Intelligent power supply control system and method for glass electric melting furnace

Abstract

The invention relates to the technical field of electric energy control in the glass manufacturing process, and discloses an intelligent power supply control system and method for a glass electric melting furnace. The method comprises the following steps: collecting operation data such as current, voltage and furnace temperature of the electric melting furnace, and carrying out filtering and normalization preprocessing; calculating target electric power and target temperature based on a fuzzy control algorithm; an adjusting scheme is determined through an optimization strategy, electric energy allocation control is executed, and dynamic adjustment of the temperature and the power is achieved. The system comprises a data acquisition and preprocessing module, an intelligent control decision module and an electric power execution and allocation module, the modules work cooperatively, and the operation stability and energy saving performance of the electric melting furnace are improved. The system can effectively reduce energy waste and prolong the service life of equipment, has the advantages of intelligence, high precision, real-time response and the like, and is suitable for large-scale industrial glass production scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy control in a glass manufacturing process, and in particular to an intelligent power supply control system and method for a glass electric melting furnace, belonging to the technical field of intersection of industrial automation and electric power control. Background Art

[0002] Traditional electric glass furnaces suffer from delayed power control and lack dynamic adjustment. Existing electric glass furnaces typically rely on fixed power supply or manual periodic adjustments, lacking the ability to intelligently sense and regulate the furnace's real-time operating status. When the heat load suddenly changes or the furnace temperature fluctuates dramatically during the glass melting process, existing control systems struggle to respond promptly, resulting in significant temperature fluctuations that affect melting stability and glass quality.

[0003] Uneven energy consumption distribution in multi-electrode, multi-zone systems can easily lead to energy waste: In large electric furnaces, multiple electrodes are usually configured to heat different zones. However, the existing system cannot intelligently distribute power based on the actual power demand of each zone. Some zones are often overheated while other zones are underpowered, resulting in low overall energy efficiency and uneconomical system operation.

[0004] Lack of integrated control systems that integrate prediction and optimization algorithms, and low level of intelligence: Although some improved systems have introduced basic PID or PLC control mechanisms, they have failed to integrate intelligent algorithms such as fuzzy control, adaptive parameter adjustment, and dynamic optimization. They are unable to perform real-time prediction and multi-objective optimization control of power distribution and temperature regulation while ensuring stable operation, and are unable to meet the needs of industrial glass production for high precision, low energy consumption, and intelligent control. Summary of the Invention

[0005] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solution: an intelligent power supply control method for a glass electric melting furnace, comprising the following steps:

[0006] S1. According to the real-time working status of the glass electric melting furnace, collect the input current I of the electric melting furnace in (t), voltage V in (t) and furnace temperature data T(t), and filter and normalize them through the data preprocessing unit to obtain the processed input current I in '(t), voltage V in '(t) and furnace temperature T'(t);

[0007] S2, the current I obtained according to step S1 in '(t), voltage V in '(t) and furnace temperature T'(t), by establishing a multi-input multi-output control model, combined with an innovative fuzzy control algorithm for power regulation, the target electric power P is calculatedtarget (t) and target temperature T target (t);

[0008] S3, the target electric power P obtained according to step S2 target (t) and target temperature T target (t), using innovative power regulation algorithm to generate optimized power scheduling plan P opt (t) and temperature regulation scheme T opt (t);

[0009] S4, the power scheduling scheme P calculated according to step S3 opt (t) and temperature regulation scheme T opt (t), power distribution and temperature control are carried out through the intelligent power distribution module, and real-time control instructions are sent to the electric furnace control system to realize intelligent power supply control of the electric furnace.

[0010] Preferably, the filtering method of the data preprocessing unit in step S1 includes:

[0011] The input current I is filtered using a low-pass filter. in (t) and voltage signal V in (t) is filtered, and the formula is:

[0012] I′ in (t) = I in (t)*H low-pass (t);

[0013] V′ in (t) = V in (t)*H low-pass (t);

[0014] T'(t)=T(t)*H low-pass (t);

[0015] Among them, H low-pass (t) is the transfer function of the low-pass filter, * is the convolution operation, I' in (t) is the input current after filtering, V in '(t) is the voltage after filtering, and T'(t) is the furnace temperature after filtering.

