Furnace temperature control method, system, device, storage medium and program product

Abstract

The application provides a strip steel cold rolling annealing furnace temperature control method, system, electronic equipment, medium and program product. The method comprises the following steps: obtaining a first parameter and a second parameter for strip steel production; determining a target strip temperature value and a region temperature setting value of a plurality of furnace temperature control regions according to the first parameter; determining a predicted strip temperature value according to the region temperature setting value and the second parameter; repeating the above steps to obtain a plurality of predicted strip temperature values; comparing the plurality of predicted strip temperature values with the target strip temperature value, selecting an optimal predicted strip temperature value in the plurality of predicted strip temperature values, and the optimal predicted strip temperature value is a strip temperature value with the smallest deviation from the target strip temperature value and within a predetermined threshold; outputting a region temperature setting value corresponding to the optimal predicted strip temperature value; and performing negative feedback control on the region temperature setting value based on an actual strip temperature value.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a furnace temperature control method, system, device, storage medium, and computer program product. Background Technology

[0002] A continuous annealing furnace is a device used to perform heat treatment processes, raising or lowering the furnace temperature or the temperature of the metal strip according to production information and processes, in order to ensure the quality and properties of the produced materials.

[0003] In the process of producing steel in a cold-rolled continuous annealing furnace, operators need to frequently adjust production and control parameters according to changes in production conditions to ensure production quality and minimize production losses. Real-time adjustments place high demands on the operators' skill level, production experience, and concentration. Therefore, the production process and quality are closely related to the operator's technical level and current state, making it possible for unavoidable errors such as untimely operation and operational mistakes to occur during production, thus affecting production quality. Summary of the Invention

[0004] To address the aforementioned issues, embodiments of this application provide a furnace temperature control method, system, device, storage medium, and program product, which can accurately control temperature and improve production efficiency and quality.

[0005] This application discloses a furnace temperature control method for a cold-rolled annealing furnace for strip steel. The annealing furnace includes multiple furnace sections, and each furnace section includes multiple furnace temperature control zones. The method controls the furnace temperature of at least one of the furnace sections as follows:

[0006] When the weld seam of the front and rear strips is located in a designated area in front of the furnace section, the furnace temperature control command for one or more furnace temperature control areas in the furnace section is generated based on the first artificial intelligence model according to the strip production parameters.

[0007] When the weld is located between a designated position before the furnace section and the furnace section exit, furnace temperature control commands for one or more furnace temperature control zones within the furnace section are generated based on a second artificial intelligence model according to the strip steel production parameters; and

[0008] After the weld has passed through the furnace section outlet, a furnace temperature control command is generated based on the strip steel production parameters and the measured strip temperature value using a third artificial intelligence model for one or more furnace temperature control zones within the furnace section.

[0009] Optionally, the furnace temperature control method further includes:

[0010] Determine whether the current strip is a normal coil or a transitional coil based on the strip production parameters.

[0011] If the current strip is a normal coil, the first artificial intelligence model, the second artificial intelligence model and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the current strip and the next normal coil;

[0012] If the current strip is a transition coil, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the next normal coil.

[0013] Optionally, the first artificial intelligence model includes a first prediction model and a second prediction model.

[0014] The first prediction model predicts the regional temperature setpoints of the multiple furnace temperature control zones based on the strip steel production parameters.

[0015] The second prediction model predicts the strip temperature value based on the strip production parameters and the regional temperature setpoint.

[0016] Repeat the above steps to obtain multiple predicted temperature values;

[0017] The multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value among the multiple predicted temperature values ​​is selected. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold.

[0018] The output temperature setpoint of the region corresponding to the optimal predicted zone temperature is used as the furnace temperature control command.

[0019] Optionally, when the weld is in the designated area, the first artificial intelligence model determines, based on the strip steel production parameters, whether it is necessary to preheat or cool one or more furnace temperature control zones in the furnace section by a factor greater than or equal to a first magnitude, and outputs a corresponding furnace temperature control command.

[0020] Optionally, the second artificial intelligence model includes a third prediction model and a fourth prediction model.

[0021] The third prediction model predicts the regional temperature setpoints of the multiple furnace temperature control zones based on the strip steel production parameters.

[0022] The fourth prediction model predicts the strip temperature value based on the strip production parameters and the regional temperature setpoint.

[0023] Repeat the above steps to obtain multiple predicted temperature values;

[0024] The multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value among the multiple predicted temperature values ​​is selected. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold.

[0025] The output temperature setpoint of the region corresponding to the optimal predicted zone temperature is used as the furnace temperature control command.

[0026] Optionally, the third artificial intelligence model includes a fifth prediction model and a sixth prediction model.

[0027] The fifth prediction model predicts the regional temperature setpoints of the multiple furnace temperature control zones based on the strip steel production parameters and the measured strip temperature values.

[0028] The sixth prediction model predicts the strip temperature value based on the strip production parameters, the measured strip temperature value, and the regional temperature setpoint.

[0029] Repeat the above steps to obtain multiple predicted temperature values;

[0030] The multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value among the multiple predicted temperature values ​​is selected. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold.

[0031] The output temperature setpoint of the region corresponding to the optimal predicted zone temperature is used as the furnace temperature control command.

[0032] Optionally, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model may also perform adaptive compensation when one or more of the furnace temperature control zones in the furnace section are unable to participate in control.

[0033] Optionally, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model may also provide adaptive compensation for situations where one or more of the furnace temperature control zones in the furnace section cannot continue to heat up or cool down.

[0034] Optionally, the strip production parameters include one or more of the following: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature of each furnace section, outlet strip temperature, and zone temperature of the multiple furnace temperature control zones.

