CN-121995982-A - Intelligent control method and system for temperature of high silica glass fiber production line

CN121995982ACN 121995982 ACN121995982 ACN 121995982ACN-121995982-A

Abstract

The invention discloses an intelligent control method and system for the temperature of a high silica glass fiber production line, which relate to the technical field of high silica glass fiber production and comprise the following steps: the method comprises the steps of firstly, acquiring temperature data in real time through temperature sensors arranged at all nodes in a hearth of a smelting furnace, constructing a regional temperature field model based on a finite element analysis algorithm by combining the temperature data, simultaneously acquiring content data of trace impurities in raw materials in real time by adopting on-line detection equipment, analyzing the viscosity change trend of a melt under the current raw materials, dynamically adjusting the current temperature threshold according to the viscosity change, breaking through the limitation of the traditional fixed temperature threshold, enabling temperature control to be better suitable for real-time fluctuation of the trace impurities in the raw materials, ensuring that proper temperature control can be realized under different raw material conditions, effectively improving the qualification rate of products, reducing the loss rate of the raw materials, simultaneously reducing manual intervention, improving the timeliness and accuracy of the temperature control, and further improving the production efficiency and the product quality.

Inventors

LI YUCAI
ZHAO YAN
ZHANG DONG
SONG SHIWEI
YU SHICHUN
DING BO
WANG HAN
WANG JIAN
ZHAO DEPENG

Assignees

沈阳工程学院

Dates

Publication Date: 20260508
Application Date: 20251219

Claims (7)