[0016] Preferably, the innovative fuzzy control algorithm in step S2 includes the following steps:

[0017] S2(1), input variable calculation:

[0018] ΔI(t)=I′ in (t)-I′ in (t-1);

[0019] ΔV(t)=V′ in (t)-V′ in (t)-1);

[0020] ΔT(t)=T'(t)-T'(t-1);

[0021] Where ΔI(t) is the current deviation, ΔV(t) is the voltage deviation, and ΔT(t) is the temperature deviation;

[0022] S2(2) Optimize the objective function: Through the innovative fuzzy control algorithm, the target electric power P is obtained. target (t) and target temperature T target (t), the calculation formula is as follows:

[0023] P target (t)=η·(ω1·ΔI(t)+ω2·ΔV(t));

[0024] Where η is the power factor of the electric power system, which can be obtained by querying the system parameters of the glass electric melting furnace;

[0025] T target (t) = ζ·ω3·ΔT(t);

[0026] Among them, ζ is the temperature control response coefficient, which represents the sensitivity of temperature regulation to the temperature control system. It can be obtained by querying the system parameters of the glass electric melting furnace. ω1, ω2, and ω3 are weight factors, satisfying ω1+ω2+ω3=1.

[0027] Preferably, in step S3, the power scheduling scheme P is calculated by an innovative power regulation algorithm. opt (t) and temperature regulation scheme T opt (t), the specific steps are as follows:

[0028] S3(1) The target electric power P at the current moment has been obtained in step S2. target (t), and combined with the innovative power regulation algorithm to calculate the power scheduling solution P opt (t), the formula is as follows:

[0029]

[0030] in:

[0031] P' in (t) is the input power after filtering, and the calculation formula is

[0032] is the derivative of the target electric power with respect to time t;

[0033] ΔI(t) is the current deviation;

[0034] ΔV(t) is the voltage deviation;

[0035] α1, α2, and α3 are dynamic scheduling weight parameters, and they all satisfy α1+α2+α3=1;

[0036] S3(2), after obtaining the target temperature T target (t), combined with the current temperature state and the impact of input power on temperature, a temperature regulation scheme T is constructed. opt (t), the specific formula is as follows:

[0037]

[0038] in:

[0039] T target (t) is the target temperature;

[0040] T'(t) is the furnace temperature after filtering at time t;

[0041] T'(t-1) is the furnace temperature after filtering at time t-1;

[0042] is the rate of change of furnace temperature;

[0043] is the rate of change of the filtered input power;

[0044] ΔT(t) is the temperature deviation, calculated as ΔT(t) = T'(t) - T'(t-1);

[0045] β1, β2, and β3 are the response coefficients of the temperature control algorithm, and they all satisfy β1+β2+β3=1;

[0046] Preferably, the intelligent power distribution module in step S4 is configured to distribute power according to the power scheduling scheme P opt (t) and temperature regulation scheme T opt (t) performing power distribution, wherein the power distribution process includes:

[0047] According to the power and temperature requirements of each part of the glass electric melting furnace, an innovative load prediction algorithm is used to calculate the power demand P of each submodule. sub (t), and dynamically adjust the power distribution of each submodule through the load balancing algorithm to optimize the overall energy efficiency of the system. The innovative load prediction algorithm is as follows:

[0048]

[0049] in:

[0050] P opt(t) is the power scheduling scheme;

[0051] T opt (t) is the temperature regulation scheme;

[0052] T'(t) is the furnace temperature after filtering at time t;

[0053] is the temperature error normalization term;

[0054] is the furnace temperature change rate;

[0055] The present invention also provides an intelligent power supply control system for a glass electric melting furnace, comprising the following modules:

[0056] The data acquisition and preprocessing module is used to collect the input current, voltage and temperature data of the glass electric melting furnace in real time, and perform low-pass filtering and normalization on the collected data to generate preprocessed multi-dimensional data to provide accurate input for control decisions;

[0057] An intelligent control decision module is used to build a multi-input multi-output model based on pre-processed input current, voltage, and furnace temperature data. It uses innovative fuzzy control algorithms and innovative power regulation algorithms to jointly calculate target electric power and target temperature, thereby generating optimized power scheduling and temperature regulation plans.

