Control method and system in glass product manufacturing process

Abstract

The invention discloses a control method and system in a glass product manufacturing process, and particularly relates to the technical field of glass product manufacturing. Voltage fluctuation and signal noise data in a plurality of time periods are analyzed by monitoring voltage fluctuation and signal noise of a temperature sensor in real time, a data accuracy index of the temperature sensor is calculated in combination with a weight assignment method, oxygen concentration fluctuation in a furnace is monitored in real time through an oxygen sensor, the influence of atmosphere change is evaluated, and the accuracy of the temperature sensor is improved. A fuzzy logic algorithm is utilized to comprehensively evaluate the accuracy of monitoring data and the fluctuation condition of oxygen concentration, and the heating power is dynamically adjusted, so that the glass melting process is optimized, the temperature is prevented from being out of control or incomplete melting is prevented, the equipment damage risk is reduced, the production efficiency is improved, the maintenance and shutdown time is shortened, and the temperature monitoring accuracy is effectively improved. The stability of the system is enhanced, and efficient and safe operation of the glass production process is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of glass product manufacturing, and in particular to a control method and system in a glass product manufacturing process. Background Art

[0002] Control in the glass manufacturing process refers to the real-time monitoring and adjustment of key parameters such as temperature, pressure, time, and chemical composition through technical means in each link of glass production to ensure stable product quality, improved process efficiency, and optimal use of resources. This control process runs through every stage from raw material mixing, melting, molding, annealing to subsequent processing, aiming to avoid defects caused by process deviations, such as bubbles, streaks, uneven thickness or insufficient strength. Specifically, during the glass melting stage, the control system monitors the temperature distribution of the furnace and the uniformity of the raw materials to ensure the purity and fluidity of the molten glass; in the molding stage, the mold temperature and glass liquid flow rate are precisely adjusted to obtain product sizes and shapes that meet specifications; during the annealing process, the cooling rate is strictly controlled to avoid brittleness problems caused by residual stress. This full-process control not only improves the quality and reliability of glass products, but also effectively reduces energy consumption and production costs.

[0003] The prior art has the following deficiencies:

[0004] Control systems rely on sensors to obtain real-time data and make decisions. If a feedback loop error occurs during data transmission, the system may fall into an erroneous adjustment loop. For example, the temperature sensor transmits erroneous data for some reason (such as electrical interference, failure or signal delay), and the control system makes adjustments based on this data, and the new adjustment in turn affects the collected data of the temperature sensor, thus entering a vicious cycle. At the same time, feedback loop errors may cause the temperature sensor to continue to send erroneous temperature data to the control system, and the system automatically adjusts the heating power based on these erroneous data. Since the new temperature data after adjustment is transmitted to the control system again, a vicious cycle is formed, which may cause the temperature to be out of control, too high or too low. If the melting furnace temperature is too high, the equipment and furnace materials may be damaged due to overheating, and even the furnace wall may melt or the equipment may burn, resulting in huge maintenance costs and downtime. Too low a temperature may cause incomplete melting of the glass, slow reaction speed in the furnace, impurities may remain in the glass, and in severe cases, the final glass product cannot even be extracted. Summary of the invention

[0005] The object of the present invention is to provide a control method and system in a glass product manufacturing process to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a control method in a glass product manufacturing process, comprising the following steps:

[0007] S1: Install a voltage monitor on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and install a noise monitor in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and monitor the heating power output of the heater in real time through a power meter;

[0008] S2: Obtain fluctuation data of the power supply voltage of the temperature sensor in several time periods and noise data in signal transmission, analyze them to determine the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and perform weighted average sum calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index;

[0009] S3: monitor the oxygen concentration of the gas in the furnace in real time through the oxygen sensor, and judge the degree of abnormal change of the oxygen content of the atmosphere in the furnace according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period;

[0010] S4: Based on the calculated accuracy index of the monitoring data and the fluctuation of the oxygen concentration of the gas in the furnace, the heating power is dynamically adjusted using fuzzy logic to optimize the melting process.

[0011] Preferably, in S2, the voltage fluctuation frequency anomaly index is generated after analyzing the fluctuation data of the temperature sensor power supply voltage, and the method for obtaining the voltage fluctuation frequency anomaly index is:

[0012] Collect voltage fluctuation data during the Q period ; Where v(s) is the value of the voltage signal at time s, N is the number of sampling points, and the time domain signal is converted into a frequency domain signal by fast Fourier transform FFT. FFT converts the voltage signal V(s) into a frequency domain signal V(f), and the calculation formula is: ; is the frequency The corresponding complex Fourier coefficients, j is the imaginary unit, ; is the corresponding frequency, T is the signal sampling period, and k is the frequency index; in order to analyze the frequency component of the voltage fluctuation signal, calculate its amplitude spectrum , that is, the energy distribution at different frequencies, expressed as: ; In the formula, Re( ) and Im ) are The real and imaginary parts of the spectrum; calculate the total energy of the entire spectrum As a reference value, the expression is: ; Identify the amplitude value If the fluctuation is greater than the normal fluctuation, ; Mark it as an abnormal frequency and calculate its energy contribution for the abnormal frequency , the expression is: ; Calculate the voltage fluctuation frequency abnormality index, the expression is: ; In the formula, AK is the voltage fluctuation frequency abnormality index.

