Furnace type equipment flow control system and method

Abstract

The invention discloses a furnace type equipment flow control system and method, and relates to the field of thermal technological process control. The method comprises the following steps: S1, collecting multi-source sensor data in real time, and carrying out time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; s2, calculating characteristic parameters based on the standardized real-time data flow, wherein the characteristic parameters comprise a dynamic heat flow equilibrium factor, a technological process entropy and equivalent purging efficiency; and S3, based on the characteristic parameters, a gas flow control instruction is generated through a preset intelligent decision rule. Through intelligent data fusion and self-learning optimization, accurate flow control and temperature control precision improvement are realized. And through intelligent purging mode switching, the purging efficiency and the energy-saving effect are optimized.

Description

Technical Field

[0001] This invention relates to the field of thermal process control, specifically to a flow control system and method for furnace equipment. Background Technology

[0002] Furnace equipment is widely used in high-temperature environments, and precise flow control is crucial for improving production efficiency, reducing energy consumption, and ensuring product quality. Most existing flow control methods rely on simple temperature, flow, and pressure feedback mechanisms. While these can achieve basic temperature control, they cannot cope with the changing factors in complex process environments, resulting in insufficient control accuracy and response speed.

[0003] Current technologies primarily rely on single physical feedback regulation, neglecting comprehensive control across multiple parameters and process stages. Especially when facing complex situations such as heat flux fluctuations and gas flow rate changes, traditional methods often fail to achieve timely and precise flow regulation. Furthermore, existing intelligent control systems lack sufficient dynamic feedback response, failing to adjust in a timely manner according to different process stages, resulting in significant control lag.

[0004] Therefore, there is an urgent need for a flow control method that can combine multi-source sensor data, dynamic process parameters, and intelligent decision-making algorithms to achieve efficient and precise gas flow regulation. This method should have the ability to dynamically adjust and optimize the process, thereby improving the overall performance and intelligence level of the furnace equipment. Summary of the Invention

[0005] Based on the shortcomings of the prior art described above, the purpose of this invention is to provide a flow control system and method for furnace equipment to solve the above-mentioned technical problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a flow control method for furnace equipment, comprising: S1: Real-time acquisition of multi-source sensor data, time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; S2: Calculate characteristic parameters based on standardized real-time data streams, including dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; S3: Based on feature parameters, generate gas flow control commands through preset intelligent decision rules.

[0007] The present invention is further configured such that S1 includes: Real-time acquisition of raw data from multiple sources of sensors, including: furnace gas inlet temperature, heating zone temperature, heater power, gas flow rate, furnace pressure, furnace inlet gas pressure, and oxygen concentration; The original data is time-synchronized, and the time synchronization is based on a unified system timestamp. The time-synchronized data is filtered, and high-frequency noise is eliminated by using a moving average method or a low-pass filter. The filtered data is normalized to normalize data of different dimensions to a predetermined standard range; All processed data is aggregated to generate a standardized real-time data stream.

[0008] The present invention is further configured such that S2 includes: a dynamic heat flow equilibrium factor generation unit, a process entropy generation unit, and an equivalent purging efficiency generation unit; The dynamic heat flow equilibrium factor generation unit includes: Receive the standardized real-time data stream output by S1 and extract the gas inlet temperature, heater power, and gas flow rate at the furnace opening; Based on the pre-stored physical property-temperature relationship mapping table, the real-time collected furnace gas inlet temperature is used as the query key for matching or interpolation calculation to obtain the corresponding gas physical properties at the current temperature. The theoretical heat load is calculated based on gas flow rate, furnace inlet gas temperature, gas physical properties, and preset target furnace temperature. By using the real-time energy benchmarking method, the heater power is taken as the actual energy input, and the deviation between it and the theoretical heat load is calculated to generate a dynamic heat flow balance factor.

[0009] The present invention is further configured such that the process entropy generation unit includes: Receive the standardized real-time data stream output by S1 and extract the heating zone temperature and gas flow rate within a preset historical time period; Multiple time scale windows with different spans are set, and the characteristic quantities of temperature fluctuation and gas flow fluctuation in the heating zone are calculated in each time scale window respectively; The system determines the current process stage based on the current process status. The process stage includes a temperature control stage and a purging stage. When it is in the temperature control stage, it further includes a heating stage, a heat preservation stage, and a cooling stage. If the current stage is temperature control, then based on the pre-stored temperature control stage-weight configuration mapping relationship, the fusion weights are assigned to the heating zone temperature fluctuation characteristics and gas flow fluctuation characteristics under each time scale window. Based on the fusion weight, the characteristic quantities of temperature fluctuation and gas flow fluctuation in the heating zone under each time scale window are weighted and fused to generate the process entropy.