[0035] This application also discloses a furnace temperature control system for a cold-rolled annealing furnace for strip steel. The annealing furnace includes multiple furnace sections, and each of the multiple furnace sections includes multiple furnace temperature control zones. The system is characterized by comprising the following modules for furnace temperature control of at least one of the furnace sections:

[0036] The first furnace temperature control module generates furnace temperature control commands for one or more furnace temperature control areas in the furnace section based on the first artificial intelligence model according to the strip production parameters when the weld seam of the front and rear strips is located in a designated area in front of the furnace section.

[0037] The second furnace temperature control module, when the weld is located between a designated position before the furnace section and the furnace section exit, generates furnace temperature control commands for one or more furnace temperature control zones within the furnace section based on the strip steel production parameters and a second artificial intelligence model; and

[0038] The third furnace temperature control module, after the weld has passed through the furnace section outlet, generates furnace temperature control commands for one or more furnace temperature control zones within the furnace section based on the strip steel production parameters and the measured strip temperature value using a third artificial intelligence model.

[0039] Optionally, the furnace temperature control system further includes:

[0040] Determine whether the current strip is a normal coil or a transitional coil based on the strip production parameters.

[0041] If the current strip is a normal coil, the first artificial intelligence model, the second artificial intelligence model and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the current strip and the next normal coil;

[0042] If the current strip is a transition coil, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the next normal coil.

[0043] Optionally, the first artificial intelligence model includes a first prediction model and a second prediction model. When the first artificial intelligence model determines that a heating or cooling rate greater than or equal to a first magnitude is required,

[0044] The first prediction model predicts the regional temperature setpoints of the multiple furnace temperature control zones based on the strip steel production parameters.

[0045] The second prediction model predicts the strip temperature value based on the strip production parameters and the regional temperature setpoint.

[0046] Repeat the above steps to obtain multiple predicted temperature values;

[0047] The multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value among the multiple predicted temperature values ​​is selected. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold.

[0048] The output temperature setpoint of the region corresponding to the optimal predicted zone temperature is used as the furnace temperature control command.

[0049] Optionally, when the weld is in the designated area, the first artificial intelligence model determines, based on the strip steel production parameters, whether it is necessary to preheat or cool one or more furnace temperature control zones in the furnace section by a factor greater than or equal to a first magnitude, and outputs a corresponding furnace temperature control command.

[0050] Optionally, the second artificial intelligence model includes a third prediction model and a fourth prediction model.

[0051] The third prediction model predicts the regional temperature setpoints of the multiple furnace temperature control zones based on the strip steel production parameters.

[0052] The fourth prediction model predicts the strip temperature value based on the strip production parameters and the regional temperature setpoint.

[0053] Repeat the above steps to obtain multiple predicted temperature values;

[0054] The multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value among the multiple predicted temperature values ​​is selected. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold.

[0055] The output temperature setpoint of the region corresponding to the optimal predicted zone temperature is used as the furnace temperature control command.

[0056] Optionally, the third artificial intelligence model includes a fifth prediction model and a sixth prediction model.

[0057] The fifth prediction model predicts the regional temperature setpoints of the multiple furnace temperature control zones based on the strip steel production parameters and the measured strip temperature values.

[0058] The sixth prediction model predicts the strip temperature value based on the strip production parameters, the measured strip temperature value, and the regional temperature setpoint.

[0059] Repeat the above steps to obtain multiple predicted temperature values;

[0060] The multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value among the multiple predicted temperature values ​​is selected. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold.

[0061] The output temperature setpoint of the region corresponding to the optimal predicted zone temperature is used as the furnace temperature control command.

[0062] Optionally, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model may also perform adaptive compensation when one or more of the furnace temperature control zones in the furnace section are unable to participate in control.

[0063] Optionally, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model may also provide adaptive compensation for situations where one or more of the furnace temperature control zones in the furnace section cannot continue to heat up or cool down.

[0064] Optionally, the strip production parameters include one or more of the following: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature of each furnace section, outlet strip temperature, and zone temperature of the multiple furnace temperature control zones.

[0065] This application also discloses an electronic device, the device including a memory storing computer-executable instructions and a processor; when the instructions are executed by the processor, the device performs any of the aforementioned methods.

[0066] This application also discloses a computer-readable medium storing one or more programs that can be executed by one or more processors to implement any of the aforementioned methods.

[0067] This application also discloses a computer program product, including a computer program that, when executed by a processor, implements any of the aforementioned methods.

[0068] Compared with the prior art, the embodiments of this application have the following advantages:

[0069] The AI ​​system for cold-rolled annealing furnaces employs neural network-based artificial intelligence methods to model the annealing furnace. Combined with the architecture and experience of traditional closed-loop control strategies, it predicts and controls the temperature commands in the continuous annealing furnace zone, ensuring that the strip steel meets production quality requirements in both steady-state (i.e., only one coil of strip steel is in the furnace or the strip steel before and after the weld is the same) and transitional (i.e., the strip steel before and after the weld is different) production processes. Simultaneously, the AI ​​system can pre-heat or cool the strip steel based on production conditions, effectively mitigating the risk of untimely heating or cooling due to large variations in specifications and other parameters during production, and effectively avoiding risks such as strip breakage within the furnace. The AI ​​system can store strip steel production and process information in real time, analyze it, and perform self-learning to automatically improve the system.

[0070] The furnace temperature control system of this strip cold rolling annealing furnace has been successfully applied to on-site control. Under normal steady-state production conditions, the strip temperature can generally be directly controlled to the target temperature, and the absolute value of the maximum error does not exceed 5℃. When there is a non-steady-state production situation with strip switching, the furnace temperature control system of the strip cold rolling annealing furnace can control the strip temperature to the target temperature as quickly as possible within the allowable time range through zone temperature control, thus ensuring the production quality of the strip. Attached Figure Description

[0071] Figure 1 This is a furnace temperature control scenario diagram of a furnace temperature control system for a cold-rolled annealing furnace for strip steel according to an embodiment of the present invention.