[0013] Preferably, in S2, the signal collected by the temperature sensor is discretized into a discrete numerical sequence, and the signal is set ; is a signal sequence of length Z, which is divided into discrete intervals, the signal is segmented, the discrete value of the signal is obtained, and the interval is defined To represent different discrete values, calculate the probability of occurrence of each discrete value in the signal X, form the probability distribution P(X) of the signal, and count each discrete value in the signal Frequency of occurrence , calculate the probability of each discrete value , the expression is: ; Calculate the information entropy according to the probability distribution of the signal, and the calculation expression is: ;in, is the entropy of signal X. By comparing the entropy of the original signal and the entropy of the denoised signal, the signal noise interference index is calculated, and the entropy H(X) of the entire temperature sensor signal sequence is calculated. The signal is subjected to noise suppression to obtain the denoised signal sequence. , and then calculate its entropy , then calculate the signal noise interference index, the expression is: ; In the formula, is the signal-to-noise interference index.

[0014] Preferably, in S2, the voltage fluctuation frequency anomaly index and the signal noise interference index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as inputs of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the weighted assignment labels of the accuracy of the temperature sensor monitoring data in each time period as the prediction target, and takes minimizing the sum of the prediction errors of the weighted assignment labels of the accuracy of the temperature sensor monitoring data in all time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weighted assignment of the accuracy of the temperature sensor monitoring data in each time period is determined according to the model output results, wherein the machine learning model is a polynomial regression model, and the weighted average summation of the weighted assignments of the accuracy of the temperature sensor monitoring data in each time period is calculated to obtain the monitoring data accuracy index.

[0015] Preferably, in S3, the oxygen concentration fluctuation deviation index is generated after analyzing the oxygen concentration fluctuation of the furnace gas within a fixed time period, and the degree of abnormal change of the oxygen content of the furnace atmosphere is judged. The method for obtaining the oxygen concentration fluctuation deviation index is:

[0016] Collect oxygen concentration data within a fixed time period and set the oxygen concentration data to , where t represents the timestamp, is the oxygen concentration data at time t; select the order of the autoregressive moving average ARMA model, the ARMA model contains autoregressive AR terms and moving average MA terms, and the model is expressed as: ;in, is the coefficient of the AR term, is the coefficient of the MA term, is the noise term, For in time The white noise residual at the moment uses the autocorrelation function and partial autocorrelation function to determine the p and q orders; according to the selected orders p and q, the parameters of the model are estimated and , or q; use the fitted ARMA model to predict future values ​​of oxygen concentration and calculate the difference between the actual observed values ​​and the values ​​predicted by the model, that is: ;in, is the residual, For the oxygen concentration value predicted by the ARMA model, the oxygen concentration fluctuation deviation index is calculated, and the expression is: ; Where Y is the total number of data points and KM is the oxygen concentration fluctuation deviation index.

[0017] Preferably, in S4, according to the calculated monitoring data accuracy index and the oxygen concentration fluctuation of the gas in the furnace, the heating power is dynamically adjusted using fuzzy logic to optimize the melting process, specifically:

[0018] The monitoring data accuracy index RY and oxygen concentration fluctuation deviation index KM are used as input items of fuzzy logic, and the heating power of the melting furnace is used as output item;

[0019] The monitoring data accuracy index, oxygen concentration fluctuation deviation index and heating power of the melting furnace are fuzzy processed respectively;

[0020] Construct fuzzy rules based on RY and KM. Fuzzy rules connect the relationship between input variables and output variables through fuzzy logic;

[0021] Convert the actually measured RY and KM values ​​into fuzzy sets;

[0022] Based on the defined fuzzy rules, the fuzzy value of heating power is obtained through the reasoning process;

[0023] In the reasoning process, a fuzzy heating power value is obtained and defuzzified at the same time, and a specific heating power value is obtained after defuzzification;

[0024] The defuzzified heating power value is fed back to the automatic control system, and the system will adjust the heating power in the melting furnace according to the heating power value, thereby optimizing the glass melting process.

[0025] The present invention also provides a control system in a glass product manufacturing process, comprising a sensor monitoring module, a data analysis module, an oxygen concentration monitoring module and a fuzzy logic control module;

[0026] Sensor monitoring module: A voltage monitor is installed on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and a noise monitor is installed in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and the heating power output of the heater is monitored in real time through a power meter;

[0027] Data analysis module: obtains the fluctuation data of the power supply voltage of the temperature sensor in several time periods and the noise data in the signal transmission, analyzes them, determines the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and performs weighted average summation calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index;

[0028] Oxygen concentration monitoring module: monitors the oxygen concentration of the gas in the furnace in real time through the oxygen sensor, and determines the degree of abnormal change of the oxygen content in the furnace atmosphere according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period;

[0029] Fuzzy logic control module: Based on the calculated accuracy index of monitoring data and the fluctuation of oxygen concentration in the furnace gas, fuzzy logic is used to dynamically adjust the heating power and optimize the melting process.

[0030] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0031] 1. The present invention installs a voltage monitor, a noise monitor and a power meter on the power supply line of the temperature sensor to detect power fluctuations, signal noise and heater power in real time, providing a strong guarantee for the accuracy of temperature data. By analyzing voltage fluctuations and signal noise, the accuracy index of monitoring data is generated in combination with a machine learning model, and on this basis, fuzzy logic analysis is performed in combination with the fluctuation of oxygen concentration in the furnace gas, and the heating power is dynamically adjusted, effectively avoiding the risk of temperature runaway or incomplete melting.