[0010] The present invention is further configured such that the equivalent purging efficiency generation unit includes: The system determines the current process stage based on the current process status; If the current stage is purging, the standardized real-time data stream output by S1 is received, and the oxygen concentration and gas flow rate are extracted. The initial oxygen concentration is set at the start of the purging phase, and a preset target oxygen concentration is called. Based on oxygen concentration and gas flow rate, the ratio of the change in oxygen concentration per unit time to the amount of gas consumed is calculated to obtain the rate of change in oxygen concentration.

[0011] The present invention is further configured to track the rate of change of oxygen concentration in real time and calculate the decay trend by linear regression. The decay trend is compared with a preset decay threshold. When the decay trend reaches or falls below the decay threshold, the purging process is determined to have entered an inefficient stage, and the purging duration is recorded. Based on the oxygen concentration change rate and purging duration, an equivalent purging efficiency is generated through an efficiency calculation model, and an efficiency decay indicator is generated simultaneously.

[0012] The present invention is further configured such that S3 includes: a parameter optimization and control unit and an intelligent purge termination unit; The parameter optimization and control unit includes: The system determines the current process stage based on the current process status; When the system is in the temperature control phase, it receives the dynamic heat flow balance factor output by S2. The dynamic heat flow balance factor is compared with the preset upper and lower limits of the heat flow target range; If the dynamic heat flow balance factor remains above the upper limit, an instruction for increasing the gas flow rate setpoint is generated and executed. If the dynamic heat flow equilibrium factor remains below the lower limit, an instruction to reduce the gas flow rate setpoint is generated and executed.

[0013] The present invention is further configured to receive the process entropy output by S2 starting from the second process cycle, and compare the process entropy of the current cycle with the process entropy of the previous cycle. If the process entropy of the current cycle is greater than that of the previous cycle, then with the goal of reducing the process entropy, the PID control parameters of the temperature controller are optimized using the parameter perturbation method, and a parameter optimization command is generated and sent to the temperature controller.

[0014] The present invention is further configured such that the intelligent purge termination unit includes: When the system is in the purging phase, receive the equivalent purging efficiency and the changing trend of the equivalent purging efficiency output by S2; The changing trend is monitored and compared with the preset efficiency decay threshold in real time; When the monitored trend of change is continuously lower than the efficiency decay threshold, a purging mode switching command is generated and executed to adjust the gas flow rate and control the flow actuator to switch from high flow purging mode to low flow maintenance mode.

[0015] The present invention also provides a flow control system for a furnace-type equipment, the system comprising: Data acquisition and preprocessing module: Real-time acquisition of multi-source sensor data, time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; High-dimensional feature parameter calculation module: Calculates feature parameters based on standardized real-time data streams, including dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; Intelligent decision-making and setpoint generation module: Based on feature parameters, it generates gas flow control commands through preset intelligent decision-making rules.

[0016] This invention provides a flow control system and method for furnace-type equipment. The system comprises: S1: Real-time acquisition of multi-source sensor data, followed by time synchronization, filtering, and normalization processing to obtain a standardized real-time data stream; S2: Calculation of characteristic parameters based on the standardized real-time data stream, including a dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; S3: Generation of gas flow control commands based on the characteristic parameters using preset intelligent decision rules. The resulting benefits include: (1) Multi-dimensional intelligent data fusion and real-time processing: This invention can comprehensively reflect the process status of furnace equipment by collecting and standardizing multi-source sensor data in real time and combining high-dimensional feature parameters. Compared with the prior art, this invention provides more accurate flow control and regulation through data fusion and dynamic optimization algorithms, enabling the system to achieve real-time adaptive adjustment at different process stages, which significantly improves control accuracy and response speed. (2) Self-learning optimization and precise adjustment capability: This invention adopts a self-optimization mechanism based on process entropy. By comparing the entropy changes of different process cycles, the PID control parameters of the temperature controller are automatically adjusted. This innovative method can continuously optimize the control strategy according to the changes in process state, effectively reducing oscillation and improving temperature control accuracy. This self-learning optimization capability greatly enhances the intelligence level of the system, reduces manual intervention, and ensures the efficient operation of the furnace equipment at different process stages. (3) Intelligent purging process and maximum efficiency: During the purging stage, this invention introduces an equivalent purging efficiency and purging mode switching mechanism. By monitoring the oxygen concentration change trend in real time and comparing it with a preset attenuation threshold, the efficiency of the purging stage is accurately determined. When the purging efficiency is detected to be continuously lower than the threshold, the system automatically switches to a low flow maintenance mode to avoid energy waste. This optimization strategy not only improves the efficiency of the purging process but also effectively reduces energy consumption, achieving a dual optimization of energy saving and efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 A flowchart illustrating a flow control method for a furnace-type equipment is shown as an exemplary embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a flow control system for a furnace-type equipment, which is an exemplary embodiment of the present invention. Detailed Implementation

