature gradient deviation value and the influence coefficient between adjacent drawing devices using a distributed computing framework. The parameter determination module is used to predict the potential impact of material changes on temperature distribution based on the influence coefficient and a neural network model if the temperature gradient deviation value exceeds a preset deviation threshold, thereby obtaining heating power parameters and wire drawing speed correction parameters. The control and optimization module is used to perform coordinated control and optimization on each wire drawing equipment based on the heating power parameters and the wire drawing speed correction parameters, so as to obtain an optimized temperature distribution scheme for the production line. The collaborative control module is used to update the linkage control logic between each wire drawing device based on the temperature distribution optimization scheme of the production line, so as to collaboratively control the production speed of the wire drawing device.

Images