1. The intelligent control method for the temperature of the high silica glass fiber production line is characterized by comprising the following steps of: Acquiring temperature data in real time through temperature sensors arranged at all nodes in a hearth of a smelting furnace, constructing a regional temperature field model based on a finite element analysis algorithm by combining the temperature data, and acquiring content data of trace impurities in raw materials in real time by adopting on-line detection equipment; Step two, acquiring historical content data of trace impurities, historical viscosity data of a melt and corresponding historical temperature thresholds from a historical database, calculating a correlation coefficient between the historical content data and the historical viscosity data through a correlation analysis method, constructing a correlation model of content and viscosity based on a deep neural network, and analyzing the viscosity change trend of the melt under the trace impurity content in the current raw material by combining the content data acquired in real time; and thirdly, dynamically adjusting the current temperature threshold according to the viscosity change trend of the melt and combining the corresponding historical temperature threshold, comparing the temperature data of each region in the constructed regional temperature field model with the dynamically adjusted current temperature threshold, correspondingly generating an operation instruction according to the comparison result, and regulating and controlling the temperature of the smelting furnace.
2. The intelligent control method for the temperature of the high silica glass fiber production line according to claim 1, wherein in the second step, the correlation analysis method is a pearson correlation coefficient method.
3. The intelligent control method for the temperature of the high silica glass fiber production line according to claim 2, wherein the specific process of constructing the regional temperature field model by combining temperature data based on a finite element analysis algorithm is as follows: s101, dividing the internal space of the furnace hearth by adopting regular hexahedral units, and dividing the furnace hearth into L, W, H parts with the length, the width and the height in a three-dimensional space Each small hexahedral unit has length, width and height of 、、 ; S102, setting nodes at the top of each small hexahedral unit area, and collecting temperature data of each node in real time through a temperature sensor , wherein, N is the total number of nodes, the temperature distribution in each small hexahedral unit is approximately calculated by adopting a linear interpolation function according to the temperature data of each node through a finite element analysis algorithm, and the calculation results are integrated to construct a regional temperature field model.
4. The intelligent control method for the temperature of the high silica glass fiber production line according to claim 3, wherein the specific process of calculating the correlation coefficient between the historical content data and the historical viscosity data by the correlation analysis method is as follows: s201, acquiring historical content data of trace impurities from a historical database Historical viscosity data for melt And a corresponding historical temperature threshold, wherein, N is the number of data samples, and the historical content data and the historical viscosity data are arranged into corresponding data pairs ; Respectively calculating the average value of the historical content data And the average of historical viscosity data The formula is as follows: ; ; Calculating covariance of historical content data and historical viscosity data The formula is as follows: ; Respectively calculating standard deviation of historical content data And standard deviation of historical viscosity data The formula is as follows: ; ; S202, calculating a correlation coefficient r between historical content data and historical viscosity data according to a Pearson correlation coefficient formula, wherein the formula is as follows: Wherein, the value range of the correlation coefficient r is The closer the absolute value of r is to 1, the stronger the linear correlation between the two variables, and the closer the absolute value of r is to 0, the weaker the linear correlation between the two variables.
5. The intelligent control method for the temperature of the high silica glass fiber production line according to claim 4, wherein the specific process of analyzing the viscosity change trend of the melt under the content of trace impurities in the current raw materials is as follows: S301, acquiring historical content data of trace impurities, historical viscosity data of a melt and corresponding historical temperature thresholds from a historical database, integrating the historical content data, the historical viscosity data and the corresponding historical temperature thresholds into a historical data set, dividing the historical data set into a training set and a verification set according to a ratio of 7:3, constructing a correlation model of content and viscosity based on a deep neural network, training the correlation model by using the training set, continuously adjusting weight and paranoid parameters of the correlation model through a back propagation algorithm, enabling a predicted value of the model to be gradually close to a true value, and verifying the trained correlation model by using the verification set; S302, content data acquired in real time Input into the correlation model, output predicted viscosity data through the correlation model The formula is as follows: , wherein, Is a weight matrix of each layer of the deep neural network, Is the bias vector of each layer, f is the activation function; S303, comparing the predicted viscosity data with the viscosity data of the melt under the same trace impurity content in a historical database, and analyzing the viscosity change trend of the melt under the trace impurity content in the current raw material.
6. The intelligent control method for the high silica glass fiber production line temperature according to claim 5, wherein the specific process of comparing the temperature data of each region in the constructed regional temperature field model with the dynamically adjusted current temperature threshold value is as follows: According to the viscosity change trend of the melt, the current temperature threshold is dynamically adjusted by combining the corresponding historical temperature threshold, and the temperature data of each region in the constructed regional temperature field model is based on the preset temperature deviation range And the current temperature threshold after dynamic adjustment Preset temperature deviation range Comparing, correspondingly generating an operation instruction according to the comparison result, adjusting the temperature of the melting furnace, and comparing as follows: If it is Judging that the temperature of the area is too high, and correspondingly generating an operation instruction for reducing the temperature of the area; If it is Judging that the temperature of the area is too low, and correspondingly generating an operation instruction for increasing the temperature of the area; If it is The temperature of the area is judged to be normal, and the temperature adjustment operation is not required.
7. An intelligent control system for the temperature of a high silica glass fiber production line, which is applied to the intelligent control method for the temperature of the high silica glass fiber production line according to any one of claims 1 to 6, is characterized by comprising a data acquisition unit, a change analysis unit and an instruction generation unit; The data acquisition unit is used for acquiring temperature data in real time through temperature sensors arranged at all nodes in a hearth of the smelting furnace, constructing a regional temperature field model based on a finite element analysis algorithm by combining the temperature data, acquiring content data of trace impurities in raw materials in real time by adopting online detection equipment, and transmitting the content data to the change analysis unit; The change analysis unit is used for acquiring temperature data and content data of trace impurities in the raw materials, acquiring historical content data of the trace impurities, historical viscosity data of the melt and corresponding historical temperature thresholds from a historical database, calculating correlation coefficients between the historical content data and the historical viscosity data through a correlation analysis method, constructing a correlation model of content and viscosity based on a deep neural network, analyzing the viscosity change trend of the melt under the trace impurity content in the current raw materials by combining the content data acquired in real time, and sending the viscosity change trend to the instruction generation unit; The instruction generation unit is used for acquiring the viscosity change trend of the melt, dynamically adjusting the current temperature threshold according to the viscosity change trend of the melt and combining the corresponding historical temperature threshold, comparing the temperature data of each region in the constructed regional temperature field model with the dynamically adjusted current temperature threshold, correspondingly generating an operation instruction according to the comparison result, and regulating and controlling the temperature of the smelting furnace.

