Electrical steel strip annealing temperature real-time monitoring and regulation system

Abstract

The invention relates to the technical field of steel production and processing, and discloses an electrical steel strip annealing temperature real-time monitoring and regulation system. The system comprises a temperature data acquisition module which is responsible for acquiring temperature and cooling rate data in an annealing process and acquiring expected parameters; the temperature deviation analysis module is used for calculating a deviation coefficient through a dynamic weighting algorithm to construct a matrix; the dynamic regulation and control module is used for generating regulation and control parameters based on a fuzzy logic control algorithm; the abnormity grading module is used for grading annealing abnormity; and the real-time feedback module transmits the regulation and control parameters and the abnormal identifier to the control end. The system also has the functions of adjusting a rule base according to the characteristics of the steel strip, backtracking historical data, optimizing regulation and control, adaptively updating an abnormal threshold value and the like. Through cooperative work of all the modules, real-time monitoring and accurate regulation and control of the annealing temperature are achieved, the annealing quality and production efficiency of the electrical steel strip are improved, and the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of steel production and processing, and particularly to a real-time monitoring and control system for the annealing temperature of electrical steel strips. Background Art

[0002] In the steel production industry, electrical steel, as an important soft magnetic alloy material, its performance has a crucial impact on the operating efficiency and energy loss of power equipment. The annealing process is one of the core links determining the performance of electrical steel strips, and the precise control of the annealing temperature is directly related to key performance indicators such as the crystal structure, magnetic permeability, and iron loss of electrical steel. However, there are many challenges in the temperature control during the annealing process of current electrical steel strips.

[0003] Traditional annealing temperature monitoring methods have obvious defects. On the one hand, the layout and accuracy limitations of temperature sensors result in the data collected being unable to comprehensively and accurately reflect the temperature distribution of the entire annealing area. For example, in some large annealing furnaces, the number of sensors is limited and unevenly distributed, making it difficult to timely capture the temperature changes in some areas, and it is easy to have blind spots in temperature monitoring, which may cause local temperatures to be too high or too low, affecting the consistency of the overall quality of the steel strip. On the other hand, existing monitoring systems often only focus on the real-time measurement of temperature and lack effective monitoring and comprehensive analysis of the cooling rate. The cooling rate also has an important impact on the organizational structure and performance of electrical steel, and an unreasonable cooling rate may cause problems such as stress concentration and organizational defects inside the steel strip, reducing the performance and qualification rate of the product.

[0004] The annealing temperature control technology also needs to be improved. Existing control methods are mostly based on fixed empirical parameters or simple control algorithms and are difficult to adapt to complex and changeable production conditions. In actual production, factors such as the material, thickness, and production speed of electrical steel strips will affect the required annealing temperature. For example, for steel strips of different thicknesses, under the same heating and cooling conditions, the rate and law of temperature change are quite different. Traditional control methods cannot dynamically adjust the heating power and cooling rate according to these real-time changing factors, resulting in a large deviation between the annealing temperature and the desired curve, seriously affecting the stability of product quality.

[0005] The handling mechanism for abnormal situations also has deficiencies. During the annealing process, once a temperature anomaly occurs, existing systems often cannot quickly and accurately determine the severity of the anomaly and take effective countermeasures in a timely manner. This may not only lead to the production of a large number of unqualified products, increasing production costs, but also cause damage to the annealing equipment, shortening the service life of the equipment, and affecting the continuity and efficiency of production. With the continuous improvement of the performance requirements for electrical steel in the power industry, and the increasing emphasis on production efficiency and product quality control by steel production enterprises, it has become particularly urgent to develop a system that can monitor and precisely control the annealing temperature of electrical steel strips in real time. Such a system needs to overcome the defects of traditional technologies, achieve comprehensive and accurate monitoring of the annealing temperature and cooling rate, possess intelligent and efficient control capabilities, as well as a perfect abnormal situation handling mechanism, to meet the high-quality and high-efficiency requirements of modern steel production. Summary of the Invention

[0006] The purpose of the present invention is to provide a real-time monitoring and control system for the annealing temperature of electrical steel strips to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above purpose, the present invention provides the following technical solution: A real-time monitoring and control system for the annealing temperature of electrical steel strips, the system includes:

[0008] A temperature data acquisition module, which is used to collect temperature monitoring data and cooling rate monitoring data of each heating zone during the annealing process in real time, and receive a preset expected annealing temperature curve and an expected cooling rate value;

[0009] A temperature deviation analysis module, which performs multi-dimensional deviation calculations on the temperature monitoring data, cooling rate monitoring data, the expected annealing temperature curve, and the expected cooling rate value through a dynamic weighting algorithm to generate a temperature deviation coefficient matrix;

[0010] A dynamic control module, which generates heating power control parameters and cooling rate compensation parameters based on the fuzzy logic control algorithm according to the temperature deviation coefficient matrix;