[0018] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0020] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0021] Example 1: A flow control method for furnace equipment, such as Figure 1 As shown, it includes: S1: Real-time acquisition of multi-source sensor data, time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; S2: Calculate characteristic parameters based on standardized real-time data streams, including dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; S3: Based on feature parameters, generate gas flow control commands through preset intelligent decision rules.

[0022] The present invention is further configured such that S1 includes: Real-time acquisition of raw data from multiple sources of sensors, including: furnace gas inlet temperature, heating zone temperature, heater power, gas flow rate, furnace pressure, furnace inlet gas pressure, and oxygen concentration; The original data is time-synchronized, and the time synchronization is based on a unified system timestamp. The time-synchronized data is filtered, and high-frequency noise is eliminated by using a moving average method or a low-pass filter. The filtered data is normalized to normalize data of different dimensions to a predetermined standard range; All processed data is aggregated to generate a standardized real-time data stream. Specifically, the system first collects various raw data from the furnace equipment in real time through multiple sensors. This raw data includes the following: 1. Furnace inlet gas temperature: reflecting the temperature of the gas at the furnace inlet, typically acquired by a thermocouple sensor installed at the furnace inlet; 2. Heating zone temperature: monitoring the temperature of the heating zone, typically acquired in real time by temperature sensors such as thermocouples or infrared sensors; 3. Heater power: provided by the power output sensor of the temperature control system, indicating the current operating power of the heater; 4. Gas flow rate: gas flow rate data is fed back in real time by a mass flow meter; 5. Furnace pressure: detected by a furnace pressure sensor, reflecting the pressure condition inside the furnace; 6. Furnace inlet gas pressure: data collected by a furnace inlet gas pressure sensor, used to monitor the inlet gas pressure at the furnace inlet; 7. Oxygen concentration: oxygen probe detects the oxygen concentration inside the furnace, often used to control atmosphere stability. All raw data collected by the sensors are marked with a unified system timestamp to ensure that data from different sensors can be processed synchronously within the same time period. The purpose of time synchronization is to eliminate data timing problems caused by different sensor response times, ensuring the accuracy and timeliness of data processing. Time synchronization is generally achieved through a centralized control system, combined with a high-precision clock signal for marking and synchronization. Time-synchronized data may contain high-frequency noise, leading to instability. Therefore, filtering is necessary to improve data quality. Common filtering methods include: Moving average: By setting a certain window period, the average value of data within each window is calculated, thus smoothing the data and removing sudden noise fluctuations. Low-pass filter: Using a low-pass filtering algorithm, noise signals above a set threshold frequency are filtered out, preserving the low-frequency components of the data and ensuring data stability. These two methods are used in combination during processing; the moving average handles rapidly changing interference, while the low-pass filter handles high-frequency noise. The filtered data is then standardized. Each data source undergoes a linear transformation to scale its values ​​to a uniform standard range, defaulting to 0 to 1. This step is accomplished using min-max normalization or Z-score normalization methods, ensuring that data with different dimensions can be processed uniformly. Ultimately, all processed data is aggregated into a standardized real-time data stream, which serves as input for subsequent computational modules, providing a foundation for flow control and other intelligent decisions.