[0058] The power execution and allocation module is used to dynamically allocate power to each sub-module of the glass electric melting furnace based on the optimized power scheduling and temperature regulation plans, using innovative load prediction and load balancing algorithms, to achieve intelligent and energy-efficient power supply control.

[0059] The data acquisition and preprocessing module includes:

[0060] Data acquisition submodule: used to collect the input current, voltage and temperature data of the glass electric melting furnace in real time, ensuring that the acquired raw data has a high sampling frequency and accuracy;

[0061] Data preprocessing submodule: used to filter and normalize the collected data to remove noise and unify the dimension, improve data availability, and provide high-quality data support for the input of subsequent control models.

[0062] The intelligent control decision module includes:

[0063] Fuzzy control submodule: used to generate target electric power and target temperature based on a multi-input and multi-output control model, combining current, voltage and temperature change trends;

[0064] Power and temperature regulation strategy submodule: used to calculate the optimized regulation scheme based on the target power and target temperature, thereby achieving fine control of the electric furnace power supply system.

[0065] The power execution and allocation module includes:

[0066] Dynamic power allocation submodule: This module allocates power resources based on the power and temperature requirements of each sub-area and optimizes the scheduling scheme to achieve a balanced power supply across multiple areas.

[0067] Load prediction and regulation submodule: used to predict the load changes of each submodule based on real-time temperature deviation and historical power change trends, and dynamically adjust the power distribution plan to optimize the overall power supply efficiency of the system.

[0068] Compared with the prior art, the present invention has the following beneficial effects:

[0069] Achieve dynamic optimal control of power supply scheduling and improve energy utilization efficiency: By building a multi-input and multi-output control model and combining innovative fuzzy control algorithms with power regulation algorithms, it is possible to analyze the changing trends of current, voltage and furnace temperature in real time, calculate the optimal power scheduling and temperature regulation plans, and accurately control the power supply behavior of the glass electric melting furnace, effectively avoiding the energy consumption redundancy and power fluctuation problems existing in traditional control methods, and significantly improving the energy utilization efficiency of the system.

[0070] Improving the power supply system's responsiveness and stability, ensuring process continuity: This invention incorporates dynamic factors such as the furnace temperature change rate and the input power derivative. By implementing temperature regulation and power scheduling formulas with response coefficients, it significantly enhances the system's ability to respond quickly to external disturbances and furnace temperature fluctuations. Furthermore, an innovative load prediction algorithm and load balancing mechanism enable dynamic power distribution among the furnace's submodules, ensuring continuity and temperature control stability during the glass melting process.

[0071] Enhanced system intelligence and improved automation and intelligent control capabilities for glass furnace operations: This invention improves data quality through low-pass filtering and normalization techniques. Fuzzy logic control and predictive algorithms are combined to intelligently evolve the control model, enabling precise sensing and intelligent control of the glass furnace's operating status. The system automatically adjusts power and temperature based on furnace conditions, independent of human intervention. This significantly enhances the control system's intelligence and automated operation capabilities, meeting the high-precision and adaptability requirements of intelligent manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic flow chart of the method steps provided for this application;

[0073] Figure 2 Schematic diagram of the system modules provided for this application. DETAILED DESCRIPTION

[0074] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0075] refer to Figure 1 The embodiment of the present invention provides an intelligent power supply control method for a glass electric melting furnace, comprising the following steps:

[0076] Step 1: According to the real-time working status of the glass melting furnace, collect the input current I of the melting furnace in (t), voltage V in (t) and furnace temperature data T(t), and filter and normalize them through the data preprocessing unit to obtain the processed input current I in '(t), voltage V in '(t) and furnace temperature T'(t).