[0032] 2. The present invention can evaluate the accuracy of the monitoring data of the temperature sensor and the changes in the atmosphere in the furnace in real time and accurately, and accurately control the melting process based on these indicators. In particular, while solving the vicious feedback loop problem, it can optimize the glass melting process, improve production efficiency, reduce the risk of equipment damage, and effectively reduce production shutdowns and maintenance costs caused by temperature fluctuations, providing the glass melting industry with an efficient, safe, and intelligent production control method with significant economic benefits and safety protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0034] Figure 1 The present invention is a flow chart of the method.

[0035] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Example 1, please refer to Figure 1 and Figure 2 As shown, the control method in the glass product manufacturing process described in this embodiment includes the following steps:

[0038] S1: Install a voltage monitor on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and install a noise monitor in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and monitor the heating power output of the heater in real time through a power meter;

[0039] S2: Obtain fluctuation data of the power supply voltage of the temperature sensor in several time periods and noise data in signal transmission, analyze them to determine the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and perform weighted average sum calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index;

[0040] S3: monitor the oxygen concentration of the gas in the furnace in real time through the oxygen sensor, and judge the degree of abnormal change of the oxygen content of the atmosphere in the furnace according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period;

[0041] S4: Based on the calculated accuracy index of the monitoring data and the fluctuation of the oxygen concentration of the gas in the furnace, the heating power is dynamically adjusted using fuzzy logic to optimize the melting process.

[0042] In S1, a voltage monitor is installed on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and a noise monitor is installed in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and the heating power output of the heater is monitored in real time through a power meter, specifically:

[0043] The voltage monitor is used to monitor the power supply voltage fluctuation of the temperature sensor in real time, and can detect errors caused by electrical interference, voltage instability, etc. The working accuracy of the temperature sensor is greatly affected by the power supply voltage, and voltage fluctuations may cause the sensor to output inaccurate temperature data.

[0044] Select an appropriate voltage monitor according to the operating voltage range of the temperature sensor. The voltage monitor should have sufficient accuracy and response speed to monitor power supply voltage fluctuations in real time. Install the voltage monitor at the power input of the temperature sensor. Make sure that the voltage monitor can directly measure the voltage received by the sensor without interference from external power supplies or equipment. By monitoring the voltage fluctuation data, it can be determined whether there is a voltage anomaly. If the power supply voltage fluctuation exceeds the set threshold, the alarm system can be triggered and compensatory measures can be taken, such as adjusting the power supply or switching to a backup power supply. By monitoring the voltage fluctuation in real time, the impact of electrical interference or unstable power supply can be identified, and sensor data errors caused by voltage anomalies can be avoided. If the temperature sensor incorrectly transmits data due to voltage fluctuations, it will cause incorrect adjustments to the automation control system, thereby causing temperature out of control. The voltage monitor helps to detect voltage anomalies in advance and prevent temperature regulation errors.

[0045] The noise monitor is used to monitor the noise in the signal transmission process between the temperature sensor and the control system in real time, and identify and eliminate communication errors caused by electromagnetic interference (EMI), signal attenuation or crosstalk. The noise monitor should be able to capture the noise in the signal line, including high-frequency and low-frequency interference. Common noise sources include power supply fluctuations, motor operation, external electromagnetic fields, etc. Connect the noise monitor to the data communication line between the temperature sensor and the control system. Make sure that the monitor can detect the noise data in the signal in real time and analyze the signal quality. The noise monitor can monitor the noise changes in the communication signal in real time and generate noise level data. If the noise exceeds the set threshold, an alarm can be triggered or the system can be automatically calibrated to fix the communication error. The noise monitor can timely identify and quantify the signal interference between the sensor and the control system to avoid erroneous data transmission caused by noise interference. Noise in signal transmission may cause the temperature sensor to transmit incorrect temperature data, which in turn affects the regulation of the automation control system. The noise monitor can improve the reliability and accuracy of data transmission.

[0046] By monitoring the power output of the heater through a power meter, the working status of the heater can be tracked in real time to ensure that its output power matches the temperature set point, thereby avoiding temperature runaway caused by abnormal heater power. The power meter should have the function of measuring the power output of the heater in real time and be able to detect instantaneous power changes as well as long-term power trends. Select a multifunctional power meter that can monitor current, voltage, and power factor. Install the power meter in the heater circuit to ensure that the current and voltage of the heater can be accurately measured and the power output can be calculated. The power meter should be directly connected to the input of the heater. The power meter can transmit real-time power data to the central control system and determine whether the heater is working properly by analyzing the changes in power output. If the power output is abnormal, the control system can immediately adjust the heater power or start a backup heater. The power meter provides data on the actual power output of the heater to ensure that the power of the heater is consistent with the temperature control requirements. If the power output is too high or too low, the system can automatically adjust to prevent the temperature from being too high or too low. By monitoring the power output in real time, it is possible to detect signs of heater failure or performance degradation in a timely manner, thereby avoiding overheating of the equipment due to excessive power or incomplete melting of the glass due to insufficient power.