[0011] An abnormal situation grading module, which is used to divide the abnormal situation level of the current annealing stage according to whether the deviation coefficients of each dimension in the temperature deviation coefficient matrix exceed the dynamic threshold, and output an abnormal situation level identifier;

[0012] A real-time feedback module, which transmits the heating power control parameters, cooling rate compensation parameters, and abnormal situation level identifier to the control terminal of the annealing furnace;

[0013] Among them, the execution steps of the temperature deviation analysis module include:

[0014] Extract the time series of temperature monitoring data for each heating zone, perform point-by-point matching with the expected annealing temperature curve, and calculate the temperature time series deviation coefficient;

[0015] Perform a sliding window comparison between the cooling rate monitoring data and the expected cooling rate value to generate a cooling rate fluctuation coefficient;

[0016] Construct a temperature deviation coefficient matrix containing weight factors based on the temperature time series deviation coefficient and the cooling rate fluctuation coefficient.

[0017] Preferably, the execution steps of the dynamic regulation module further include:

[0018] Input the temperature deviation coefficient matrix into a fuzzy logic controller, and perform fuzzy processing on the deviation interval through a preset membership function;

[0019] Generate fuzzy outputs of heating power regulation parameters and cooling rate compensation parameters based on a fuzzy rule base, and convert them into precise control instructions through a defuzzification algorithm.

[0020] Preferably, the execution steps of the temperature data acquisition module include:

[0021] Collect real-time temperature data for each heating zone through a distributed temperature sensor array and record the time stamp;

[0022] Obtain the steel strip conveying speed through a laser velocimeter, and calculate the cooling rate monitoring value in combination with the thermal imaging data of the cooling zone;

[0023] Retrieve the expected annealing temperature curve and the expected cooling rate value matching the current steel strip model from the annealing process database;

[0024] Add the real-time temperature data and the cooling rate monitoring value to the temperature monitoring data set, and synchronously store the time stamp information.

[0025] Preferably, the execution steps of the temperature deviation analysis module further include:

[0026] Define the calculation formula for the temperature time series deviation coefficient as:

[0027]

[0028] where, δ T is the temperature time series deviation coefficient, T 监测,i is the monitored temperature at the i-th time point, T 期望,i is the corresponding expected temperature, w i is the dynamic weight factor within the time window, and N is the number of sampling points;

[0029] Define the calculation formula for the cooling rate fluctuation coefficient as:

[0030]

[0031] Among them, δ C is the cooling rate fluctuation coefficient, C 监测 is the actually monitored cooling rate value, C 期望 is the preset expected value of the cooling rate, and α is the correction factor for the sensitivity of the cooling rate.

[0032] Preferably, the execution steps of the dynamic regulation module further include:

[0033] Dynamically adjust the rule base of the fuzzy logic controller according to the steel strip thickness and material properties, including:

[0034] If the proportion of the deviation in the high-temperature area in the temperature deviation coefficient matrix exceeds 50%, the cooling rate compensation parameter is preferentially increased;

[0035] If the deviation in the low-temperature area continuously exceeds 3 sampling periods, a stepped increase strategy for the heating power is triggered.

[0036] Preferably, the execution steps of the anomaly classification module include:

[0037] Calculate the regional anomaly index according to the deviation coefficients of each heating zone in the temperature deviation coefficient matrix:

[0038]

[0039] Among them, R j is the anomaly index of the jth heating subzone, δ T,j,k is the temperature time-series deviation coefficient of the kth monitoring point in the jth heating subzone, γ k is the kth weight factor of region j, and M is the number of monitoring points in the region;

[0040] If the regional anomaly index exceeds the preset threshold, the corresponding region is marked as a first-level anomaly; otherwise, it is marked as a second-level anomaly.

[0041] Preferably, the dynamic regulation module is further connected with a historical data backtracking unit, and the execution steps of the historical data backtracking unit include:

[0042] Retrieve cases in the historical annealing records with a similarity greater than 80% to the current temperature deviation coefficient matrix, and extract the corresponding optimization scheme for the regulation parameters;

[0043] Perform weighted fusion on the optimization scheme and the output result of the fuzzy logic controller to generate the final regulation instruction.

[0044] Preferably, the anomaly classification module is further connected with an adaptive threshold update unit, and its execution steps include:

[0045] Statistically analyze the temperature deviation coefficient distribution of each heating zone within the last 24 hours, and dynamically adjust the threshold range for abnormal level classification;

[0046] If no abnormality is triggered within 10 consecutive sampling periods, reduce the threshold sensitivity by 5%.

[0047] Preferably, the execution steps of the real-time feedback module further include:

[0048] Encapsulate the control parameters and abnormal level identifiers into a JSON format data packet and transmit it to the annealing furnace control terminal through the industrial Ethernet;

[0049] Visualize the temperature deviation distribution and abnormal level identifiers of each heating zone in the form of a heat map on the control terminal interface.