[0077] In step 1, the input current I of the glass electric melting furnace is first collected in real time by the sensor. in (t), input voltage V in The data acquisition module ensures that the collected current, voltage and temperature signals have high sampling frequency and high accuracy.

[0078] All collected data is then fed into a data preprocessing unit, where it is filtered using a low-pass filter to remove high-frequency fluctuations from environmental noise, interference, and other sources, ensuring data stability and accuracy.

[0079] The specific filtering process is as follows:

[0080] For input current I in (t) is filtered, and the formula is:

[0081] I′ in (t) = I in (t)*H low-pass (t);

[0082] For input voltage V in (t) is filtered, and the formula is:

[0083] V′ in (t) = V in(t)*H low-pass (t);

[0084] The furnace temperature T(t) is filtered and the formula is:

[0085] T'(t)=T(t)*H low-pass (t);

[0086] Among them, H low-pass (t) is the transfer function of the low-pass filter, * is the convolution operation, I' in (t) is the input current after filtering, V' in (t) is the filtered input voltage, and T'(t) is the filtered furnace temperature data. After filtering, high-frequency noise in the data is effectively removed, resulting in a more stable signal.

[0087] Step 2: The current I obtained in step 1 in '(t), voltage V in '(t) and furnace temperature T'(t), by establishing a multi-input multi-output control model, combined with an innovative fuzzy control algorithm for power regulation, the target electric power P is calculated target (t) and target temperature T target (t).

[0088] First, according to the current I after filtering in step 1 in '(t), voltage V in '(t) and furnace temperature T'(t) data, calculate the deviation between the current moment and the previous moment. The specific calculation method is as follows:

[0089] Current deviation calculation:

[0090] ΔI(t)=I′ in (t)-I′ in (t-1);

[0091] Among them, ΔI(t) represents the current deviation between the current moment and the previous moment, reflecting the degree of change of the current signal.

[0092] Voltage deviation calculation:

[0093] ΔV(t)=V′ in (t)-V′ in (t-1);

[0094] Among them, ΔV(t) represents the voltage deviation between the current moment and the previous moment, reflecting the changing trend of the voltage signal.

[0095] Temperature deviation calculation:

[0096] ΔT(t)=T'(t)-T'(t-1);

[0097] Among them, ΔT(t) represents the temperature deviation between the current moment and the previous moment, which is used to quantify the change of furnace temperature.

[0098] These calculated deviation values ​​will serve as input variables of the fuzzy control algorithm, reflecting the temporal trends of current, voltage and temperature.

[0099] After obtaining the deviation values ​​of current, voltage and temperature, the innovative fuzzy control algorithm calculates the target electric power P according to these input variables. target (t) and target temperature T target (t). The control strategy is optimized by fuzzy control algorithm to ensure that the glass electric melting furnace can be stable and achieve the expected power and temperature targets during operation.

[0100] Calculate the target electric power:

[0101] P target (t)=η·(ω1·ΔI(t)+ω2·ΔV(t));

[0102] Where η is the power factor of the electric power system, which can be obtained by querying the system parameters of the glass electric melting furnace;

[0103] Calculate the target temperature:

[0104] T target (t) = ζ·ω3·ΔT(t);

[0105] ζ is the temperature control response coefficient, which indicates the sensitivity of temperature regulation to the temperature control system and can be obtained by querying the system parameters of the glass electric melting furnace;

[0106] ω1, ω2, and ω3 are weight factors, satisfying ω1+ω2+ω3=1.

[0107] By optimizing this objective function, the system dynamically adjusts the target power and temperature based on the deviations in current, voltage, and temperature to achieve stable control. In practical applications, the fuzzy control algorithm flexibly addresses system uncertainty and complexity, ensuring stable operation and high-efficiency output of the glass furnace.