[0047] By installing voltage monitors and noise monitors, it is possible to ensure that the temperature sensor operates in a stable power and signal environment, thereby improving the accuracy of the temperature monitoring data. When the temperature sensor data is inaccurate, it may cause the control system to make continuous incorrect adjustments, forming a vicious feedback loop. By monitoring voltage fluctuations, signal noise, and heater power output in real time, early warnings can be issued and adjustments can be taken before problems occur, thereby preventing this error cycle. Through multiple monitoring and real-time data analysis, the system can adaptively adjust the control strategy to ensure that the temperature and heating power during the glass melting process remain in the optimal state, thereby improving production efficiency and reducing equipment damage.

[0048] In this application, by installing a voltage monitor on the temperature sensor power supply line, installing a noise monitor in the signal transmission line, and using a power meter to monitor the power output of the heater, the temperature control problems caused by electrical interference, signal transmission errors, or abnormal heater power can be effectively reduced. Such a comprehensive monitoring and feedback mechanism can not only monitor and optimize system parameters in real time, but also take corrective measures in time when abnormalities occur, so as to ensure the temperature control accuracy and equipment stability in the glass melting production process.

[0049] S2: Obtain the fluctuation data of the power supply voltage of the temperature sensor in several time periods and the noise data in the signal transmission, analyze them to determine the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and perform weighted average sum calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index.

[0050] According to the sampling frequency of the temperature sensor and the response time of the control system, set the initial time period length. For example, if the temperature sensor samples once per second and the control system makes adjustments every 5 seconds, the time period can be set to 5 seconds or 10 seconds.

[0051] The power supply voltage fluctuation data of the temperature sensor in a certain period of time is collected in real time, and the voltage fluctuation frequency abnormality index is generated after analyzing the fluctuation data of the power supply voltage of the temperature sensor. The method for obtaining the voltage fluctuation frequency abnormality index is as follows:

[0052] Collect voltage fluctuation data during the Q period ; Where v(s) is the value of the voltage signal at time s, N is the number of sampling points, and the time domain signal is converted into a frequency domain signal by fast Fourier transform FFT. FFT converts the voltage signal V(s) into a frequency domain signal V(f), and the calculation formula is: ; is the frequency The corresponding complex Fourier coefficients, j is the imaginary unit, ; is the corresponding frequency, T is the signal sampling period, and k is the frequency index; in order to analyze the frequency component of the voltage fluctuation signal, calculate its amplitude spectrum , that is, the energy distribution at different frequencies, expressed as: ; In the formula, Re( ) and Im ) are The real and imaginary parts of the spectrum; calculate the total energy of the entire spectrum As a reference value, the expression is: ; Identify the amplitude value If the fluctuation is greater than the normal fluctuation, ; Mark it as an abnormal frequency and calculate its energy contribution for the abnormal frequency , the expression is: ; Calculate the voltage fluctuation frequency abnormality index, the expression is: ; In the formula, AK is the voltage fluctuation frequency abnormality index.

[0053] The larger the voltage fluctuation frequency anomaly index is, the more significant abnormal fluctuations are usually present in the power supply line or signal transmission channel where the temperature sensor is located. These abnormal fluctuations may be caused by factors such as electrical interference, equipment failure, and signal delay, thus affecting the accuracy of the data collected by the temperature sensor. When the voltage fluctuation frequency anomaly index is high, it means that the stability of the power supply voltage is poor, and the working environment of the sensor is adversely affected, resulting in errors or deviations in the monitoring data of the temperature sensor. At this time, the temperature sensor may continue to collect erroneous data, thereby affecting the decision-making and adjustment of the entire automation control system, and even causing the temperature to be out of control during the production process, increasing the risk of equipment failure and downtime.

[0054] On the other hand, when the voltage fluctuation frequency anomaly index is small, it means that the voltage fluctuation of the power line where the temperature sensor is located is small, there is less interference in the signal transmission process, and the power supply is relatively stable. In this case, the temperature data collected by the sensor is more likely to be accurate and reliable because the impact of electrical interference, signal delay and other failure factors is small. Therefore, a lower anomaly index is usually associated with higher data accuracy, indicating that the sensor can provide stable and reliable data, which helps the automation control system make accurate temperature adjustment and production decisions, and ensure the smooth progress of the production process.

[0055] The noise data in the temperature sensor signal transmission in several time periods is collected in real time, and the signal noise interference index is generated after the noise data in the temperature sensor signal transmission is analyzed. The method for obtaining the signal noise interference index is:

[0056] Discretize the signal collected by the temperature sensor into a discrete numerical sequence and set the signal ; is a signal sequence of length Z, which is divided into discrete intervals, the signal is segmented, the discrete value of the signal is obtained, and the interval is defined To represent different discrete values, calculate the probability of occurrence of each discrete value in the signal X, form the probability distribution P(X) of the signal, and count each discrete value in the signal Frequency of occurrence , calculate the probability of each discrete value , the expression is: ; Calculate information entropy based on the probability distribution of the signal. Information entropy is used to measure the uncertainty or confusion of the signal. The higher the entropy, the more uncertainty there is in the signal, which may indicate stronger noise. The calculation expression is: ;in, It is the entropy of signal X. If the probability distribution of the signal is relatively uniform, that is, the probability of occurrence of each discrete value is similar, then the entropy is high, indicating that the signal has higher complexity or noise.

[0057] By comparing the entropy of the original signal and the entropy of the denoised signal, the signal noise interference index is calculated, the entropy H(X) of the entire temperature sensor signal sequence is calculated, and the signal is subjected to noise suppression or filtering (such as low-pass filtering, wavelet denoising, etc.) to obtain the denoised signal sequence. , and then calculate its entropy , then calculate the signal noise interference index, the expression is: ; In the formula, is the signal-to-noise interference index.