[0050] Preferably, the present invention further includes an electronic device, and the device includes:

[0051] A memory for storing the control program of the real-time monitoring and regulation system for the annealing temperature of electrical steel strips as described in the present invention;

[0052] A processor for executing the control program to achieve real-time monitoring and regulation of the annealing temperature of electrical steel strips.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] The real-time monitoring and regulation system for the annealing temperature of electrical steel strips of the present invention has many significant beneficial effects. In terms of data collection, the temperature data collection module collects real-time temperature data of each heating zone through a distributed temperature sensor array and records the time stamp, combines the laser velocimeter and the thermal imaging data of the cooling zone to obtain the cooling rate monitoring value, and simultaneously retrieves the matching annealing temperature desired curve and cooling rate desired value from the annealing process database, ensuring that the collected data is comprehensive, accurate and closely related to actual production, providing a solid foundation for subsequent precise analysis and regulation.

[0055] The temperature deviation analysis module uses a dynamic weighting algorithm to calculate the temperature time series deviation coefficient and the cooling rate fluctuation coefficient, constructs a temperature deviation coefficient matrix, and realizes multi-dimensional accurate analysis of the temperature and cooling rate deviations during the annealing process. This comprehensive and detailed deviation calculation method can accurately reflect the difference between the actual annealing situation and the ideal state, providing a key basis for subsequent regulation. Compared with the traditional simple comparison method, it greatly improves the accuracy and reliability of the analysis.

[0056] The dynamic regulation module generates heating power regulation parameters and cooling rate compensation parameters based on the fuzzy logic control algorithm according to the temperature deviation coefficient matrix. First, it performs fuzzy processing on the deviation interval through a preset membership function, then generates a fuzzy output based on the fuzzy rule base, and finally converts it into an accurate control instruction through a defuzzification algorithm. This process simulates the human thinking mode, fully considers various complex situations, can flexibly adjust the regulation parameters according to the real-time deviation, makes the annealing temperature closer to the expected curve, and effectively improves the accuracy and stability of temperature regulation. For example, when the thickness and material properties of the steel strip change, it can also dynamically adjust the fuzzy logic controller rule base to further optimize the regulation strategy and ensure the annealing quality.

[0057] The anomaly classification module classifies the anomaly levels according to the temperature deviation coefficient matrix. By calculating the regional anomaly index and comparing it with the preset threshold, it accurately judges the degree of anomaly and outputs the anomaly level identifier. This enables the operator to quickly understand the anomaly situation during the annealing process, take corresponding measures in a timely manner for different levels of anomalies, avoid the problem from deteriorating, reduce the production of unqualified products, and lower the production cost.

[0058] The real-time feedback module encapsulates the regulation parameters and the anomaly level identifier into a JSON format data packet and transmits it to the annealing furnace control end through the industrial Ethernet, and visualizes it in the form of a heat map on the control end interface. This method enables the operator to intuitively and clearly grasp the temperature deviation distribution and anomaly status of each heating zone, facilitating timely decision-making and operation, and improving the visualization degree and management efficiency of the production process. The historical data retrieval unit and the adaptive threshold update unit in the system further enhance the system performance. The historical data retrieval unit retrieves similar cases, extracts optimization solutions and weights and fuses them with the output results of the fuzzy logic controller, providing more references for regulation and improving the regulation effect; the adaptive threshold update unit dynamically adjusts the anomaly level division threshold according to the temperature deviation coefficient distribution, improving the accuracy and adaptability of anomaly monitoring. Description of the Drawings

[0059] Figure 1 It is the working principle diagram of the real-time monitoring and regulation system for the annealing temperature of the electrical steel strip described in the present invention;

[0060] Figure 2 It is the flowchart of data acquisition and processing of the temperature data acquisition module;

[0061] Figure 3 It is the flowchart of the regulation strategy based on deviation of the dynamic regulation module;

[0062] Figure 4 It is the flowchart of historical data retrieval and optimization of the dynamic regulation module. Detailed Embodiment

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Please refer to Figures 1-4 , the present invention provides a real-time monitoring and control system for the annealing temperature of electrical steel strips, and its overall implementation solution is as follows:

[0065] The temperature data acquisition module plays a fundamental role in data collection in the entire system. It uses specific devices and methods to collect the temperature monitoring data and cooling rate monitoring data of each heating zone during the annealing process in real time. Specifically, when collecting temperature data, a distributed temperature sensor array is used. This array can accurately obtain the real-time temperature data of each heating zone and record an accurate timestamp for each data for subsequent analysis. In terms of obtaining the cooling rate monitoring data, a laser velocimeter is used to obtain the conveying speed of the steel strip, and then the cooling rate monitoring value is calculated in combination with the thermal imaging data in the cooling zone. At the same time, this module also retrieves the expected annealing temperature curve and the expected cooling rate value that match the current steel strip model from the annealing process database, adds all the collected real-time temperature data and cooling rate monitoring values to the temperature monitoring data set, and synchronously stores the timestamp information to provide comprehensive and accurate data support for subsequent analysis and control.