[0023] The present invention is further configured such that S2 includes: a dynamic heat flow equilibrium factor generation unit, a process entropy generation unit, and an equivalent purging efficiency generation unit; The dynamic heat flow equilibrium factor generation unit includes: Receive the standardized real-time data stream output by S1 and extract the gas inlet temperature, heater power, and gas flow rate at the furnace opening; Based on the pre-stored physical property-temperature relationship mapping table, the real-time collected furnace gas inlet temperature is used as the query key for matching or interpolation calculation to obtain the corresponding gas physical properties at the current temperature. The theoretical heat load is calculated based on gas flow rate, furnace inlet gas temperature, gas physical properties, and preset target furnace temperature. By using a real-time energy benchmarking method, the heater power is taken as the actual energy input, and the deviation from the theoretical heat load is calculated to generate a dynamic heat flow balance factor. Specifically, the furnace inlet gas temperature, heater power, and gas flow rate are extracted from the standardized real-time data stream output by S1. These data reflect the current working status inside the furnace in real time. Subsequently, the furnace inlet gas temperature is used to look up the corresponding gas physical properties at the current temperature in a pre-stored property-temperature relationship mapping table. The gas physical properties include specific heat capacity and density. If there is no corresponding temperature point in the mapping table, the gas physical properties are calculated using interpolation algorithms, such as linear interpolation. Combining the gas flow rate, furnace inlet gas temperature, gas physical properties, and the preset target furnace temperature, the theoretical heat load is calculated. The theoretical heat load represents the amount of heat that needs to be carried into the furnace by the gas flow per unit time to maintain the target furnace temperature. The specific calculation process is as follows: Based on the gas flow rate and gas physical properties, the heat carried away by the gas is calculated. The calculation principle is: the theoretical heat load is equal to the product of the gas mass flow rate, the gas isobaric specific heat capacity, and the difference between the target furnace temperature and the furnace inlet gas temperature. Finally, a dynamic heat flow balance factor is generated using the real-time energy benchmarking method. The real-time energy benchmarking method compares the actual output power of the heater as the actual energy input with the calculated theoretical heat load, and the resulting ratio is the dynamic heat flow balance factor. The dynamic heat flow balance factor quantifies the dynamic balance state of heat flow in the furnace. If the value is close to 1, it indicates that the heating power in the furnace is well matched with the actual demand; if it is greater than 1, it indicates that there is excess heat; if it is less than 1, it indicates that the heat input needs to be increased.

[0024] The present invention is further configured such that the process entropy generation unit includes: Receive the standardized real-time data stream output by S1 and extract the heating zone temperature and gas flow rate within a preset historical time period; Multiple time scale windows with different spans are set, and the characteristic quantities of temperature fluctuation and gas flow fluctuation in the heating zone are calculated in each time scale window respectively; The system determines the current process stage based on the current process status. The process stage includes a temperature control stage and a purging stage. When it is in the temperature control stage, it further includes a heating stage, a heat preservation stage, and a cooling stage. If the current stage is temperature control, then based on the pre-stored temperature control stage-weight configuration mapping relationship, the fusion weights are assigned to the heating zone temperature fluctuation characteristics and gas flow fluctuation characteristics under each time scale window.Based on fusion weights, the characteristic quantities of temperature fluctuation in the heating zone and gas flow fluctuation under each time scale window are weighted and fused to generate the process entropy. Specifically, the process entropy generation unit first extracts the heating zone temperature and gas flow data from the standardized real-time data stream output by S1. These data reflect the state of the furnace equipment at each process stage, especially the temperature changes and gas flow fluctuations in the heating zone. The heating zone temperature represents the temperature of the heating area, reflecting the energy distribution during the heating process; the gas flow represents the flow rate of the gas in the furnace, reflecting the impact of gas circulation on the heat and process within the furnace. To comprehensively understand the fluctuation characteristics of the process within the furnace, the system needs to set multiple time scale windows with different spans. These windows can be flexibly adjusted according to actual needs; each window represents a different time period, aiming to capture the characteristics of temperature and flow fluctuations at different time scales. The time scale window can be at the second, minute, or hour level, depending on the fluctuation frequency and period to be analyzed; the default setting is at the minute level. For each timescale window, the system needs to calculate the following two fluctuation characteristics: 1. Heating zone temperature fluctuation characteristic: This represents the degree of change and volatility of the heating zone temperature within a certain time window, expressed by calculating the standard deviation of the temperature within that window; 2. Gas flow rate fluctuation characteristic: This represents the fluctuation of the gas flow rate within a certain time window, similar to the heating zone temperature fluctuation characteristic, expressed by calculating the standard deviation of the flow rate within that window. These fluctuation characteristics help measure the stability of heat and gas flow during the process, as well as their impact on the system. Based on the calculation of these fluctuation characteristics, the system determines the process stage of the furnace equipment according to the current process state. Different stages have different impacts on the stability and entropy of the process, therefore, weighting needs to be configured according to the process stage. The main process stages include: 1. Temperature control stage: This refers to the stage of furnace temperature control, specifically subdivided into: Heating stage: the equipment is heating or heating up; Holding stage: the equipment maintains a constant temperature; Cooling stage: the equipment is cooling down. 2. Purging stage: This refers to the stage where the equipment is purging or cleaning. If the current stage is temperature control, then according to the pre-stored process stage-weight configuration mapping relationship, the characteristic quantities of temperature fluctuation in the heating zone and gas flow fluctuation under different time scale windows are fused and weighted. Specifically, when designing at the beginning, when setting the process stage-weight configuration mapping relationship, it is necessary to assign higher weights to short time scale windows during the heating or cooling stage, and assign higher weights to long time scale windows during the heat preservation stage.Finally, based on the assigned fusion weights, the temperature and flow fluctuation characteristics under each time scale window are weighted and fused to calculate the process entropy. The process entropy comprehensively considers the influence of temperature and flow fluctuations on the process entropy. The process entropy quantifies the volatility and disorder of the process: the larger the entropy value, the higher the volatility and uncertainty of the system; the smaller the entropy value, the more stable and orderly the process.