[0108] Step 3: Target power P obtained in step 2 target (t) and target temperature T target (t), using innovative power regulation algorithm to generate optimized power scheduling plan P opt (t) and temperature regulation scheme P opt (t).

[0109] In step 3, the target electric power P is calculated according to the fuzzy control algorithm. target(t). Next, the system uses an innovative power regulation algorithm to further optimize the electric power scheduling scheme P opt (t). The calculation formula of the power scheduling scheme is as follows:

[0110]

[0111] Among them, P' in (t) is the input power after filtering, and the calculation formula is:

[0112]

[0113] The system first calculates the input power based on the filtered input current and voltage. Then, combined with the target power P target (t) Rate of change relative to time The current deviation ΔI(t) and voltage deviation ΔV(t) are adjusted using dynamic weight parameters α1, α2, and α3. The weight parameters satisfy α1+α2+α3=1. Based on system requirements, the weights of each parameter are adjusted in a timely manner to optimize the power scheduling solution.

[0114] Then, the system has obtained the target temperature T target (t), and on this basis, combined with the current temperature state and the impact of input power on temperature, calculate the temperature adjustment scheme T opt (t). The specific temperature adjustment solution calculation formula is as follows:

[0115]

[0116] Among them, T target (t) is the target temperature, T'(t) is the furnace temperature after filtering at the current moment, and T'(t-1) is the furnace temperature after filtering at the previous moment. By calculating the furnace temperature change rate The system can reflect the dynamic change trend of furnace temperature. At the same time, the system also takes into account the input power change rate The impact on temperature is determined, and the temperature deviation ΔT(t) is used as a control factor. The temperature control algorithm's response coefficients β1, β2, and β3 dynamically adjust the contribution of each factor to ensure accurate temperature control. The weight parameters β1+β2+β3=1 are properly set to optimize the temperature control process and ensure stable operation of the furnace temperature within the target range.

[0117] Step 4: Power scheduling scheme P calculated according to step 3 opt (t) and temperature regulation scheme T opt (t), power distribution and temperature control are carried out through the intelligent power distribution module, and real-time control instructions are sent to the electric furnace control system to realize intelligent power supply control of the electric furnace.

[0118] In step 4, the system has obtained the power scheduling solution P through the innovative power regulation algorithm. opt (t) and temperature regulation scheme T opt (t). Next, the intelligent power distribution module distributes power to the system according to these plans. First, the system calculates the power demand P of each submodule based on the power demand and temperature demand of each submodule of the glass electric melting furnace (such as heater, furnace wall, temperature sensor, etc.) using an innovative load prediction algorithm. sub (t). Its calculation formula is as follows:

[0119]

[0120] Among them, P opt (t) is the power scheduling scheme, T opt (t) is the temperature adjustment scheme, T'(t) is the furnace temperature after filtering, Represents the normalized term of temperature error. The system adjusts the power demand based on this error term to compensate for temperature fluctuations. At the same time, the rate of change of furnace temperature It also serves as an adjustment factor to make the power distribution of each submodule more accurate.

[0121] After obtaining the power requirement P of each submodule sub After (t), the intelligent power distribution module dynamically adjusts the power distribution of each submodule using a load balancing algorithm. This load balancing algorithm rationally allocates power resources based on the overall system power and temperature requirements, ensuring that each submodule operates in a balanced load state, thereby optimizing overall energy efficiency. This process takes into account system load changes in real time and dynamically adjusts power distribution based on the actual operating status of the glass furnace. For example, during certain periods of time, if the furnace temperature is low, the system will increase the power output of the heater, and otherwise reduce it to ensure that the furnace temperature operates within the target range.

[0122] refer to Figure 2 The embodiment of the present invention provides an intelligent power supply control system for a glass electric melting furnace, comprising the following modules:

[0123] The data acquisition and preprocessing module is used to collect the input current, voltage and temperature data of the glass electric melting furnace in real time, and perform low-pass filtering and normalization on the collected data to generate preprocessed multi-dimensional data to provide accurate input for control decisions;

[0124] An intelligent control decision module is used to build a multi-input multi-output model based on pre-processed input current, voltage, and furnace temperature data. It uses innovative fuzzy control algorithms and innovative power regulation algorithms to jointly calculate target electric power and target temperature, thereby generating optimized power scheduling and temperature regulation plans.