[0066] The temperature deviation analysis module receives the data transmitted by the temperature data acquisition module and uses the dynamic weighted algorithm to perform multi-dimensional deviation calculations on the temperature monitoring data, cooling rate monitoring data, annealing temperature expected curve, and expected cooling rate value. It first extracts the time series of the temperature monitoring data of each heating zone, performs point-by-point matching with the annealing temperature expected curve, and calculates the temperature time series deviation coefficient; then performs a sliding window comparison between the cooling rate monitoring data and the expected cooling rate value to generate a cooling rate fluctuation coefficient; finally, based on these two coefficients, a temperature deviation coefficient matrix containing weight factors is constructed. This matrix comprehensively reflects the deviation degree of the temperature and cooling rate from the expected situation during the annealing process, providing a key basis for subsequent control and anomaly judgment.

[0067] The dynamic regulation module generates heating power regulation parameters and cooling rate compensation parameters based on the fuzzy logic control algorithm according to the temperature deviation coefficient matrix. First, it inputs the temperature deviation coefficient matrix into the fuzzy logic controller, performs fuzzy processing on the deviation interval through the preset membership function, and converts the accurate deviation value into a fuzzy linguistic variable. Then, based on the fuzzy rule base, it generates the fuzzy output of the heating power regulation parameters and cooling rate compensation parameters, and then converts the fuzzy output into an accurate control instruction through the defuzzification algorithm, so as to achieve precise regulation of the heating power and cooling rate during the annealing process.

[0068] The anomaly grading module classifies the anomaly level of the current annealing stage according to whether the deviation coefficients of each dimension in the temperature deviation coefficient matrix exceed the dynamic threshold. By calculating the regional anomaly index of each heating zone, if the regional anomaly index exceeds the preset threshold, the corresponding area is marked as a first-level anomaly; otherwise, it is marked as a second-level anomaly. The anomaly level identifier output by this module helps the operator to detect anomalies in the annealing process in a timely manner and take corresponding measures.

[0069] The real-time feedback module is responsible for transmitting the heating power regulation parameters, cooling rate compensation parameters generated by the dynamic regulation module and the anomaly level identifier output by the anomaly grading module to the annealing furnace control terminal. It encapsulates these data into a JSON format data packet and transmits it efficiently through the industrial Ethernet. At the same time, in the control terminal interface, the temperature deviation distribution and anomaly level identifier of each heating zone are visualized in the form of a heat map, so that the operator can intuitively and clearly understand the temperature situation and anomaly status during the annealing process, which is convenient for making decisions in a timely manner.

[0070] The following further illustrates the implementation of the present invention in conjunction with Embodiments 1 to 6.

[0071] Embodiment 1:

[0072] In this embodiment, the working processes of the dynamic regulation module and the temperature deviation analysis module are further elaborated in detail.

[0073] When the dynamic regulation module generates heating power regulation parameters and cooling rate compensation parameters, it inputs the temperature deviation coefficient matrix into the fuzzy logic controller. A variety of membership functions are preset in the fuzzy logic controller, such as triangular membership function, trapezoidal membership function, etc. Taking the temperature deviation as an example, for different deviation ranges, fuzzy processing is performed through the corresponding membership function. Assuming that when the temperature deviation is large, under the action of the membership function, its fuzzy linguistic variable may be "very large"; when the deviation is small, the linguistic variable may be "very small".

[0074] Generate fuzzy outputs for heating power regulation parameters and cooling rate compensation parameters based on the fuzzy rule base. The fuzzy rule base is established according to a large amount of experimental data and practical experience. For example, when the temperature deviation is "very large" and the cooling rate fluctuation is also "relatively large", the fuzzy rule base will give corresponding fuzzy outputs of heating power regulation parameters and cooling rate compensation parameters. Then, the fuzzy outputs are converted into precise control instructions through defuzzification algorithms. Commonly used defuzzification algorithms include the centroid method, the maximum membership degree method, etc. Taking the centroid method as an example, it determines the precise value by calculating the centroid of the region enclosed by the membership function curve of the fuzzy set and the abscissa.

[0075] When calculating the temperature time-series deviation coefficient and the cooling rate fluctuation coefficient, the temperature deviation analysis module has specific calculation formulas. Define the calculation formula for the temperature time-series deviation coefficient as:

[0076]

[0077] where δ T is the temperature time-series deviation coefficient, which comprehensively reflects the deviation degree between the monitored temperature and the desired temperature over a period of time. T 监测,i is the monitored temperature at the i-th time point, which is the temperature data of each heating zone during the annealing process actually collected at a certain moment. T 期望,i is the corresponding desired temperature, which is the temperature value at the i-th time point on the annealing temperature desired curve retrieved from the annealing process database according to the current steel strip model. w i is the dynamic weight factor within the time window, which will be adjusted according to the actual situation. For example, during the critical stage of the annealing process, the weight of the data closer to the current moment may be greater to highlight the impact of recent temperature changes. N is the number of sampling points, which is the number of sampling times within the time window selected when calculating the temperature time-series deviation coefficient. The number of sampling points will affect the accuracy and stability of the calculation results.