[0025] The present invention is further configured such that the equivalent purging efficiency generation unit includes: The system determines the current process stage based on the current process status; If the current stage is purging, the standardized real-time data stream output by S1 is received, and the oxygen concentration and gas flow rate are extracted. The initial oxygen concentration is set at the start of the purging phase, and a preset target oxygen concentration is called. Based on oxygen concentration and gas flow rate, the ratio of the change in oxygen concentration to the gas consumption per unit time is calculated to obtain the oxygen concentration change rate. Specifically, when the system determines that it is currently in the purging stage, it first extracts key real-time data from the standardized real-time data stream output by S1. This data includes oxygen concentration and gas flow rate. Specifically, the oxygen concentration is measured and fed back by an oxygen concentration sensor, reflecting the oxygen content in the furnace atmosphere; the gas flow rate is monitored by a mass flow meter, indicating the flow rate of the gas during the purging stage. The oxygen concentration value at the start of the purging stage is used as the initial oxygen concentration, representing the oxygen content in the furnace at the start of the purging stage and the atmosphere state in the furnace at the beginning of the purging stage. This initial oxygen concentration value will serve as a benchmark value for tracking subsequent changes in oxygen concentration. Simultaneously, the system obtains the ideal oxygen concentration from a preset target oxygen concentration value, which is set based on process requirements and design standards. Based on the change in oxygen concentration from the start of purging to the current moment and the cumulative gas consumption, the oxygen concentration change rate is calculated. In a preferred embodiment, the oxygen concentration change rate is calculated as follows: the difference between the initial oxygen concentration and the current oxygen concentration is divided by the cumulative gas consumption volume from the start of purging to the current moment, and the ratio of these two values ​​is the oxygen concentration change rate. The oxygen concentration change rate is a measure of the ratio of the change in oxygen concentration to the amount of gas consumed, and it characterizes the reduction in oxygen concentration that can be achieved by consuming a unit volume of purging gas.