[0072] Figure 2 This is a flowchart of a furnace temperature control method for a cold-rolled annealing furnace for strip steel according to an embodiment of the present invention;

[0073] Figure 3 This is a flowchart of the furnace temperature control system for a cold-rolled annealing furnace for strip steel according to an embodiment of the present invention.

[0074] Figure 4 This is a block diagram of the furnace temperature control system of a cold-rolled annealing furnace for strip steel according to an embodiment of the present invention;

[0075] Figure 5 This is an interactive functional structure diagram of the furnace temperature control system of the cold rolling annealing furnace for strip steel according to an embodiment of the present invention;

[0076] Figure 6 This is a structural diagram of the annealing control function of the furnace temperature control system of the cold rolling annealing furnace for strip steel according to an embodiment of the present invention;

[0077] Figure 7 This is a model update function structure diagram of the furnace temperature control system of the cold rolling annealing furnace for strip steel according to an embodiment of the present invention;

[0078] Figure 8 This is a block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0079] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0080] The furnace temperature control system of this strip cold rolling annealing furnace is implemented through an AI system, and therefore will be referred to as the cold rolling annealing furnace AI system in the following text. In this article, furnace temperature refers to the temperature of the controlled area.

[0081] In actual production, based on the function of the strip steel, the strip steel in the furnace section can be divided into normal coils and transition coils. Normal coils are the actual production material needed, while transition coils do not participate in production but serve as buffer coils to prevent insufficient switching time between normal coils, allowing for more precise temperature control of the current strip steel. Therefore, before each furnace temperature control, it is necessary to assess the current strip steel based on its production parameters to determine the appropriate furnace temperature control command for the production process.

[0082] If the current strip is a normal coil, the cold rolling annealing furnace AI model determines the furnace temperature control command based on the parameters of the current normal coil and the next normal coil; if the current strip is a transition coil, the cold rolling annealing furnace AI model determines the furnace temperature control command based on the parameters of the next normal coil. Strip production parameters include one or more of the following: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature (i.e., strip temperature), outlet strip temperature, and zone temperatures of multiple furnace temperature control areas.

[0083] The furnace temperature control will be described in detail below. Since the transition coils are not involved in actual production, for ease of explanation, the normal coils will be referred to as strip steel in the following text, and the transition coils will not be discussed.

[0084] like Figure 1 As shown, the AI ​​system for the cold-rolled annealing furnace divides the control cycle of the entire furnace section into three sub-regions based on the real-time position of the weld seam between the front and rear strips in the production line. These sub-regions correspond to the safety protection region, the dynamic predictive control region, and the steady-state feedback control region, respectively. The following section combines... Figure 2 The furnace temperature control method according to this application will be described in detail below. In each sub-region, the cold rolling annealing furnace AI system uses an artificial intelligence model for temperature control.

[0085] In step 201, when the weld seam of the front and rear strips is located in a designated area in front of the furnace section, furnace temperature control instructions for one or more furnace temperature control areas in the furnace section are generated based on the first artificial intelligence model according to the strip production parameters.

[0086] Step 201 is performed when the weld is located in the safety protection zone. The location of the safety protection zone can be determined according to the actual production situation and commissioning, for example, it can be the area 100 meters to 30 meters in front of the furnace section.

[0087] In actual production, parameters such as strip type, grade, specifications, production speed, and target strip temperature can change significantly, leading to a sharp rise or fall in strip temperature. In such cases, if the furnace temperature cannot be controlled in time to adjust the strip temperature, the strip quality will be affected by these drastic temperature changes. To avoid these risks, when the strip after the weld enters the safety protection zone, the cold rolling annealing furnace AI system uses parameters such as strip type, grade, specifications, production speed, and target strip temperature to determine whether to generate a furnace temperature control command to pre-heat or cool the temperature control area of ​​the furnace section, preventing drastic temperature changes.

[0088] For example, if the AI ​​system determines, based on strip steel parameters, that the target strip temperature for the preceding strip is 720℃ and the target strip temperature for the following strip is 740℃, because the temperature difference is greater than or equal to a threshold (which can be any reasonable temperature value based on actual production needs, such as 20℃, 25℃, or 30℃), the temperature control zone of the furnace section will be preheated to a temperature greater than or equal to this threshold to prevent excessively drastic temperature changes when the following strip enters the temperature control zone. Conversely, if the target strip temperature for the preceding strip is 740℃ and the target strip temperature for the following strip is 720℃, the temperature control zone of the furnace section will be preheated. In other words, the safety protection zone is a buffer zone where various parameters are used to determine whether temperature control needs to be implemented in advance in subsequent areas to prevent rapid temperature changes. It is understandable that the AI ​​system can also determine whether to generate furnace temperature control commands to preheat or cool the temperature control zone of the furnace section based on changes in one or more of the following strip production speeds, widths, grades, etc.

[0089] In step 202, when the weld is located between a designated position in front of the furnace section and the furnace section exit, furnace temperature control instructions for one or more furnace temperature control zones within the furnace section are generated based on the strip steel production parameters and the second artificial intelligence model.

[0090] Step 202 is performed within the dynamic prediction control zone, which extends from the weld seam of the preceding and following strips through the safety protection zone to the weld seam reaching the outlet of the furnace section. For example... Figure 1As shown, the length of the dynamic predictive control zone is greater than or equal to the length of the controlled furnace segment. Since temperature sensors are located at the outlet of each furnace segment, and the furnace segment outlet is at the end of this dynamic predictive control zone, the actual temperature of the subsequent strip cannot be measured within this zone. Therefore, within this dynamic predictive control zone, the cold-rolled annealing furnace AI system uses an artificial intelligence model to predict the furnace temperature and controls the actual furnace temperature based on the predicted temperature. This ensures that the furnace temperature begins to change while the weld seam is still inside the furnace, accelerating the temperature change during the transition process and reducing the length of strip affected by the transition process.