[0078] Define the calculation formula for the cooling rate fluctuation coefficient as:

[0079]

[0080] where δ C is the cooling rate fluctuation coefficient, which is used to measure the fluctuation between the actual cooling rate and the desired cooling rate. C 期望 is the actually monitored cooling rate value, which is calculated by obtaining the steel strip conveying speed through a laser speedometer and combining the thermal imaging data of the cooling zone. C 期望$v_0$ is the expected value of the preset cooling rate, which is also retrieved from the annealing process database according to the steel strip model. $\alpha$ is the correction factor for the sensitivity of the cooling rate, which is set according to different steel strip materials and annealing process requirements and is used to adjust the sensitivity of the cooling rate fluctuation coefficient to the actual cooling rate fluctuation. For example, for some steel strip materials with high requirements for the cooling rate, the value of $\alpha$ may be set larger to more timely reflect the fluctuation of the cooling rate. The temperature sequence deviation coefficient and the cooling rate fluctuation coefficient calculated by these formulas provide an accurate data basis for constructing the temperature deviation coefficient matrix.

[0081] Example 2:

[0082] The temperature data acquisition module plays an important role as the data source in the entire system. Its working process includes multiple specific steps.

[0083] Collect the real-time temperature data of each heating zone through the distributed temperature sensor array. The distributed temperature sensor array consists of multiple temperature sensors distributed at different positions. These sensors have the characteristics of high precision and high sensitivity and can accurately measure the temperature at different positions in each heating zone. While collecting the temperature data, a time stamp is recorded for each data, accurate to the millisecond level, to ensure that subsequent data analysis can accurately correspond to specific time points.

[0084] Obtain the steel strip conveying speed through a laser velocimeter. The laser velocimeter uses the laser Doppler effect to calculate the conveying speed of the steel strip by measuring the frequency change of the reflected light of the laser irradiated on the surface of the steel strip. After obtaining the steel strip conveying speed, calculate the monitored value of the cooling rate in combination with the thermal imaging data of the cooling zone. The thermal imaging data of the cooling zone is obtained by a thermal imager, which can capture the temperature distribution on the surface of the steel strip in the cooling zone. By analyzing the change of temperature with time in the thermal imaging data and the conveying speed of the steel strip, the monitored value of the cooling rate is calculated using a specific algorithm.

[0085] Retrieve the expected annealing temperature curve and the expected cooling rate corresponding to the current steel strip model from the annealing process database. The annealing process database stores a large number of annealing process parameters corresponding to different steel strip models, including the expected annealing temperature curve and the expected cooling rate. In actual production, according to the steel strip model currently being produced, the system can quickly and accurately retrieve the corresponding parameters from the database.

[0086] Add the real-time temperature data and the monitored cooling rate values to the temperature monitoring data set, and synchronously store the timestamp information. The temperature monitoring data set is stored in the form of a database for convenient data management and query. During the storage process, the temperature data, the monitored cooling rate values, and the timestamp information are associated and stored in a certain format. For example, using the table structure of a relational database, the timestamp is used as the primary key, and the temperature data and the monitored cooling rate values are stored as fields. In this way, subsequent modules such as the temperature deviation analysis module and the dynamic regulation module can conveniently obtain the required data from the temperature monitoring data set for analysis and processing. Through these operations of the temperature data acquisition module, accurate and timely data support is provided for the entire real-time monitoring and regulation system of the annealing temperature of electrical steel strips, ensuring that the system can effectively monitor and regulate the annealing process.

[0087] Embodiment 3:

[0088] During the actual operation of the dynamic regulation module, the rule base of the fuzzy logic controller is dynamically adjusted according to the strip thickness and material properties to achieve more precise regulation.

[0089] During the annealing process, strips of different thicknesses have different requirements for temperature and cooling rate. For thicker strips, their heat capacity is larger, and the heating and cooling are relatively slower. When the proportion of the deviation in the high-temperature region in the temperature deviation coefficient matrix exceeds 50%, it indicates that the temperature in the high-temperature region deviates significantly from the desired temperature. In this case, the cooling rate compensation parameter is preferentially increased. Because if a thicker strip stays in the high-temperature region for too long, it may cause problems with the strip's microstructure and properties. By increasing the cooling rate compensation parameter, the cooling speed of the strip in the high-temperature region can be accelerated, enabling it to quickly return to a reasonable temperature range. For example, if the current electrical steel strip being produced has a thickness of 5 mm, and at a certain moment, the temperature deviation coefficient matrix shows that the proportion of the deviation in the high-temperature region reaches 60%, the system will automatically increase the cooling rate compensation parameter according to the rule base. Assuming the original cooling rate compensation parameter is 0, it may be adjusted to 5 (the specific value is determined according to the actual situation and preset rules) to accelerate the cooling speed.