Description

Intelligent control method and system for temperature of high silica glass fiber production line Technical Field The invention relates to the technical field of high silica glass fiber production, in particular to an intelligent temperature control method and system for a high silica glass fiber production line. Background The high silica glass fiber is a special glass fiber with SiO 2 content higher than 96%, has high temperature resistance (the long-term use temperature can reach more than 1000 ℃), excellent chemical stability and electrical insulation, and is widely applied to high-end fields such as aerospace, high-temperature filtration, fire prevention and heat insulation and the like. The high silica glass fiber production line is a continuous production system for realizing the processes from glass raw material melting, wire drawing and molding to finished product treatment, and the core processes comprise raw material melting (raw materials such as quartz sand and the like are melted into homogeneous phase melt in a high-temperature hearth), wire drawing molding (molten glass is drawn into fibers through a bushing), and high-temperature sintering (SiO 2 components in amorphous glass are rearranged and crystallized through gradient heating). In the high silica glass fiber production process, a melting furnace is used as key equipment, the temperature fluctuation of the melting furnace can trigger a chain reaction, the product quality and the production efficiency are directly influenced, the existing temperature control method adopts a single-point temperature measurement characterization area temperature field, the condition that a glass melt generates bubbles due to local overheating or wire drawing and breakage due to insufficient temperature is ignored, the temperature threshold is a fixed value, the real-time fluctuation of trace impurities in raw materials is not related, when the impurity content is increased, the melt viscosity can be obviously changed at the same temperature, the condition that the deviation of the wire drawing diameter is larger can be caused only by the adjustment of the fixed temperature, and therefore, unqualified products are increased, and meanwhile, the loss rate of the raw materials is increased. Accordingly, the present invention provides a method and a system for intelligent temperature control of a high silica glass fiber production line to overcome and improve the shortcomings of the prior art. Disclosure of Invention In order to solve the technical problems, the invention provides an intelligent control method and system for the temperature of a high silica glass fiber production line, which are used for solving the corresponding technical problems in the background art. In order to achieve the purpose, the technical scheme adopted by the invention is that the intelligent control method for the temperature of the high silica glass fiber production line comprises the following steps: Acquiring temperature data in real time through temperature sensors arranged at all nodes in a hearth of a smelting furnace, constructing a regional temperature field model based on a finite element analysis algorithm by combining the temperature data, and acquiring content data of trace impurities in raw materials in real time by adopting on-line detection equipment; Step two, acquiring historical content data of trace impurities, historical viscosity data of a melt and corresponding historical temperature thresholds from a historical database, calculating a correlation coefficient between the historical content data and the historical viscosity data through a correlation analysis method, constructing a correlation model of content and viscosity based on a deep neural network, and analyzing the viscosity change trend of the melt under the trace impurity content in the current raw material by combining the content data acquired in real time; and thirdly, dynamically adjusting the current temperature threshold according to the viscosity change trend of the melt and combining the corresponding historical temperature threshold, comparing the temperature data of each region in the constructed regional temperature field model with the dynamically adjusted current temperature threshold, correspondingly generating an operation instruction according to the comparison result, and regulating and controlling the temperature of the smelting furnace. Preferably, in the second step, the correlation analysis method is a pearson correlation coefficient method. Preferably, based on a finite element analysis algorithm, the specific process of constructing the regional temperature field model by combining temperature data is as follows: s101, dividing the internal space of the furnace hearth by adopting regular hexahedral units, and dividing the furnace hearth into L, W, H parts with the length, the width and the height in a three-dimensional space Each small hexahedral unit has length, width and heig