[0091] Specifically, temperature control in the safety protection zone and the dynamic predictive control zone is achieved through the following method. First, the predictive model outputs a set of predicted furnace temperatures (furnace temperature control values ​​1 to n) based on the strip parameters before and after the furnace (e.g., strip type, strip grade, strip specifications, production speed, inlet strip temperature of each furnace section, and furnace temperature of each control zone). This set of predicted furnace temperatures represents the predicted temperatures of multiple furnace temperature control sub-regions within the furnace section. Then, this set of predicted furnace temperatures is input into another predictive model, which outputs the predicted strip temperature value of the strip after passing through the control zone under this set of predicted furnace temperatures.

[0092] The above steps are repeated within one calculation cycle to obtain multiple predicted zone temperatures. These predicted zone temperatures are then compared one by one with the target zone temperature to obtain the predicted zone temperature with the smallest deviation. Finally, the predicted furnace temperatures corresponding to the predicted zone temperature with the smallest deviation are output as the optimal furnace temperature control command to control the temperature of each control sub-region within the furnace section.

[0093] In this embodiment, the prediction model used to output the predicted furnace temperature and the prediction model used to output the predicted zone temperature are different models. However, those skilled in the art should understand that other prediction model schemes or variations can also be applied to this invention.

[0094] In step 203, after the weld has passed through the furnace section exit, based on the strip steel production parameters and the measured strip temperature value, furnace temperature control instructions for one or more furnace temperature control zones within the furnace section are generated based on the third artificial intelligence model.

[0095] Step 203 is performed in the steady-state feedback control region. This means that after passing through the dynamic predictive control region, the weld seams of the preceding and following strips have reached the steady-state feedback control region via the furnace exit. The actual strip temperature can be detected by a temperature sensor installed at the furnace exit. Since the actual strip temperature has been obtained, a steady-state feedback control system can be constructed using this temperature. In actual production, after obtaining the actual strip temperature through the temperature sensor, the above-mentioned temperature control method is used. When predicting the furnace temperature, the actual strip temperature parameters are combined to obtain the predicted furnace temperature corresponding to the optimal predicted strip temperature value. Feedback control is then performed by comparing the actual strip temperature with the target strip temperature and comparing the optimal predicted strip temperature with the target strip temperature to further adjust the furnace temperature control quantity and obtain a more precise furnace temperature control command.

[0096] In this embodiment, the same or different artificial intelligence models from the AI ​​system are used for temperature control in the safety protection zone, dynamic predictive control zone, and steady-state feedback control zone, respectively. This artificial intelligence model employs neural network technology and can be implemented using, for example, convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM), and other neural networks. Based on the above description, those skilled in the art will understand that these artificial intelligence models may differ, but are essentially the same; they can be considered as one model or multiple models. Therefore, other artificial intelligence model schemes or variations can also be applied to this invention.

[0097] Now, taking the use of the first artificial intelligence model for furnace temperature control in the safety protection zone as an example, refer to... Figure 3 The furnace temperature control process is illustrated in the furnace temperature control flowchart 300.

[0098] In step 301, the production parameters of the strip are obtained, and the target strip temperature is determined based on the parameters. In one or more embodiments, the target strip temperature can be determined, for example, by using a lookup table. Depending on the actual production conditions, the parameters include one or more of the following: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature of each furnace section, outlet strip temperature, and zone temperatures of multiple furnace temperature control areas.

[0099] Those skilled in the art will understand that the number of parameters in actual production can be enormous, ranging from hundreds to thousands. Therefore, the parameters listed are merely examples, and more parameters from the production process may be included depending on the actual production needs.

[0100] In step 302, the regional temperature setpoints for multiple furnace temperature control sub-regions are determined based on parameters. This determination process is performed using a first prediction model of a first artificial intelligence model.

[0101] In step 303, the predicted zone temperature value is determined based on the zone temperature setpoint and parameters. This determination process is performed using a second prediction model based on the first artificial intelligence model.

[0102] Those skilled in the art will understand that the first prediction model and the second prediction model can be the same or different models.

[0103] In step 304, steps 302 and 303 are repeated to obtain multiple predicted zone temperature values. Those skilled in the art will understand that, since the parameter values ​​are constantly changing in real time with the actual production process (for example, the zone temperatures of multiple furnace temperature control areas can have different combinations), multiple different values ​​can be obtained through repeated calculations.

[0104] In step 305, multiple predicted temperature values ​​are compared with the target temperature value, and the optimal predicted temperature value is selected from the multiple predicted temperature values. The optimal predicted temperature value is the temperature value with the smallest deviation from the target temperature value and within a predetermined threshold. Obviously, regardless of the method, the predicted temperature value with the smallest deviation from the target temperature value can be determined from the multiple predicted temperature values. However, if the deviation of this predicted temperature value is still too large to meet the needs of actual production, all of the multiple predicted temperature values ​​in this group are discarded, and the evaluation continues in the next calculation cycle.

[0105] In step 306, the regional temperature setpoint corresponding to the optimal predicted zone temperature value is output.

[0106] It is understandable that the second artificial intelligence model used in the dynamic predictive control region includes the third and fourth predictive models, and the third artificial intelligence model used in the steady-state feedback control region includes the fifth and sixth predictive models. Their principles are the same as those of the first artificial intelligence model, the first predictive model, and the second predictive model mentioned above. In addition, the actual temperature value measured by the temperature sensor is used to control the temperature setpoint of the region in the steady-state feedback control region. The principle of the furnace temperature control process in the three regions is also the same, so it will not be elaborated further.

[0107] Now for reference Figure 4 , Figure 4 A schematic diagram of the cold rolling annealing furnace AI system 400 of this application is shown. System 400 includes the following modules:

[0108] The first furnace temperature control module 401 is configured to generate furnace temperature control instructions for one or more furnace temperature control areas in the furnace section based on the first artificial intelligence model, according to the strip production parameters, when the weld seam of the front and rear strips is located in a first designated area in front of the furnace section.