[0125] The power execution and allocation module is used to dynamically allocate power to each sub-module of the glass electric melting furnace based on the optimized power scheduling and temperature regulation plans, using innovative load prediction and load balancing algorithms, to achieve intelligent and energy-efficient power supply control.

[0126] In the data acquisition and preprocessing module, this module is a key component of the intelligent power supply control system. It is mainly responsible for real-time collection of current, voltage and furnace temperature data of the glass electric melting furnace, and performing necessary processing on the collected raw data to ensure the accuracy and reliability of the subsequent control process.

[0127] The data acquisition submodule collects real-time data through sensors (such as current sensors, voltage sensors, and temperature sensors) installed at key locations of the glass electric melting furnace. Specifically, this submodule collects the current I per second. in (t), voltage V in (t) and furnace temperature T(t), ensuring that the acquisition frequency reaches above 100Hz to meet the needs of real-time control. To ensure the accuracy of data acquisition, this submodule uses high-precision sensors and multi-channel data acquisition equipment to ensure that data from all sensors are collected synchronously and without errors.

[0128] The data preprocessing submodule filters and normalizes the raw data. First, the collected current, voltage and furnace temperature data are low-pass filtered to remove high-frequency noise in the signal and improve data quality. The specific filtering method uses a low-pass filtering algorithm, through the convolution operation I' in (t) = I in (t)*H low-pass (t) Smoothing the input signal. Secondly, the data preprocessing module normalizes the filtered data to eliminate dimensional differences and bring the data to a uniform standard. Normalization ensures that current, voltage, and furnace temperature data are processed on a uniform scale, providing high-quality data support for subsequent control models.

[0129] In the intelligent control decision module, this module is the core part of the entire intelligent power supply control system, responsible for making decisions on power and temperature regulation based on the collected data and real-time system status.

[0130] The fuzzy control submodule combines the multi-input multi-output control model to generate the target electric power and target temperature according to the changing trends of the input current, voltage and temperature of the glass electric melting furnace. Specifically, this submodule uses the fuzzy logic control algorithm to generate fuzzy control rules by fuzzifying the deviation of current and voltage and the changing trend of temperature, and then outputs the target electric power P according to the rules. target (t) and target temperature T target(t). For example, if the current and voltage fluctuate greatly and the furnace temperature is low, the fuzzy control algorithm will adjust the electrical power and temperature set points to stabilize the furnace temperature in the optimal operating range.

[0131] The power and temperature regulation strategy submodule uses the target power and temperature generated by fuzzy control and an optimization algorithm to calculate an optimized regulation plan. Based on these target power and temperature, this submodule uses an iterative optimization algorithm to adjust the power and temperature control strategy. The regulation plan includes specific power output, heating mode, and furnace temperature adjustment strategies to achieve refined control of the electric furnace power supply system, ensuring optimal energy utilization and maintaining a stable temperature for the glass furnace, thereby improving production efficiency.

[0132] In the power execution and allocation module, this module is responsible for rationally allocating and scheduling the power resources of the glass electric melting furnace according to the optimized adjustment plan.

[0133] The dynamic power allocation submodule performs dynamic power allocation based on the power and temperature requirements of each sub-area in the system (such as the heating area, melting area, and furnace discharge area, etc.), as well as the optimized scheduling scheme calculated by the intelligent control decision module. Specifically, the power demand of each sub-area is dynamically adjusted based on the current load, temperature deviation, and power scheduling scheme of the area. For example, higher power is required in the heating area to maintain high temperature, while in the furnace discharge area, the system may reduce power to avoid overheating. Through dynamic power allocation, the submodule can accurately adjust the power distribution according to the specific needs of different areas to achieve energy efficiency optimization of the entire system.