[0090] For the case of low-temperature zone deviation, if the low-temperature zone deviation continuously exceeds 3 sampling periods, a stepped increase strategy for the heating power is triggered. This is because too low a temperature in the low-temperature zone will affect the annealing effect of the steel strip, resulting in the performance of the steel strip not meeting the expected standards. The stepped increase strategy means increasing a certain power value each time to gradually raise the temperature in the low-temperature zone. For example, if each sampling period is set to 10 seconds, and the low-temperature zone deviation exceeds the allowable range for 30 consecutive seconds, the system will start the stepped increase strategy for the heating power. The first power increase is 10 kW. After a period of time, if the low-temperature zone deviation still exists, the power is increased again. The power value increased each time can be adjusted according to the actual situation. For example, the second increase is 15 kW, and so on, until the temperature in the low-temperature zone returns to a reasonable range. At the same time, during the process of adjusting the heating power, the system will continuously monitor the change of the temperature deviation coefficient matrix and dynamically adjust the subsequent control strategy according to the new deviation situation to ensure that the annealing process can proceed stably and efficiently, and the performance of the steel strip reaches the best state.

[0091] Example 4:

[0092] The anomaly grading module is used in the whole system to classify the anomaly level of the current annealing stage, and its execution steps have clear calculation logic and judgment criteria.

[0093] According to the deviation coefficients of each heating zone in the temperature deviation coefficient matrix, calculate the regional anomaly index. The calculation formula is:

[0094]

[0095] Among them, R j is the anomaly index of the jth heating subzone, which comprehensively reflects the overall situation of the temperature deviation within this heating subzone. δ T,j,k is the temperature time-series deviation coefficient of the kth monitoring point in the jth heating subzone. These coefficients are calculated by the temperature deviation analysis module and reflect the deviation degree of the temperature of each monitoring point from the expected temperature. γ k is the kth weight factor of region j, which is set according to factors such as the position and importance of the monitoring point within the heating subzone. For example, for the monitoring points close to the center of the steel strip, since their temperatures have a greater impact on the overall performance of the steel strip, their weight factors may be set higher; while for the monitoring points at the edge position, the weight factors are relatively lower. M is the number of monitoring points within the region, and this number is determined according to the size of the heating subzone and the monitoring accuracy requirements. Generally speaking, the more the number of monitoring points, the more accurately the calculated regional anomaly index can reflect the temperature deviation situation within the heating subzone.

[0096] After calculating the regional anomaly index, the anomaly level is divided according to a preset threshold. If the regional anomaly index exceeds the preset threshold, the corresponding area is marked as a first-level anomaly; otherwise, it is marked as a second-level anomaly. The preset threshold is determined based on a large amount of historical production data and experimental results. For example, after multiple experiments and data analyses, it is determined that when the regional anomaly index is greater than 0.8, the temperature deviation in this area is relatively serious and will have a greater impact on the annealing quality of the steel strip. At this time, this area is marked as a first-level anomaly. Operators can take corresponding measures in a timely manner according to the anomaly level identification. For the first-level anomaly area, it may be necessary to immediately stop the annealing process and check and adjust the equipment; for the second-level anomaly area, the heating power or cooling rate can be appropriately adjusted to avoid the further deterioration of the abnormal situation and ensure that the annealing process can proceed smoothly and produce electrical steel strips that meet the quality requirements.

[0097] Example 5:

[0098] During the operation of the system, the historical data retrieval unit connected to the dynamic regulation module plays a key role. The core task of this unit is to screen out past cases from the huge historical annealing record database whose similarity to the current temperature deviation coefficient matrix is greater than 80%. The historical annealing record database stores a large amount of annealing data under different working conditions, which details various parameter changes during the annealing process and the final regulation results.

[0099] The historical data retrieval unit uses a specific similarity calculation algorithm for case retrieval. For example, using the similarity algorithm based on Euclidean distance, the temperature deviation coefficient matrix is regarded as a vector in a multi-dimensional space, and the Euclidean distance between the current matrix vector and the matrix vector in the historical record is calculated to measure the similarity. The Euclidean distance calculation formula is: where d represents the Euclidean distance between two vectors, x i and y i are the components of the two vectors in the i-th dimension respectively, and n is the dimension of the vector. In the temperature deviation coefficient matrix, n is the number of elements in the matrix. After calculating the Euclidean distance, the distance value is converted into a similarity value through a specific conversion formula. When the similarity is greater than 80%, it is determined that the historical case meets the screening conditions.

[0100] When the historical cases that meet the conditions are screened out, the historical data retrieval unit will extract the corresponding regulation parameter optimization schemes for these cases. These optimization schemes are effective regulation strategies that have been tested and verified multiple times in past actual production. For example, in a certain historical case, for a temperature deviation situation similar to the current one, the regulation measures of first reducing the heating power by 20% and simultaneously increasing the cooling rate by 15% were taken, which successfully restored the annealing process to normal and ensured the quality of the steel strip.