[0058] The larger the signal-noise interference index, the lower the accuracy of the temperature sensor monitoring data. When the signal-noise interference index is large, it means that the noise component in the signal monitored by the temperature sensor is strong and the entropy value of the signal is high, indicating that the signal has greater uncertainty and confusion. This usually indicates that the signal is affected by a large degree of external interference or the noise of the sensor itself, resulting in unstable and unreliable measurement data. Noise interference will affect the accuracy and response speed of the sensor, which may cause erroneous data to be input into the control system, leading to wrong decisions and adjustments, and ultimately affecting the stability and efficiency of the entire glass production process. At this time, the monitoring data of the temperature sensor is less accurate, and the decisions made by the control system based on this data may cause equipment damage, increased energy consumption, or reduced product quality.

[0059] The smaller the signal-noise interference index, the higher the accuracy of the temperature sensor monitoring data. When the signal-noise interference index is small, it means that the noise component in the signal is low and the entropy value of the signal is small, which means that the signal is relatively stable, clear, and less affected by external interference or sensor failure. In this case, the temperature sensor can provide more accurate temperature data, and the control system can make more effective adjustments based on these accurate data, thereby ensuring the temperature control accuracy and consistency of the glass production process. This can not only improve production efficiency, but also reduce energy waste and equipment wear, and ensure that the quality of the product meets the standards. Therefore, a smaller noise interference index indicates that the monitoring data of the temperature sensor is more accurate, which helps to improve the overall performance of the production process.

[0060] The voltage fluctuation frequency anomaly index and the signal noise interference index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the weighted assignment labels of the accuracy of the temperature sensor monitoring data in each time period as the prediction target, and takes minimizing the sum of the prediction errors of the weighted assignment labels of the accuracy of the temperature sensor monitoring data in all time periods as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The weighted assignment of the accuracy of the temperature sensor monitoring data in each time period is determined according to the model output results. Among them, the machine learning model is a polynomial regression model, and the weighted average summation of the weighted assignment of the accuracy of the temperature sensor monitoring data in each time period is calculated to obtain the monitoring data accuracy index.

[0061] The method for obtaining the weight assignment of the accuracy of the temperature sensor monitoring data in each time period is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, AK is the voltage fluctuation frequency anomaly index, GH is the signal noise interference index, Assign weights to the accuracy of the temperature sensor monitoring data in each time period.

[0062] S3: The oxygen concentration of the gas in the furnace is monitored in real time by an oxygen sensor, and the degree of abnormal change of the oxygen content in the furnace atmosphere is determined according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period.

[0063] Oxygen sensors are used to measure the oxygen concentration in the furnace gas in real time and transmit data to the control system. These data can reflect the oxygen content in the furnace, thereby indirectly inferring the atmosphere in the furnace. Changes in oxygen concentration directly affect the stability and quality of the glass melting process. Oxygen concentration data is usually a continuous real-time data stream. The sensor will record and transmit the oxygen concentration value (such as percentage concentration or PPM value) at regular intervals. Select a set of fixed time periods for data collection. For example, the data collection cycle can be divided into monitoring every few minutes or every hour. The choice of time period depends on the working cycle of the furnace, the reaction time and the requirements of the production process. For example, you can choose a time period of every 10 minutes, 30 minutes or 1 hour to ensure that the fluctuations in the oxygen concentration in the furnace are covered and sufficient time series data is obtained for analysis.

[0064] The oxygen concentration fluctuation deviation index is generated by analyzing the fluctuation of the oxygen concentration of the furnace gas within a fixed time period to judge the degree of abnormal change of the oxygen content in the furnace atmosphere. The method for obtaining the oxygen concentration fluctuation deviation index is as follows:

[0065] Collect oxygen concentration data for a fixed period of time. These data should be recorded at fixed time intervals (such as every minute, every hour, etc.). Set the oxygen concentration data to , where t represents the timestamp, is the oxygen concentration data at time t.

[0066] Select the order of the autoregressive moving average ARMA model. The ARMA model contains autoregressive AR terms and moving average MA terms. The model is expressed as: ;in, is the coefficient of the AR term (autoregression coefficient), is the coefficient of the MA term (moving average coefficient), is the noise term, For in time The white noise residual at time t, uses the autocorrelation function (ACF) and partial autocorrelation function (PACF) to determine the appropriate p and q orders.

[0067] Depending on the chosen order p and q, the parameters of the model are estimated using either the least squares method or the maximum likelihood estimation method. and , or q; use the fitted ARMA model to predict future values ​​of oxygen concentration and calculate the difference between the actual observed values ​​and the model predicted values, that is: ;in, is the residual, For the oxygen concentration value predicted by the ARMA model, the oxygen concentration fluctuation deviation index is calculated, and the expression is: ; Where Y is the total number of data points and KM is the oxygen concentration fluctuation deviation index.