[0026] The present invention is further configured to track the rate of change of oxygen concentration in real time and calculate the decay trend by linear regression. The decay trend is compared with a preset decay threshold. When the decay trend reaches or falls below the decay threshold, the purging process is determined to have entered an inefficient stage, and the purging duration is recorded. Based on the oxygen concentration change rate and purging duration, an equivalent purging efficiency is generated through an efficiency calculation model, along with an efficiency decay indicator. Specifically, the system tracks the trend of the oxygen concentration change rate in real time. Within a preset time range, linear regression is used to fit the data sequence of the oxygen concentration change rate over time. The slope of the resulting straight line represents the decay trend. Linear regression establishes a mathematical model to describe the change in oxygen concentration change rate over time, thereby calculating a decay trend. The decay trend quantifies the rate of decrease in the oxygen concentration change rate. The calculated decay trend is compared with a preset decay threshold. When the absolute value of the decay trend reaches or falls below this threshold, the system determines that the purging process has entered an inefficient phase and records the purging duration from the start of purging to the present. Subsequently, based on the oxygen concentration change rate and purging duration, an equivalent purging efficiency is generated through an efficiency calculation model. The equivalent purging efficiency is a comprehensive efficiency value that considers both oxygen concentration change and gas flow consumption, representing the overall efficiency of the purging process. A higher value indicates better gas utilization efficiency during purging. Once the system calculates the equivalent purging efficiency, it further generates an efficiency decay flag. The efficiency decay flag is used to indicate whether the efficiency has decreased during the purging process. It is a Boolean value that indicates whether the current stage is an inefficient purging phase.

[0027] The present invention is further configured such that S3 includes: a parameter optimization and control unit and an intelligent purge termination unit; The parameter optimization and control unit includes: The system determines the current process stage based on the current process status; When the system is in the temperature control phase, it receives the dynamic heat flow balance factor output by S2. The dynamic heat flow balance factor is compared with the preset upper and lower limits of the heat flow target range; If the dynamic heat flow balance factor remains above the upper limit, an instruction for increasing the gas flow rate setpoint is generated and executed. If the dynamic heat flow balance factor remains below the lower limit, an instruction to decrease the gas flow rate setpoint is generated and executed. Specifically, the system first determines the current process stage based on real-time data, such as furnace inlet temperature, heater power, and gas flow rate, to confirm whether it is currently in the temperature control stage. When in the temperature control stage, the system receives the dynamic heat flow balance factor from layer S2 and compares it with the preset upper and lower limits of the heat flow target range. The heat flow target range includes the upper and lower limits of the dynamic heat flow balance factor to ensure that the furnace temperature is maintained within the ideal range. If the dynamic heat flow balance factor remains above the upper limit, it indicates that the furnace heating power is excessive. The system then generates and executes an instruction to increase the gas flow rate setpoint. By increasing the gas flow rate, its cooling effect on the furnace is enhanced, thus causing the factor to fall back to the target range. If the dynamic heat flow balance factor remains below the lower limit, it indicates that the gas flow carries away too much heat. The system then generates and executes an instruction to decrease the gas flow rate setpoint. By reducing the gas flow rate, its cooling effect is weakened, which helps the furnace temperature rise, causing the dynamic heat flow balance factor to return to the target range. The adjustment process typically involves short-cycle cycles to ensure real-time response to temperature changes. Short-cycle control is based on real-time data feedback, with the system continuously fine-tuning the gas flow rate to address furnace temperature variations. During execution, the system continuously monitors the temperature control effectiveness; if the adjusted gas flow rate fails to bring the furnace temperature back within the target range, the system will reassess and make further adjustments.

[0028] The present invention is further configured to receive the process entropy output by S2 starting from the second process cycle, and compare the process entropy of the current cycle with the process entropy of the previous cycle. If the process entropy of the current cycle is greater than that of the previous cycle, the system aims to reduce the process entropy by optimizing the PID control parameters of the temperature controller using a parameter perturbation method, and generates a parameter optimization command which is then sent to the temperature controller. Specifically, starting from the second process cycle, at the end of each cycle, the system receives the process entropy of the current cycle output from layer S2 and compares it with the process entropy of the previous cycle stored in the database. If the process entropy of the current cycle is less than or equal to the entropy value of the previous cycle, it indicates that the process stability is stable or has improved, and the system maintains the current PID parameters unchanged and directly enters the next cycle. If the process entropy of the current cycle is greater than that of the previous cycle, it indicates that the process volatility has increased, and the system initiates the parameter optimization process. This process is based on the parameter perturbation method, and the specific steps are as follows: First, the system backs up the currently used PID parameter set, including proportional gain, integral time, and derivative time. Then, a preset, small positive perturbation is applied to one of the parameters, for example, increasing the proportional gain by 5%, generating a new set of candidate parameters. This set of candidate parameters is sent to the temperature controller and applied to the next complete process cycle. After the cycle ends, the process entropy generated under the new parameters is obtained. The optimized process entropy is compared with the unoptimized process entropy. If the optimized entropy is less than the unoptimized entropy, the perturbation direction is correct and the optimization is effective. The system retains this set of parameters as a new benchmark and performs the next perturbation along this direction. If the optimized entropy is greater than the unoptimized entropy, the perturbation direction is incorrect. The system restores the original parameters from the backup and applies a negative perturbation to the parameter, for example, reducing the proportional gain by 5%. The previous steps are repeated until the process entropy no longer decreases significantly or the maximum number of iterations is reached. At this point, the current scheme is considered the optimal parameters. Finally, the optimized PID control parameter command is sent to the temperature controller. The temperature controller adjusts the heating power of the heating zone according to the new PID parameters to achieve more precise temperature control.