[0101] Next, the historical data backtracking unit performs weighted fusion on the extracted optimization solution and the output result of the fuzzy logic controller to generate the final control instruction. During the weighted fusion process, different weights are assigned to the optimization solution and the output result of the fuzzy logic controller according to the similarity degree between the current production environment and historical cases as well as actual production experience. Suppose after evaluation, it is considered that the current production environment is highly similar to a certain historical case. The weight of the historical optimization solution can be set to 0.7, and the weight of the output result of the fuzzy logic controller can be set to 0.3. Through weighted calculation, for example, for the heating power regulation parameter, if the heating power regulation parameter in the historical optimization solution is P1 and the heating power regulation parameter output by the fuzzy logic controller is P2, then the final heating power regulation parameter P = 0.7P1 + 0.3P2; similarly calculate the cooling rate compensation parameter. In this way, by fully combining historical experience with modern intelligent algorithms, the generated control instruction is made more scientific and reasonable, effectively improving the regulation accuracy and stability of the system for the annealing process.

[0102] Example 6:

[0103] The adaptive threshold update unit and the real-time feedback module connected to the anomaly grading module play an indispensable role in the stable operation of the system.

[0104] The adaptive threshold update unit regularly counts the distribution of temperature deviation coefficients in each heating zone within the most recent 24 hours. It first collects all the temperature deviation coefficient data of each heating zone within these 24 hours, and these data reflect the deviation degree between the actual temperature and the desired temperature of each heating zone at each moment. Then, data analysis methods are used, such as calculating statistical quantities such as the average value, median, and variance of the data, to deeply understand the distribution characteristics of the temperature deviation coefficients. If it is found that the variance of the temperature deviation coefficients increases, this means that the fluctuation range of the temperature deviation is expanding, and the stability of the annealing process has decreased. At this time, the adaptive threshold update unit will appropriately increase the threshold for anomaly level classification. For example, the original threshold for level 1 anomaly is 0.5. After analysis, it is found that the fluctuation of the temperature deviation coefficients increases, and the threshold is increased to 0.6. In this way, the annealing process can be monitored more strictly, and potential anomalies can be detected in a timely manner. Conversely, if the variance decreases, indicating that the annealing process tends to be stable, the threshold is appropriately reduced.

[0105] In addition, if no anomaly is triggered within 10 consecutive sampling periods, indicating that the current annealing process is relatively stable, in order to avoid the system being too sensitive and generating too many false alarms, the adaptive threshold update unit will reduce the threshold sensitivity by 5%. Suppose the current threshold for level 1 anomaly is 0.6. After reducing it by 5%, the new threshold becomes 0.6×(1 - 0.05) = 0.57. By dynamically adjusting the threshold in this way, the system can better adapt to different production conditions, improving the accuracy and reliability of anomaly monitoring.

[0106] The real-time feedback module is responsible for efficiently transmitting the regulation parameters and the anomaly level identifier to the annealing furnace control terminal and presenting the relevant information in an intuitive manner. First, it encapsulates the heating power regulation parameters generated by the dynamic regulation module, the cooling rate compensation parameters, and the anomaly level identifier output by the anomaly classification module in JSON format. The JSON format has the characteristics of being lightweight, easy to parse and transmit, and is very suitable for data interaction in industrial systems. The encapsulated data is transmitted through the industrial Ethernet, which has the characteristics of high speed and stability, and can ensure that the data arrives at the annealing furnace control terminal accurately and in a timely manner.

[0107] On the annealing furnace control terminal interface, the real-time feedback module visualizes the temperature deviation distribution and the anomaly level identifier of each heating zone in the form of a heat map. The heat map uses different colors to represent the magnitude of the temperature deviation. For example, red is used to represent the area with a larger temperature deviation, and green is used to represent the area with a smaller temperature deviation. The depth of the color further reflects the specific value of the deviation. At the same time, the anomaly level identifier is directly marked at the corresponding heating zone position, such as "Level 1 anomaly" or "Level 2 anomaly". By observing the heat map, the operator can clearly understand the temperature conditions and anomaly status of each heating zone of the entire annealing furnace, discover problems in a timely manner and take corresponding measures, thus effectively ensuring the smooth progress of the annealing process of the electrical steel strip and the product quality.