[0109] The second furnace temperature control module 402 is configured to, when the weld is located between a designated position before the furnace section and the furnace section exit, generate furnace temperature control commands for one or more furnace temperature control zones within the furnace section based on strip steel production parameters and a second artificial intelligence model; and

[0110] The third furnace temperature control module 403 is configured to generate furnace temperature control commands for one or more furnace temperature control zones within the furnace section based on the strip steel production parameters and the measured strip temperature value, after the weld has passed through the furnace section exit.

[0111] This embodiment is an implementation corresponding to the method described above, and the relevant technical details mentioned in the method remain valid in this embodiment. To avoid repetition, they will not be repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the method described above.

[0112] It is understandable that the first, second, and third artificial intelligence models are only used to indicate the corresponding artificial intelligence models used in different furnace temperature control modules. However, the principles of these artificial intelligence models are essentially the same. Therefore, these artificial intelligence models can be the same artificial intelligence model or independent and different artificial intelligence models.

[0113] The above description explains the core function of the present invention: furnace temperature control. The other functions of the AI ​​system for the cold rolling annealing furnace will be described below.

[0114] The AI ​​system for cold rolling annealing furnaces mainly includes three functions: interactive functions, annealing control functions, and model update functions. Each main function contains several sub-functional modules, which together fulfill the complete functional requirements.

[0115] Now refer to Figure 5 The diagram shows the interactive sub-functional structure of the AI ​​system for cold rolling annealing furnace.

[0116] The interactive function is primarily responsible for communication between the cold rolling annealing furnace AI system and external systems. It exchanges data and performs corresponding functions according to the communication protocol. The cold rolling annealing furnace AI system employs a TCP / IP multi-threaded high-concurrency server architecture to receive input data from the artificial intelligence model and send the model's output data to external systems. The interactive function includes sub-functions such as heartbeat connection, data communication, and parameter updates.

[0117] First, the heartbeat connection sub-function will be explained. The cold rolling annealing furnace AI system acts as the communication client, and the external system acts as the communication server. The cold rolling annealing furnace AI system periodically sends specified information to the external system, and the external system simultaneously replies with the specified information. If the external system does not receive the specified information sent by the cold rolling annealing furnace AI system within a set time threshold, or if the cold rolling annealing furnace AI system does not receive a response from the external system within a set time threshold after sending the specified information, communication is considered to be disconnected. Then, the cold rolling annealing furnace AI system automatically and periodically initiates connection requests to the target IP of the external system until communication between the cold rolling annealing furnace AI system and the external system is restored.

[0118] The data communication sub-function is then described. Data packets transmitted from external systems that meet communication protocol requirements are processed through unpacking, parsing, and judgment to transform the data packets into corresponding data units, which are then sent to the cold rolling annealing furnace AI system as input data for the model. Simultaneously, the cold rolling annealing furnace AI system packages the control command data required by the external system according to the communication protocol and sends it to the external system as output data for the model. Input data mainly includes one or more of the following production parameters: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature of each furnace section, outlet strip temperature, and zone temperatures of multiple furnace temperature control areas. Output data mainly consists of the setpoints for zone temperatures and strip temperatures.

[0119] Finally, the parameter update sub-function is explained. After receiving communication data, the cold rolling annealing furnace AI system parses the parameter file and executes parameter update commands to achieve online parameter updates, storing the updated parameters in the corresponding files and database according to the specified format. The new parameters will be automatically applied to the cold rolling annealing furnace AI system in the next calculation cycle, without the need for manual updates or recompilation, which is beneficial for on-site debugging and system maintenance.

[0120] The annealing control function will now be described in general. The main sub-functions of the annealing control function include: strip condition judgment, error prediction, furnace temperature control quantity generation, furnace zone switching adaptive function, and control saturation adaptive function.

[0121] Now refer to Figure 6 The diagram shows the annealing control function structure of the AI ​​system for cold rolling annealing furnace.

[0122] First, the strip condition judgment sub-function is explained. Based on parameters such as the weld position of the front and rear strips, strip type, strip grade, strip specifications, and changes in strip speed in the production line, the cold rolling annealing furnace AI system determines in real time whether the front and rear strips in the current production are in a steady state or a transitional state, and performs subsequent control operations according to the production status.

[0123] Next, the error prediction sub-function is explained. This error prediction sub-function is based on Kalman filtering technology. During model training, the AI ​​system for the cold rolling annealing furnace monitors whether the training results are within the prediction error, thereby improving the prediction accuracy of the machine learning model.

[0124] Next, the sub-function for generating furnace temperature control parameters will be explained. The cold rolling annealing furnace AI system adopts a decoupled independent fitting method to fit corresponding artificial intelligence models for each section of the continuous annealing furnace, and uses these artificial intelligence models as tools for generating furnace temperature commands. After receiving relevant parameters of the cold rolling continuous annealing furnace from the external system, the cold rolling annealing furnace AI system calls the furnace temperature command generation tools of each section to generate furnace temperature commands that meet the current production requirements, and uses these furnace temperature commands to achieve automatic calculation and automatic control of the furnace temperature of the strip steel in each control area.

[0125] Finally, the adaptive control sub-functions are explained. These sub-functions include furnace zone switching adaptation and control saturation adaptation.

[0126] In this paper, "furnace zone switching" refers to the manual control by on-site operators during the production process of a cold rolling continuous annealing furnace. This involves shutting down temperature control components (such as burners) in one or more control zones based on actual production conditions. This disruption of temperature control in those zones affects the entire production process and ultimately, the final product quality. Therefore, to avoid the impact of furnace zone switching on production quality, this cold rolling annealing furnace AI system can adaptively adjust the opening and closing of control zones in each furnace section. By adjusting other control zones, it adaptively compensates for the control quantity changes caused by the switching of these zones, ensuring that the overall control performance of each furnace section meets production requirements.