[0029] The present invention is further configured such that the intelligent purge termination unit includes: When the system is in the purging phase, receive the equivalent purging efficiency and the changing trend of the equivalent purging efficiency output by S2; The changing trend is monitored and compared with the preset efficiency decay threshold in real time; When the monitored trend is consistently below the efficiency decay threshold, a purging mode switching command is generated and executed to adjust the gas flow rate and control the flow actuator to switch from high-flow purging mode to low-flow maintenance mode. Specifically, when the system is in the purging phase, it receives the equivalent purging efficiency and its changing trend from the S2 output, and compares the changing trend with the preset efficiency decay threshold in real time. The specific value of the efficiency decay threshold is determined by engineering experience or historical data and is set in advance based on the range of changes in gas flow rate and oxygen concentration. When the monitored trend is consistently below the efficiency decay threshold, it indicates that the purging process has entered an inefficient phase. At this point, the purification effect improvement per unit of gas consumption is negligible. The system generates and executes a purging mode switching command to control the flow actuator to switch the gas flow rate from high-flow purging mode to low-flow maintenance mode, thereby significantly saving gas consumption while ensuring the quality of the atmosphere inside the furnace.

[0030] Example 2: Please refer to Figure 2 An exemplary flow control system for a furnace includes: Data acquisition and preprocessing module: Real-time acquisition of multi-source sensor data, time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; High-dimensional feature parameter calculation module: Calculates feature parameters based on standardized real-time data streams, including dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; Intelligent decision-making and setpoint generation module: Based on feature parameters, it generates gas flow control commands through preset intelligent decision-making rules.

[0031] It should be noted that the furnace equipment flow control system provided in the above embodiments and the furnace equipment flow control method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments, and will not be repeated here. In practical applications, the furnace equipment flow control system provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0032] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A flow control method for a furnace-type equipment, characterized in that, include: S1: Real-time acquisition of multi-source sensor data, time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; S2: Calculate characteristic parameters based on standardized real-time data streams, including dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; S3: Based on feature parameters, generate gas flow control commands through preset intelligent decision rules.

2. The flow control method for a furnace-type equipment according to claim 1, characterized in that, S1 includes: Real-time acquisition of raw data from multiple sources of sensors, including: furnace gas inlet temperature, heating zone temperature, heater power, gas flow rate, furnace pressure, furnace inlet gas pressure, and oxygen concentration; The original data is time-synchronized, and the time synchronization is based on a unified system timestamp. The time-synchronized data is filtered, and high-frequency noise is eliminated by using a moving average method or a low-pass filter. The filtered data is normalized to normalize data of different dimensions to a predetermined standard range; All processed data is aggregated to generate a standardized real-time data stream.

3. The flow control method for a furnace-type equipment according to claim 1, characterized in that, The S2 includes: a dynamic heat flow equilibrium factor generation unit, a process entropy generation unit, and an equivalent purging efficiency generation unit. The dynamic heat flow equilibrium factor generation unit includes: Receive the standardized real-time data stream output by S1 and extract the gas inlet temperature, heater power, and gas flow rate at the furnace opening; Based on the pre-stored physical property-temperature relationship mapping table, the gas inlet temperature collected in real time at the furnace mouth is used as the query key for matching or interpolation calculation to obtain the corresponding gas physical properties at the current temperature; The theoretical heat load is calculated based on gas flow rate, furnace inlet gas temperature, gas physical properties, and preset target furnace temperature. By using the real-time energy benchmarking method, the heater power is taken as the actual energy input, and the deviation between it and the theoretical heat load is calculated to generate a dynamic heat flow balance factor.