[0134] The load prediction and adjustment submodule uses real-time temperature deviations and historical power trends to predict load changes for each submodule and dynamically adjust the power distribution plan. For example, by monitoring temperature changes in real time, it can predict the power demand of a submodule in the next moment, allowing the system to make adjustments in advance. This prediction function uses historical data analysis and temperature trends, combined with a model prediction algorithm, to pre-allocate power. This module effectively predicts load changes and adjusts power output in advance, thereby avoiding system overload and uneven power distribution, further improving the overall power supply efficiency of the system.

[0135] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions therein may be combined with each other.

[0136] Obviously, the embodiments described above are only some embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the accompanying drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present invention specification and drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. An intelligent power supply control method for a glass electric melting furnace, characterized in that: The following steps are involved: S1. According to the real-time working status of the glass electric melting furnace, collect the input current I of the electric melting furnace in (t), voltage V in (t) and furnace temperature data T(t), and filter and normalize them through the data preprocessing unit to obtain the processed input current I in '(t), voltage V in '(t) and furnace temperature T'(t); S2, the current I obtained according to step S1 in '(t), voltage V in '(t) and furnace temperature T'(t), by establishing a multi-input multi-output control model, combined with an innovative fuzzy control algorithm for power regulation, the target electric power P is calculated target (t) and target temperature T target (t); S3, the target electric power P obtained according to step S2 target (t) and target temperature T target (t), using innovative power regulation algorithm to generate optimized power scheduling plan P opt (t) and temperature regulation scheme T opt (t); S4, the power scheduling scheme P calculated according to step S3 opt (t) and temperature regulation scheme T opt (t), power distribution and temperature control are carried out through the intelligent power distribution module, and real-time control instructions are sent to the electric furnace control system to realize intelligent power supply control of the electric furnace.

2. The intelligent power supply control method for a glass electric melting furnace according to claim 1, characterized in that: The filtering method of the data preprocessing unit in step S1 includes: The input current I is filtered using a low-pass filter. in (t) and voltage signal V in (t) is filtered, and the formula is: I′ in (t)=I in (t)*H low-pass (t); V′ in (t)=V in (t)*H low-pass (t); T'(t)=T(t)*H low-pass (t); Among them, H low-pass (t) is the transfer function of the low-pass filter, * is the convolution operation, I' in (t) is the input current after filtering, V in '(t) is the voltage after filtering, and T'(t) is the furnace temperature after filtering.

3. The intelligent power supply control method for a glass electric melting furnace according to claim 1, characterized in that: The innovative fuzzy control algorithm in step S2 includes the following steps: S2(1), input variable calculation: ΔI(t)=I′ in (t)-I′ in (t-1); ΔV(t)=V′ in (t)-V′ in (t)-1); ΔT(t)=T'(t)-T'(t-1); Where ΔI(t) is the current deviation, ΔV(t) is the voltage deviation, and ΔT(t) is the temperature deviation; S2(2) Optimize the objective function: Through the innovative fuzzy control algorithm, the target electric power P is obtained. target (t) and target temperature T target (t), the calculation formula is as follows: P target (t)=η·(ω1·ΔI(t)+ω2·ΔV(t)); Where η is the power factor of the electric power system, which can be obtained by querying the system parameters of the glass electric melting furnace; T target (t)=ζ·ω3·ΔT(t); Among them, ζ is the temperature control response coefficient, which represents the sensitivity of temperature regulation to the temperature control system. It can be obtained by querying the system parameters of the glass electric melting furnace. ω1, ω2, and ω3 are weight factors, satisfying ω1+ω2+ω3=1.