[0068] The larger the oxygen concentration fluctuation deviation index, the more serious the abnormal change in the oxygen content of the furnace atmosphere: when the oxygen concentration fluctuation deviation index increases, it means that the oxygen concentration fluctuation in the furnace atmosphere is more drastic. This usually means that the oxygen concentration changes greatly within a certain period of time, which may be due to the unstable atmosphere caused by certain factors in the furnace (such as incomplete combustion, uneven oxygen supply or changes in the external environment). Frequent fluctuations in oxygen concentration will lead to unstable temperature in the melting furnace, thereby affecting the glass melting process, which may cause the quality of the finished glass to fail to meet the standards, and even cause damage to the equipment or failure of the melting furnace. At this time, a large oxygen concentration fluctuation deviation index can be regarded as a signal of poor atmosphere control, indicating that there may be uneven oxygen supply or other abnormal conditions in the furnace, which may affect production efficiency and quality in severe cases.

[0069] The smaller the oxygen concentration fluctuation deviation index, the less abnormal the oxygen content in the furnace atmosphere is: on the contrary, when the oxygen concentration fluctuation deviation index is small, it means that the oxygen concentration in the furnace atmosphere is relatively stable and the fluctuation is small. Stable oxygen concentration indicates that the atmosphere control in the furnace is more precise, and the oxygen supply and emission are kept within a reasonable range, which is very important for the glass melting process. In this case, the temperature of the glass melting process is more stable, the efficiency of the melting reaction is higher, the impurity removal effect is better, and the final product quality is more reliable. Therefore, a smaller oxygen concentration fluctuation deviation index usually means that the oxygen concentration in the furnace atmosphere fluctuates less, indicating that the oxygen control system is operating well, the production process is stable, and the risk of abnormal changes is low.

[0070] S4: Based on the calculated accuracy index of the monitoring data and the fluctuation of the oxygen concentration of the gas in the furnace, the heating power is dynamically adjusted using fuzzy logic to optimize the melting process.

[0071] The monitoring data accuracy index RY and oxygen concentration fluctuation deviation index KM are used as input items of fuzzy logic, and the heating power of the melting furnace is used as output item;

[0072] The monitoring data accuracy index RY is usually between 0 and 1 (the larger the value, the more accurate the data). Fuzzy definition: Low Accuracy: RY is less than a certain threshold (such as 0.3). Medium Accuracy: RY is between 0.3 and 0.7. High Accuracy: RY is greater than 0.7.

[0073] The oxygen concentration fluctuation deviation index KM indicates the degree of fluctuation of oxygen concentration, ranging from 0 to a certain maximum value. Generally, the larger the value, the more serious the fluctuation. Fuzzy definition: Low Variation: KM is less than a certain threshold (such as 0.3). Medium Variation: KM is between 0.3 and 0.7. High Variation: KM is greater than 0.7.

[0074] The output variable is the heating power of the furnace, which is dynamically adjusted according to the input RY and KM. For simplicity, it is assumed that the range of heating power is 0 to 100, which represents the percentage of heating power of the furnace. Low Power: 0 - 30%; Medium Power: 30% - 70%; High Power: 70% - 100%.

[0075] Construct a fuzzy rule system based on RY and KM. Fuzzy rules connect the relationship between input variables and output variables through fuzzy logic. The following are some possible rules:

[0076] Rule 1: If RY is low accuracy and KM is high fluctuation, the heating power is low power. Rule 2: If RY is medium accuracy and KM is medium fluctuation, the heating power is medium power. Rule 3: If RY is high accuracy and KM is low fluctuation, the heating power is high power. Rule 4: If RY is low accuracy and KM is low fluctuation, the heating power is medium power. Rule 5: If RY is high accuracy and KM is high fluctuation, the heating power is medium power.

[0077] The actual measured RY and KM values ​​are converted into fuzzy sets. For example, for RY=0.6 and KM=0.4, their fuzzy values ​​are determined according to the defined membership function.

[0078] Based on the defined fuzzy rules, the fuzzy value of the heating power is obtained through the reasoning process. The reasoning process combines the rules and inputs through fuzzy operations (such as minimum value, weighted average) to generate the output fuzzy results.

[0079] In the process of reasoning, a fuzzy heating power value is obtained, for example, a fuzzy value in the range of "medium power". In order to convert this fuzzy result into a specific heating power value, defuzzification is required. The commonly used defuzzification method is the weighted average method.

[0080] After defuzzification, a specific heating power value is obtained, which represents the adjustment value of the heating power in the melting furnace.

[0081] The defuzzified heating power value is fed back to the automated control system, which adjusts the heating power in the furnace based on this value to optimize the glass melting process. The adjustment of the heating power affects the temperature control of the furnace, thereby improving the melting efficiency of the glass and the quality of the final product.

[0082] In the fuzzy logic system, by analyzing the monitoring data accuracy (RY) of the temperature sensor and the fluctuation deviation of the oxygen concentration (KM), a specific heating power value is finally obtained by using fuzzy reasoning and defuzzification process. For example, the heating power after defuzzification may be 68% (that is, the heating power of the melting furnace should be adjusted to 68%).

[0083] The defuzzified heating power value is fed back to the automation control system. This feedback is a real-time control signal that represents the required power output of the heating system. The automation control system uses this value as a control variable and compares it with the current furnace heating power to determine whether the power output of the heating equipment needs to be adjusted.

[0084] The automation control system adjusts the furnace temperature by controlling the power output of the heating equipment according to the current heating power and the target heating power (the defuzzified value). The adjustment methods may include: Electric heaters of the heating furnace: increase or decrease the power input to increase or decrease the heating power. Gas flow of the gas furnace: adjust the gas supply to achieve the required heating power. The control system will use a precise feedback mechanism (such as a PID controller) to adjust the heating power to ensure that the temperature of the melting furnace is stable within the optimal range to avoid glass quality problems caused by excessive temperature fluctuations.