[0127] Meanwhile, in this paper, control saturation refers to a situation where a local area within the control zone experiences excessively high or low heat loads, preventing that control zone from continuing to heat up or cool down. Consequently, the strip cannot reach the target strip temperature (i.e., strip temperature) in the corresponding furnace section, thus affecting production quality. Therefore, to avoid the impact of control saturation, this cold rolling annealing furnace AI system can adaptively adjust based on the control saturation state of the corresponding furnace section's control area. By adjusting other control areas, it adaptively compensates for changes in control quantities caused by the switching on and off of that control area, ensuring that the overall control performance of each furnace section meets production requirements.

[0128] Model update is a crucial function of the AI ​​system for cold rolling annealing furnaces. Updating the AI ​​model improves the precision of AI system control, which in turn enhances production quality. The model update function primarily includes two sub-functions: dataset update and model self-learning update.

[0129] Now refer to Figure 7 The diagram shows the model update function structure of the AI ​​system for the cold rolling annealing furnace.

[0130] First, the dataset update process is explained. After receiving input data from an external system, the AI ​​system for the cold rolling annealing furnace analyzes and judges the reasonableness of the input data based on the actual production status of the current cold rolling continuous annealing furnace, i.e., whether the input data conforms to the current actual production status. Then, the AI ​​system stores the input data deemed reasonable in a specified data format into a dataset file, which is used for model self-learning updates.

[0131] Next, the self-learning update of the model is explained. During the set update cycle, the AI ​​system of the cold rolling annealing furnace uses the updated dataset to retrain the model and judges the accuracy of the trained model. If the accuracy meets the requirements, the updated model replaces the original model.

[0132] Furthermore, the AI ​​system for the cold rolling annealing furnace adopts a multi-task, multi-threaded architecture. A thread pool is used to construct task threads for different tasks, and threads communicate via sockets for instructions and a global static stack for data. The AI ​​system acts as a client, exchanging data with external systems using TCP / IP connections. The communication IP address and port number can be changed by modifying the parameters in the parameter file.

[0133] Finally, to maintain the control accuracy of the cold rolling annealing furnace AI system, multiple debugging sessions are required. Firstly, based on the structural parameters of the continuous cold rolling annealing furnace used in production, corresponding parameters in the AI ​​system are modified, such as the number of control zones, the size of the control zones, and the location of the pyrometer. Then, the AI ​​system is deployed on a server and offline debugging is conducted. After offline debugging, when the AI ​​system is actually applied in the production process, the data generated on the production line is acquired by the AI ​​system and used to form a training dataset for training the artificial intelligence model. The training cycle can be modified synchronously according to actual production needs and conditions. Secondly, after fitting the artificial intelligence model, the AI ​​system updates the corresponding parameters of the model (such as the furnace temperature control quantity set, saturation threshold, etc.) to ensure control accuracy.

[0134] Now for reference Figure 8The diagram shown is a block diagram of an electronic device 800 according to an embodiment of the present application. The device 800 may include one or more processors 802, system control logic 808 connected to at least one of the processors 802, system memory 804 connected to the system control logic 808, non-volatile memory (NVM) 806 connected to the system control logic 808, and network interface 810 connected to the system control logic 808.

[0135] Processor 802 may include one or more single-core or multi-core processors. Processor 802 may include any combination of general-purpose processors and special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In embodiments herein, processor 802 may be configured to perform the AI-controlled furnace temperature method of this embodiment.

[0136] In some embodiments, system control logic 808 may include any suitable interface controller to provide any suitable interface to at least one of the processors 802 and / or any suitable device or component communicating with system control logic 808.

[0137] In some embodiments, system control logic 808 may include one or more memory controllers to provide an interface to system memory 804. System memory 804 may be used to load and store data and / or instructions. In some embodiments, system memory 804 of device 800 may include any suitable volatile memory, such as suitable dynamic random access memory (DRAM).

[0138] NVM / memory 806 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, NVM / memory 806 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device, such as at least one of HDD (Hard Disk Drive), CD (Compact Disc) drive, and DVD (Digital Versatile Disc) drive.

[0139] NVM / Memory 806 may include a portion of the storage resources mounted on the device 800, or it may be accessible by the device but is not necessarily part of the device. For example, NVM / Memory 806 may be accessed over a network via network interface 810.

[0140] Specifically, system memory 804 and NVM / memory 806 may each include a temporary copy and a permanent copy of instruction 820. Instruction 820 may include instructions that, when executed by at least one of processors 802, cause device 800 to implement the furnace temperature control method of this embodiment. In some embodiments, instruction 820, hardware, firmware, and / or its software components may additionally / alternatively reside in system control logic 808, network interface 810, and / or processor 802.

[0141] In some embodiments, network interface 810 may be integrated into other components of device 800. For example, network interface 810 may be integrated into at least one of processor 802, system memory 804, NVM / memory 806, and firmware device (not shown) with instructions that, when at least one of processor 802 executes the instructions, device 800 implements the furnace temperature control method of this embodiment. Network interface 810 may further include any suitable hardware and / or firmware to provide a multiple-input multiple-output radio interface.

[0142] In one embodiment, at least one of the processors 802 may be packaged together with the logic of one or more controllers for system control logic 808 to form a system package (SiP). In another embodiment, at least one of the processors 802 may be integrated on the same die with the logic of one or more controllers for system control logic 808 to form a system on chip (SoC).

[0143] Device 800 may further include: input / output (I / O) device 812. I / O device 812 may include a user interface that enables a user to interact with device 800; the design of the peripheral component interface enables peripheral components to also interact with device 800.