4. The flow control method for a furnace-type equipment according to claim 3, characterized in that, The process entropy generation unit includes: Receive the standardized real-time data stream output by S1 and extract the heating zone temperature and gas flow rate within a preset historical time period; Multiple time scale windows with different spans are set, and the characteristic quantities of temperature fluctuation and gas flow fluctuation in the heating zone are calculated in each time scale window respectively; The system determines the current process stage based on the current process status. The process stage includes a temperature control stage and a purging stage. When it is in the temperature control stage, it further includes a heating stage, a heat preservation stage, and a cooling stage. If the current stage is temperature control, then based on the pre-stored temperature control stage-weight configuration mapping relationship, the fusion weights are assigned to the heating zone temperature fluctuation characteristics and gas flow fluctuation characteristics under each time scale window. Based on the fusion weight, the characteristic quantities of temperature fluctuation and gas flow fluctuation in the heating zone under each time scale window are weighted and fused to generate the process entropy.

5. The flow control method for a furnace-type equipment according to claim 4, characterized in that, The equivalent purging efficiency generation unit includes: The system determines the current process stage based on the current process status; If the current stage is purging, the standardized real-time data stream output by S1 is received, and the oxygen concentration and gas flow rate are extracted. The initial oxygen concentration is set at the start of the purging phase, and a preset target oxygen concentration is called. Based on oxygen concentration and gas flow rate, the ratio of the change in oxygen concentration per unit time to the amount of gas consumed is calculated to obtain the rate of change in oxygen concentration.

6. The flow control method for a furnace-type equipment according to claim 5, characterized in that, Real-time tracking of oxygen concentration change rate, and calculation of decay trend using linear regression method; The decay trend is compared with a preset decay threshold. When the decay trend reaches or falls below the decay threshold, the purging process is determined to have entered an inefficient stage, and the purging duration is recorded. Based on the oxygen concentration change rate and purging duration, an equivalent purging efficiency is generated through an efficiency calculation model, and an efficiency decay indicator is generated simultaneously.

7. The flow control method for a furnace-type equipment according to claim 1, characterized in that, The S3 includes: a parameter optimization and control unit and an intelligent purge termination unit; The parameter optimization and control unit includes: The system determines the current process stage based on the current process status; When the system is in the temperature control phase, it receives the dynamic heat flow balance factor output by S2. The dynamic heat flow balance factor is compared with the preset upper and lower limits of the heat flow target range; If the dynamic heat flow balance factor remains above the upper limit, an instruction for increasing the gas flow rate setpoint is generated and executed. If the dynamic heat flow equilibrium factor remains below the lower limit, an instruction to reduce the gas flow rate setpoint is generated and executed.

8. The flow control method for a furnace-type equipment according to claim 1, characterized in that, Starting from the second process cycle, receive the process entropy output by S2 and compare the current cycle process entropy with the previous cycle process entropy. If the process entropy of the current cycle is greater than that of the previous cycle, then with the goal of reducing the process entropy, the PID control parameters of the temperature controller are optimized using the parameter perturbation method, and a parameter optimization command is generated and sent to the temperature controller.

9. A flow control method for a furnace-type equipment according to claim 8, characterized in that, The intelligent purge termination unit includes: When the system is in the purging phase, receive the equivalent purging efficiency and the changing trend of the equivalent purging efficiency output by S2; The changing trend is monitored and compared with the preset efficiency decay threshold in real time; When the monitored trend of change is continuously lower than the efficiency decay threshold, a purging mode switching command is generated and executed to adjust the gas flow rate and control the flow actuator to switch from high flow purging mode to low flow maintenance mode.

10. A flow control system for a furnace-type equipment, used to implement the flow control method for a furnace-type equipment as described in any one of claims 1-9, characterized in that, include: Data acquisition and preprocessing module: Real-time acquisition of multi-source sensor data, time synchronization, filtering and normalization processing to obtain a standardized real-time data stream; High-dimensional feature parameter calculation module: Calculates feature parameters based on standardized real-time data streams, including dynamic heat flow equilibrium factor, process entropy, and equivalent purging efficiency; Intelligent decision-making and setpoint generation module: Based on feature parameters, it generates gas flow control commands through preset intelligent decision-making rules.

Images