[0085] By precisely adjusting the heating power, the temperature inside the furnace can be gradually increased or decreased as needed, thereby optimizing the glass melting process: keeping the furnace temperature within the optimal temperature range for glass melting (usually 1300°C to 1500°C) ensures that the glass melts evenly and without bubbles or impurities. If the glass melts slowly or the oxygen concentration fluctuates greatly, increasing the heating power can accelerate the melting reaction and improve production efficiency. Dynamically adjusting the heating power based on the accuracy of the monitoring data and the fluctuation of the oxygen concentration helps to reduce energy waste and avoid excessive energy consumption caused by too high or too low temperatures. By optimizing the heating power and controlling the oxygen concentration, the uniformity of the glass composition can be ensured and the quality of the finished glass can be avoided due to unstable temperature or atmosphere fluctuations.

[0086] The control process is real-time, so the automation system needs to constantly monitor the data from the temperature sensor, the data from the oxygen sensor, and the actual output of the heating power. The system periodically acquires this data and reruns the fuzzy logic control to dynamically adjust the heating power. This closed-loop feedback control helps to respond to any changes in production, such as changes in raw materials, fluctuations in equipment performance, or changes in environmental conditions.

[0087] In this embodiment, by installing a voltage monitor in the power supply line of the temperature sensor, installing a noise monitor in the communication line between the sensor and the control system, and monitoring the heating power of the heater in real time through a power meter, the temperature sensor power supply voltage fluctuation and signal noise data are obtained and analyzed, and then the weight assignment of the accuracy of the temperature sensor monitoring data in each time period is calculated, and the monitoring data accuracy index is obtained by weighted average. At the same time, an oxygen sensor is used to monitor the change of oxygen concentration in the furnace to determine the abnormal change of oxygen content in the furnace atmosphere. In combination with the monitoring data accuracy index and oxygen concentration fluctuation, fuzzy logic is used to adjust the heating power, thereby optimizing the glass melting process, improving production efficiency, reducing energy waste, and ensuring the stability of glass quality.

[0088] Embodiment 2, a control system in a glass product manufacturing process described in this embodiment includes a sensor monitoring module, a data analysis module, an oxygen concentration monitoring module and a fuzzy logic control module;

[0089] Sensor monitoring module: A voltage monitor is installed on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and a noise monitor is installed in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and the heating power output of the heater is monitored in real time through a power meter;

[0090] Data analysis module: obtains the fluctuation data of the power supply voltage of the temperature sensor in several time periods and the noise data in the signal transmission, analyzes them, determines the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and performs weighted average summation calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index;

[0091] Oxygen concentration monitoring module: monitors the oxygen concentration of the gas in the furnace in real time through the oxygen sensor, and determines the degree of abnormal change of the oxygen content in the furnace atmosphere according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period;

[0092] Fuzzy logic control module: Based on the calculated accuracy index of monitoring data and the fluctuation of oxygen concentration in the furnace gas, fuzzy logic is used to dynamically adjust the heating power and optimize the melting process.

[0093] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A control method in a glass product manufacturing process, characterized in that: The steps include: S1: Install a voltage monitor on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and install a noise monitor in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and monitor the heating power output of the heater in real time through a power meter; S2: Obtain fluctuation data of the power supply voltage of the temperature sensor in several time periods and noise data in signal transmission, analyze them to determine the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and perform weighted average sum calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index; S3: monitor the oxygen concentration of the gas in the furnace in real time through the oxygen sensor, and judge the degree of abnormal change of the oxygen content of the atmosphere in the furnace according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period; S4: Based on the calculated accuracy index of the monitoring data and the fluctuation of the oxygen concentration of the gas in the furnace, the heating power is dynamically adjusted using fuzzy logic to optimize the melting process.

2. The control method in a glass product manufacturing process according to claim 1, characterized in that: In S2, the voltage fluctuation frequency abnormality index is generated after analyzing the fluctuation data of the temperature sensor power supply voltage. The method for obtaining the voltage fluctuation frequency abnormality index is: Collect voltage fluctuation data during the Q period ; Where v(s) is the value of the voltage signal at time s, N is the number of sampling points, and the time domain signal is converted into a frequency domain signal by fast Fourier transform FFT. FFT converts the voltage signal V(s) into a frequency domain signal V(f), and the calculation formula is: ; is the frequency The corresponding complex Fourier coefficients, j is the imaginary unit, ; is the corresponding frequency, T is the signal sampling period, and k is the frequency index; in order to analyze the frequency component of the voltage fluctuation signal, calculate its amplitude spectrum , that is, the energy distribution at different frequencies, expressed as: ; In the formula, Re( ) and Im ) are The real and imaginary parts of the spectrum; calculate the total energy of the entire spectrum As a reference value, the expression is: ; Identify the amplitude value If the fluctuation is greater than the normal fluctuation, ; Mark it as an abnormal frequency and calculate its energy contribution for the abnormal frequency , the expression is: ; Calculate the voltage fluctuation frequency abnormality index, the expression is: ; Where AK is the voltage fluctuation frequency abnormality index.