[0144] In some embodiments, the user interface may include, but is not limited to, a display (e.g., a liquid crystal display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and / or a video camera), a flashlight (e.g., a light-emitting diode flash), and a keyboard.

[0145] In some embodiments, the peripheral component interface may include, but is not limited to, a non-volatile memory port, an audio jack, and a power interface.

[0146] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 800. In other embodiments of this application, the electronic device 800 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0147] Program code can be applied to input instructions to perform the functions described herein and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application-specific integrated circuit (ASIC), or a microprocessor.

[0148] The program code can be implemented using a high-level procedural language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used when needed. In fact, the mechanisms described in this paper are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0149] One or more aspects of at least one embodiment can be implemented by representational instructions stored on a computer-readable storage medium, the instructions representing various logics in a processor, which, when read by a machine, cause the machine to create logic for performing the techniques described herein. These representations, referred to as “IP cores,” can be stored on a tangible computer-readable storage medium and provided to multiple customers or production facilities for loading into manufacturing machines that actually manufacture the logic or processor.

[0150] One embodiment of this application discloses a computer-readable medium storing one or more programs executable by one or more processors to implement the methods of this application.

[0151] One embodiment of this application discloses a computer program product, including a computer program that, when executed by a processor, implements the method of this application.

[0152] The specific embodiments described above illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Although the description of this application is presented in conjunction with preferred embodiments, this does not mean that the features of this invention are limited to these embodiments. Furthermore, to avoid confusion or obscuring the focus of this application, some specific details will be omitted in the description. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0153] Furthermore, the various operations will be described as multiple discrete operations in a manner most conducive to understanding the illustrative embodiments; however, the order of description should not be construed as implying that these operations must depend on the order. In particular, these operations do not need to be performed in the order presented.

[0154] Unless the context otherwise requires, the terms “contains,” “has,” and “includes” are synonyms.

[0155] As used herein, the terms “module” or “unit” may refer to, be, or include: application-specific integrated circuits (ASICs), electronic circuits, (shared, dedicated, or group) processors and / or memories that execute one or more software or firmware programs, combinational logic circuits, and / or other suitable components that provide the described functionality.

[0156] In the accompanying drawings, certain structural or methodological features are shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. In some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Furthermore, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0157] It should be understood that although terms such as "first," "second," etc., may be used herein to describe various units or data, these units or data should not be limited by these terms. These terms are used merely to distinguish one feature from another. For example, without departing from the scope of the exemplary embodiments, a first feature may be referred to as a second feature, and similarly, a second feature may be referred to as a first feature.

[0158] It should be noted that in this specification, similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0159] Although the invention has been illustrated and described with reference to certain preferred embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.

Claims

1. A method for controlling the furnace temperature of a cold-rolled annealing furnace for strip steel, wherein the annealing furnace comprises multiple furnace sections, and each of the multiple furnace sections comprises multiple furnace temperature control zones, characterized in that, The method performs the following furnace temperature control on at least one of the furnace sections: When the weld seam of the preceding and following strip steel is located in a designated area before the furnace section, based on the strip steel production parameters, a furnace temperature control command for one or more furnace temperature control areas in the furnace section is generated using a first artificial intelligence model. The first artificial intelligence model includes a first prediction model and a second prediction model. The first prediction model predicts the area temperature setpoints for the multiple furnace temperature control areas based on the strip steel production parameters. The second prediction model predicts the strip temperature value based on the strip steel production parameters and the area temperature setpoints. The above steps are repeated to obtain multiple predicted strip temperature values. These multiple predicted strip temperature values ​​are compared with a target strip temperature value, and the optimal predicted strip temperature value is selected. The optimal predicted strip temperature value is the strip temperature value with the smallest deviation from the target strip temperature value and within a predetermined threshold. The area temperature setpoint corresponding to the optimal predicted strip temperature value is output as the furnace temperature control command. When the weld seam is in the designated area, the first artificial intelligence model determines, based on the strip steel production parameters, whether it is necessary to preheat or cool one or more furnace temperature control areas in the furnace section by a factor greater than or equal to a first amplitude, and outputs the corresponding furnace temperature control command. When the weld is located between a designated position before the furnace section and the furnace section exit, based on the strip steel production parameters, a furnace temperature control command for one or more furnace temperature control zones within the furnace section is generated using a second artificial intelligence model. The second artificial intelligence model includes a third prediction model and a fourth prediction model. The third prediction model predicts the zone temperature setpoints for the multiple furnace temperature control zones based on the strip steel production parameters. The fourth prediction model predicts a zone temperature value based on the strip steel production parameters and the zone temperature setpoints. The above steps are repeated to obtain multiple predicted zone temperature values. These multiple predicted zone temperature values ​​are compared with a target zone temperature value, and the optimal predicted zone temperature value is selected from the multiple predicted zone temperature values. The optimal predicted zone temperature value is the zone temperature value with the smallest deviation from the target zone temperature value and within a predetermined threshold. The zone temperature setpoint corresponding to the optimal predicted zone temperature value is output as the furnace temperature control command. After the weld has passed through the furnace section exit, based on the strip steel production parameters and the measured strip temperature value, a furnace temperature control command for one or more furnace temperature control zones within the furnace section is generated using a third artificial intelligence model. The third artificial intelligence model includes a fifth prediction model and a sixth prediction model. The fifth prediction model predicts the zone temperature setpoints for the multiple furnace temperature control zones based on the strip steel production parameters and the measured strip temperature value. The sixth prediction model predicts the strip temperature value based on the strip steel production parameters, the measured strip temperature value, and the zone temperature setpoint. The above steps are repeated to obtain multiple predicted strip temperature values. These multiple predicted strip temperature values ​​are compared with a target strip temperature value, and the optimal predicted strip temperature value is selected. The optimal predicted strip temperature value is the one with the smallest deviation from the target strip temperature value and is within a predetermined threshold. The zone temperature setpoint corresponding to the optimal predicted strip temperature value is output as the furnace temperature control command.