4. The intelligent power supply control method for a glass electric melting furnace according to claim 1, characterized in that: In step S3, the power scheduling scheme P is calculated by the innovative power regulation algorithm. opt (t) and temperature regulation scheme T opt (t), the specific steps are as follows: S3(1) The target electric power P at the current moment has been obtained in step S2. target (t), and combined with the innovative power regulation algorithm to calculate the power scheduling solution P opt (t), the formula is as follows: in: P' in (t) is the input power after filtering, and the calculation formula is is the derivative of the target electric power with respect to time t; ΔI(t) is the current deviation; ΔV(t) is the voltage deviation; α1, α2, and α3 are dynamic scheduling weight parameters, and they all satisfy α1+α2+α3=1; S3(2), after obtaining the target temperature T target (t), combined with the current temperature state and the impact of input power on temperature, a temperature regulation scheme T is constructed. opt (t), the specific formula is as follows: in: T target (t) is the target temperature; T'(t) is the furnace temperature after filtering at time t; T'(t-1) is the furnace temperature after filtering at time t-1; is the rate of change of furnace temperature; is the rate of change of the filtered input power; ΔT(t) is the temperature deviation, calculated as ΔT(t) = T'(t) - T'(t-1); β1, β2, and β3 are response coefficients of the temperature control algorithm, and they all satisfy β1+β2+β3=1.

5. The intelligent power supply control method for a glass electric melting furnace according to claim 1, characterized in that: The intelligent power distribution module in step S4 is based on the power scheduling scheme P opt (t) and temperature regulation scheme T opt (t) performing power distribution, wherein the power distribution process includes: According to the power and temperature requirements of each part of the glass electric melting furnace, an innovative load prediction algorithm is used to calculate the power demand P of each submodule. sub (t), and dynamically adjust the power distribution of each submodule through the load balancing algorithm to optimize the overall energy efficiency of the system. The innovative load prediction algorithm is as follows: in: P opt (t) is the power scheduling scheme; T opt (t) is the temperature regulation scheme; T'(t) is the furnace temperature after filtering at time t; is the temperature error normalization term; is the furnace temperature change rate.

6. An intelligent power supply control system for a glass electric melting furnace, characterized in that: Includes the following modules: The data acquisition and preprocessing module is used to collect the input current, voltage and temperature data of the glass electric melting furnace in real time, and perform low-pass filtering and normalization on the collected data to generate preprocessed multi-dimensional data to provide accurate input for control decisions; An intelligent control decision module is used to build a multi-input multi-output model based on pre-processed input current, voltage, and furnace temperature data. It uses innovative fuzzy control algorithms and innovative power regulation algorithms to jointly calculate target electric power and target temperature, thereby generating optimized power scheduling and temperature regulation plans. The power execution and allocation module is used to dynamically allocate power to each sub-module of the glass electric melting furnace based on the optimized power scheduling and temperature regulation plans, using innovative load prediction and load balancing algorithms, to achieve intelligent and energy-efficient power supply control.

7. The intelligent power supply control system for a glass electric melting furnace according to claim 6, characterized in that: The data acquisition and preprocessing module includes: Data acquisition submodule: used to collect the input current, voltage and temperature data of the glass electric melting furnace in real time, ensuring that the acquired raw data has a high sampling frequency and accuracy; Data preprocessing submodule: used to filter and normalize the collected data to remove noise and unify the dimension, improve data availability, and provide high-quality data support for the input of subsequent control models.

8. The intelligent power supply control system for a glass electric melting furnace according to claim 6, characterized in that: The intelligent control decision module includes: Fuzzy control submodule: used to generate target electric power and target temperature based on a multi-input and multi-output control model, combining current, voltage and temperature change trends; Power and temperature regulation strategy submodule: used to calculate the optimized regulation scheme based on the target power and target temperature, thereby achieving fine control of the electric furnace power supply system.

9. The intelligent power supply control system for a glass electric melting furnace according to claim 6, characterized in that: The power execution and allocation module includes: Dynamic power allocation submodule: This module allocates power resources based on the power and temperature requirements of each sub-area and optimizes the scheduling scheme to achieve a balanced power supply across multiple areas. Load prediction and regulation submodule: used to predict the load changes of each submodule based on real-time temperature deviation and historical power change trends, and dynamically adjust the power distribution plan to optimize the overall power supply efficiency of the system.

Images