3. The control method in a glass product manufacturing process according to claim 2, characterized in that: In S2, the signal collected by the temperature sensor is discretized into a discrete numerical sequence, and the signal is set ; is a signal sequence of length Z, which is divided into discrete intervals, the signal is segmented, the discrete value of the signal is obtained, and the interval is defined To represent different discrete values, calculate the probability of occurrence of each discrete value in the signal X, form the probability distribution P(X) of the signal, and count each discrete value in the signal Frequency of occurrence , calculate the probability of each discrete value , the expression is: ; Calculate the information entropy according to the probability distribution of the signal, and the calculation expression is: ;in, is the entropy of signal X. By comparing the entropy of the original signal and the entropy of the denoised signal, the signal noise interference index is calculated, and the entropy H(X) of the entire temperature sensor signal sequence is calculated. The signal is subjected to noise suppression to obtain the denoised signal sequence. , and then calculate its entropy , then calculate the signal noise interference index, the expression is: ; In the formula, is the signal-to-noise interference index.

4. The control method in a glass product manufacturing process according to claim 3, characterized in that: In S2, the voltage fluctuation frequency anomaly index and the signal noise interference index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the weighted assignment labels of the accuracy of the temperature sensor monitoring data in each time period as the prediction target, and takes minimizing the sum of the prediction errors of the weighted assignment labels of the accuracy of the temperature sensor monitoring data in all time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weighted assignment of the accuracy of the temperature sensor monitoring data in each time period is determined according to the model output results, wherein the machine learning model is a polynomial regression model, and the weighted average summation of the weighted assignments of the accuracy of the temperature sensor monitoring data in each time period is calculated to obtain the monitoring data accuracy index.

5. The control method in a glass product manufacturing process according to claim 4, characterized in that: In S3, the oxygen concentration fluctuation deviation index is generated after analyzing the oxygen concentration fluctuation of the furnace gas within a fixed time period, and the degree of abnormal change of the oxygen content in the furnace atmosphere is judged. The method for obtaining the oxygen concentration fluctuation deviation index is: Collect oxygen concentration data within a fixed time period and set the oxygen concentration data to , where t represents the timestamp, is the oxygen concentration data at time t; select the order of the autoregressive moving average ARMA model, the ARMA model contains autoregressive AR terms and moving average MA terms, and the model is expressed as: ;in, is the coefficient of the AR term, is the coefficient of the MA term, is the noise term, For in time The white noise residual at the moment uses the autocorrelation function and partial autocorrelation function to determine the p and q orders; according to the selected orders p and q, the parameters of the model are estimated and , or q; use the fitted ARMA model to predict future values ​​of oxygen concentration and calculate the difference between the actual observed values ​​and the model predicted values, that is: ;in, is the residual, For the oxygen concentration value predicted by the ARMA model, the oxygen concentration fluctuation deviation index is calculated, and the expression is: ; Where Y is the total number of data points and KM is the oxygen concentration fluctuation deviation index.

6. The control method in the glass product manufacturing process according to claim 5, characterized in that: In S4, according to the calculated monitoring data accuracy index and the fluctuation of oxygen concentration in the furnace gas, the heating power is dynamically adjusted using fuzzy logic to optimize the melting process, specifically: The monitoring data accuracy index RY and oxygen concentration fluctuation deviation index KM are used as input items of fuzzy logic, and the heating power of the melting furnace is used as output item; The monitoring data accuracy index, oxygen concentration fluctuation deviation index and heating power of the melting furnace are fuzzy processed respectively; Construct fuzzy rules based on RY and KM. Fuzzy rules connect the relationship between input variables and output variables through fuzzy logic; Convert the actually measured RY and KM values ​​into fuzzy sets; Based on the defined fuzzy rules, the fuzzy value of heating power is obtained through the reasoning process; In the reasoning process, a fuzzy heating power value is obtained and defuzzified at the same time, and a specific heating power value is obtained after defuzzification; The defuzzified heating power value is fed back to the automatic control system, and the system will adjust the heating power in the melting furnace according to the heating power value, thereby optimizing the glass melting process.

7. A control system in a glass product manufacturing process, used to implement a control method in a glass product manufacturing process according to any one of claims 1 to 6, characterized in that: It includes sensor monitoring module, data analysis module, oxygen concentration monitoring module and fuzzy logic control module; Sensor monitoring module: A voltage monitor is installed on the power supply line of the temperature sensor to detect the fluctuation data of the power supply voltage in real time, and a noise monitor is installed in the communication line between the temperature sensor and the control system to monitor the noise data in signal transmission in real time, and the heating power output of the heater is monitored in real time through a power meter; Data analysis module: obtains the fluctuation data of the power supply voltage of the temperature sensor in several time periods and the noise data in the signal transmission, analyzes them, determines the weight assignment of the accuracy of the temperature sensor monitoring data in each time period, and performs weighted average summation calculation on the weight assignment of the accuracy of the temperature sensor monitoring data in each time period to obtain the monitoring data accuracy index; Oxygen concentration monitoring module: monitors the oxygen concentration of the gas in the furnace in real time through the oxygen sensor, and determines the degree of abnormal change of the oxygen content in the furnace atmosphere according to the fluctuation of the oxygen concentration of the gas in the furnace within a fixed time period; Fuzzy logic control module: Based on the calculated accuracy index of monitoring data and the fluctuation of oxygen concentration in the furnace gas, fuzzy logic is used to dynamically adjust the heating power and optimize the melting process.

Images