[0108] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0109] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring and control system for the annealing temperature of electrical steel strip, characterized in that, Including: A temperature data acquisition module, which is used to collect the temperature monitoring data and cooling rate monitoring data of each heating zone during the annealing process in real time, and receive the preset annealing temperature desired curve and cooling rate desired value; A temperature deviation analysis module, which calculates multi-dimensional deviations of the temperature monitoring data, cooling rate monitoring data, the annealing temperature desired curve, and the cooling rate desired value through a dynamic weighting algorithm to generate a temperature deviation coefficient matrix; A dynamic regulation module, which generates heating power regulation parameters and cooling rate compensation parameters based on the fuzzy logic control algorithm according to the temperature deviation coefficient matrix; An anomaly classification module, which is used to divide the anomaly level of the current annealing stage according to whether the deviation coefficients of each dimension in the temperature deviation coefficient matrix exceed the dynamic threshold, and output an anomaly level identifier; A real-time feedback module, which transmits the heating power regulation parameters, cooling rate compensation parameters, and anomaly level identifier to the annealing furnace control terminal; Among them, the execution steps of the temperature deviation analysis module include: Extracting the time series of the temperature monitoring data of each heating zone, performing point-by-point matching with the annealing temperature desired curve, and calculating the temperature time series deviation coefficient; Performing a sliding window comparison between the cooling rate monitoring data and the cooling rate desired value to generate a cooling rate fluctuation coefficient; Constructing a temperature deviation coefficient matrix containing weight factors according to the temperature time series deviation coefficient and the cooling rate fluctuation coefficient.

2. The system according to claim 1, wherein The execution steps of the dynamic regulation module further include: Inputting the temperature deviation coefficient matrix into a fuzzy logic controller, and performing fuzzy processing on the deviation interval through a preset membership function; Generating a fuzzy output of heating power regulation parameters and cooling rate compensation parameters based on the fuzzy rule base, and converting it into an accurate control instruction through a defuzzification algorithm.

3. The system according to claim 1, wherein The execution steps of the temperature data acquisition module include: Collecting the real-time temperature data of each heating zone through a distributed temperature sensor array and recording the time stamp; Obtaining the steel strip conveying speed through a laser velocimeter, and calculating the cooling rate monitoring value in combination with the thermal imaging data of the cooling zone; Retrieving the annealing temperature desired curve and cooling rate desired value matching the current steel strip model from the annealing process database; Adding the real-time temperature data and cooling rate monitoring value to the temperature monitoring data set, and synchronously storing the time stamp information.

4. The system according to claim 2, wherein The execution steps of the temperature deviation analysis module further include: Defining the calculation formula of the temperature time series deviation coefficient as: Among them, δ T is the temperature time series deviation coefficient, T 监测,i is the monitored temperature at the i-th time point, T 期望,i is the corresponding expected temperature, w i is the dynamic weight factor within the time window, and N is the number of sampling points; Defining the calculation formula of the cooling rate fluctuation coefficient as: Among them, δ C is the cooling rate fluctuation coefficient, C 监测 is the actually monitored cooling rate value, C 期望 is the preset expected value of the cooling rate, and α is the correction factor for the cooling rate sensitivity.

5. The system according to claim 2, wherein The execution steps of the dynamic regulation module further include: Dynamically adjusting the rule base of the fuzzy logic controller according to the steel strip thickness and material characteristics, including: If the proportion of the deviation in the high-temperature zone in the temperature deviation coefficient matrix exceeds 50%, then preferentially increase the cooling rate compensation parameter; If the deviation in the low-temperature zone continuously exceeds 3 sampling periods, then trigger a stepped increase strategy for the heating power.

6. The system according to claim 2, wherein The execution steps of the anomaly classification module include: Calculating the regional anomaly index according to the deviation coefficients of each heating zone in the temperature deviation coefficient matrix: Among them, R j is the anomaly index of the j-th heating zone, and δ T,j,k is the temperature time series deviation coefficient of the k-th monitoring point in the j-th heating zone, and γ k is the k-th weight factor of zone j, and M is the number of monitoring points in the zone; If the regional anomaly index exceeds the preset threshold, the corresponding region is marked as a first-level anomaly; otherwise, it is marked as a second-level anomaly.

7. The system according to claim 1, characterized in that The dynamic regulation module is also connected to a historical data backtracking unit, and the execution steps of the historical data backtracking unit include: Retrieving cases in the historical annealing records with a similarity greater than 80% to the current temperature deviation coefficient matrix, and extracting the corresponding regulation parameter optimization solutions; Performing weighted fusion on the optimization solutions and the output results of the fuzzy logic controller to generate the final regulation instructions.

8. The system according to claim 1, characterized in that, The anomaly grading module is also connected to an adaptive threshold updating unit, and its execution steps include: Statistical distribution of the temperature deviation coefficients of each heating zone within the most recent 24 hours, and dynamically adjusting the threshold range for anomaly level classification; If no anomaly is triggered within 10 consecutive sampling periods, the threshold sensitivity is reduced by 5%.

9. The system according to claim 1, wherein The execution steps of the real-time feedback module further include: Encapsulating the regulation parameters and anomaly level identifiers into a JSON format data packet and transmitting them to the annealing furnace control terminal through the industrial Ethernet; Visualizing the temperature deviation distribution and anomaly level identifiers of each heating zone in the form of a heat map on the control terminal interface.

10. An electronic device, characterized in that, Comprising: A memory for storing the control program of the system according to any one of claims 1-9; A processor for executing the control program to achieve real-time monitoring and regulation of the annealing temperature of the electrical steel strip.

Images