2. The furnace temperature control method according to claim 1, characterized in that, Also includes: Determine whether the current strip is a normal coil or a transitional coil based on the strip production parameters. If the current strip is a normal coil, the first artificial intelligence model, the second artificial intelligence model and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the current strip and the next normal coil; If the current strip is a transition coil, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the next normal coil.

3. The furnace temperature control method according to claim 1 or 2, characterized in that, The first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model also provide adaptive compensation when one or more of the furnace temperature control zones in the furnace section cannot participate in the control.

4. The furnace temperature control method according to claim 1 or 2, characterized in that, The first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model also provide adaptive compensation for situations where one or more of the furnace temperature control zones in the furnace section cannot continue to heat up or cool down.

5. The furnace temperature control method according to claim 1 or 2, characterized in that, The strip production parameters include one or more of the following: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature of each furnace section, outlet strip temperature, and zone temperature of the multiple furnace temperature control zones.

6. A furnace temperature control system for a cold-rolled annealing furnace for strip steel, the annealing furnace comprising multiple furnace sections, each of the multiple furnace sections comprising multiple furnace temperature control zones, characterized in that, The system includes the following modules for furnace temperature control of at least one of the furnace sections: The first furnace temperature control module, when the weld seam of the preceding and following strip steel is located in a designated area in front of the furnace section, generates furnace temperature control commands for one or more furnace temperature control areas in the furnace section based on strip steel production parameters and a first artificial intelligence model. The first artificial intelligence model includes a first prediction model and a second prediction model. When the first artificial intelligence model determines that a temperature increase or decrease of greater than or equal to a first magnitude is required, the first prediction model predicts the area temperature setpoints for the multiple furnace temperature control areas based on the strip steel production parameters; the second prediction model predicts the strip temperature value based on the strip steel production parameters and the area temperature setpoints; the above steps are repeated. The process involves obtaining multiple predicted zone temperatures; comparing these predicted zone temperatures with a target zone temperature; selecting the optimal predicted zone temperature from the multiple predicted zone temperatures, wherein the optimal predicted zone temperature is the zone temperature with the smallest deviation from the target zone temperature and within a predetermined threshold; outputting the zone temperature setpoint corresponding to the optimal predicted zone temperature as the furnace temperature control command; when the weld is located in the designated zone, the first artificial intelligence model determines, based on the strip steel production parameters, whether it is necessary to preheat or cool one or more furnace temperature control zones within the furnace section by a factor greater than or equal to a first amplitude, and outputting the corresponding furnace temperature control command. The second furnace temperature control module, when the weld is located between a designated position before the furnace section and the furnace section exit, generates furnace temperature control commands for one or more furnace temperature control zones within the furnace section based on the strip steel production parameters and a second artificial intelligence model. The second artificial intelligence model includes a third prediction model and a fourth prediction model. The third prediction model predicts the zone temperature setpoints for the multiple furnace temperature control zones based on the strip steel production parameters; the fourth prediction model predicts the zone temperature value based on the strip steel production parameters and the zone temperature setpoints. The above steps are repeated to obtain multiple predicted zone temperature values. These predicted zone temperature values ​​are compared with a target zone temperature value, and the optimal predicted zone temperature value is selected. The optimal predicted zone temperature value is the zone temperature value with the smallest deviation from the target zone temperature value and within a predetermined threshold. The zone temperature setpoint corresponding to the optimal predicted zone temperature value is output as the furnace temperature control command. The third furnace temperature control module, after the weld has passed through the furnace section outlet, generates furnace temperature control commands for one or more furnace temperature control zones within the furnace section based on the strip steel production parameters and the measured strip temperature value, using a third artificial intelligence model. The third artificial intelligence model includes a fifth prediction model and a sixth prediction model. The fifth prediction model predicts the zone temperature setpoints for the multiple furnace temperature control zones based on the strip steel production parameters and the measured strip temperature value. The sixth prediction model predicts the strip temperature value based on the strip steel production parameters, the measured strip temperature value, and the zone temperature setpoint. This process is repeated to obtain multiple predicted strip temperature values. These predicted strip temperature values ​​are compared with a target strip temperature value, and the optimal predicted strip temperature value is selected. The optimal predicted strip temperature value is the one with the smallest deviation from the target strip temperature value and within a predetermined threshold. The zone temperature setpoint corresponding to the optimal predicted strip temperature value is output as the furnace temperature control command.

7. The furnace temperature control system according to claim 6, characterized in that, Also includes: Determine whether the current strip is a normal coil or a transitional coil based on the strip production parameters. If the current strip is a normal coil, the first artificial intelligence model, the second artificial intelligence model and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the current strip and the next normal coil; If the current strip is a transition coil, the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model determine the furnace temperature control command based on the parameters of the next normal coil.

8. The furnace temperature control system according to claim 6 or 7, characterized in that, The first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model also provide adaptive compensation when one or more of the furnace temperature control zones in the furnace section cannot participate in the control.

9. The furnace temperature control system according to claim 6 or 7, characterized in that, The first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model also provide adaptive compensation for situations where one or more of the furnace temperature control zones in the furnace section cannot continue to heat up or cool down.

10. The furnace temperature control system according to claim 6 or 7, characterized in that, The strip production parameters include one or more of the following: weld location, strip type, strip grade, strip specifications, strip speed, burner information, heat load information, flow rate information, inlet strip temperature of each furnace section, outlet strip temperature, and zone temperature of the multiple furnace temperature control zones.

11. An electronic device, characterized in that, The device includes a memory storing computer-executable instructions and a processor; when the instructions are executed by the processor, the device performs the method according to any one of claims 1 to 5.

12. A computer-readable medium, characterized in that, The computer-readable medium stores one or more programs, which can be executed by one or more processors to implement the method of any one of claims 1 to 5.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images