Energy consumption control method and system applied to annealing furnace

Abstract

The application discloses an energy consumption control method and system applied to an annealing furnace, relates to the technical field of annealing furnace control, and determines position information of a plurality of hot zones to construct a hot zone state matrix; a neighboring hot zone coupling strength model is constructed to calculate the coupling strength between each neighboring hot zone and construct a coupling strength standard matrix; training samples are constructed and a first compensation factor formula is fitted based on a least square method; the neighboring hot zone set of each target hot zone is counted, the thermal disturbance influence weight is calculated according to the coupling strength, the temperature change value of the neighboring hot zone is collected, and a second compensation factor is constructed; real-time operation parameters of the annealing furnace are acquired and input into a temperature prediction model, the first compensation factor and the second compensation factor are calculated, and the temperature control set value executed by the central control system is calculated, so that the energy-saving level, the temperature control stability and the process adaptation capability of the annealing furnace system are improved.

Description

Technical Field

[0001] This invention relates to the field of annealing furnace control technology, specifically to an energy consumption control method and system for annealing furnaces. Background Technology

[0002] In modern industrial heat treatment processes, annealing furnaces are core equipment. Currently, the mainstream temperature control systems for annealing furnaces generally adopt PID control strategies based on single-hot-zone feedback or fixed heating curves set based on experience. This mode ignores the thermal coupling relationship between the hot zones inside the furnace and cannot coordinate control according to the overall system status, resulting in low thermal energy utilization, slow temperature response, and high energy consumption.

[0003] In addition, the invention patent application with Chinese patent publication number CN104962727A states that when the deviation between the actual strip temperature obtained from the furnace working condition information and the production line status information and the set target strip temperature exceeds the set range, the furnace temperature value of the heating section is reset and a furnace control message is sent to the basic automation equipment to control the furnace temperature. Although this method takes into account the thermal coupling relationship between the various hot zones inside the furnace, it has a lag and does not take into account the interference of adjacent hot zones.

[0004] Therefore, there is a need for a method that can combine the state of the hot zone to extract and predict the energy consumption control of the annealing furnace, so as to achieve accurate temperature prediction and correction under complex thermal disturbance conditions, and improve the energy efficiency, adaptability and robustness of the overall control system through systematic data modeling, thereby achieving energy saving. Summary of the Invention

[0005] The purpose of this invention is to provide an energy consumption control method and system for annealing furnaces to solve the problems raised in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an energy consumption control method applied to an annealing furnace, the method comprising:

[0007] Step S100: Obtain the internal structure diagram of the annealing furnace, determine and mark the location information of several hot zones, and arrange multiple sensors inside each hot zone; collect the operating parameters of each hot zone according to the preset acquisition time points, and construct the hot zone state matrix.

[0008] Step S200: Based on the thermal zone state matrix and the spatial arrangement of the thermal zones, construct a coupling strength model for adjacent thermal zones, calculate the coupling strength between each adjacent thermal zone, and construct a standard coupling strength matrix;

[0009] Step S300: Compare the predicted temperature and actual temperature of each hot zone in the historical operation record, calculate the average temperature control deviation, combine the average difference and variance of the coupling strength of adjacent hot zones, construct training samples, and fit the formula of the first compensation factor based on the least squares method.

[0010] Step S400: Calculate the set of adjacent hot zones for each target hot zone, calculate the thermal disturbance influence weight based on the coupling strength, collect the temperature change values ​​of adjacent hot zones, and construct the second compensation factor;

[0011] Step S500: Obtain the real-time operating parameters of the annealing furnace and input them into the temperature prediction model to calculate the real-time predicted temperature. Combine the real-time temperature control deviation average value, the real-time coupling strength average difference, and the real-time variance parameter, and input them into the formulas for the first compensation factor and the second compensation factor respectively to calculate the first compensation factor and the second compensation factor. Calculate the temperature control setpoint executed by the central control system, send the temperature control setpoint to the annealing furnace controller through the command interface, and adjust the heater power output of the corresponding hot zone.

[0012] Furthermore, step S100 includes:

[0013] Step S101: Obtain the internal structure diagram of the annealing furnace, determine and mark the location information of each hot zone according to the internal structure diagram, arrange several sensors inside each hot zone, and monitor the operating parameters of each hot zone according to the preset acquisition time points;

[0014] Step S102: Obtain the historical operation record for each hot zone, collect the operation parameters corresponding to each collection time point in the historical operation record, obtain the temperature of the heated object, and calculate the temperature difference between the collected time point and the previous collected time point. The power feedback value at the acquisition time point is calculated using the following formula:

[0015] ;

[0016] Where A1 represents the power feedback value, D represents the material mass, E represents the IoT specific heat capacity, and y represents the time difference between the current acquisition time point and the previous acquisition time point. The power command value at the acquisition time point is calculated according to the following formula:

[0017] ;

[0018] Where A2 represents the power command value, B represents the average current between the current sampling point and the previous sampling point, and C represents the average voltage between the current sampling point and the previous sampling point; the load status at the sampling point is calculated according to the following formula:

[0019] ;

[0020] Where A represents the load state at the acquisition time point, F is the temperature monitored at the acquisition time point, and the temperature and load state are combined to construct the thermal zone state variable S=(A, F).

[0021] Step S103: Collect the state variables generated by each hot zone at multiple acquisition time points to form a hot zone state matrix containing time series, and upload and store the state matrix to the central control system.

[0022] Step S104: Obtain the historical thermal zone state matrix in the central control system. Use the load state sequence and temperature of the historical thermal zone state matrix as training data. Construct a time series model for temperature prediction, F, through a sliding window regression model. t =f(A t-n A t-n+1 A t The time-series prediction model takes the load state at multiple consecutive sampling time points as input and the temperature at the t-th sampling time point as output, where F t Let A be the temperature at the t-th sampling time point. t-n A t-n+1 A t These represent the load status at the tn, t-n+1, ​​..., t-th data collection time points, respectively, where n represents the window length;

[0023] Dynamic modeling and structured representation of hot zone states were achieved. State variables were constructed by combining load state and temperature, enabling the system to accurately perceive the operating state of each hot zone.

[0024] Introducing a sliding window prediction model can accurately capture the temporal correlation between load status and temperature changes. Compared with traditional prediction methods based on single points or empirical rules, it improves the accuracy of temperature prediction and provides data support for subsequent energy consumption optimization and control.

[0025] Constructing a hot zone state matrix and uploading it to the central system is beneficial for realizing distributed sensing and centralized intelligent control, and provides a data foundation for subsequent coupled modeling, compensation control and other steps.

[0026] Model data-driven, avoiding reliance on manual settings or experience-based adjustments, and possessing excellent scalability and adaptability, it is suitable for deployment and application of various annealing furnace equipment of different specifications.

[0027] Furthermore, step S200 includes:

[0028] Step S201: Based on the historical hot zone state matrix of step S104, and combined with the spatial arrangement relationship of each hot zone in the annealing furnace, determine the coupling relationship set of adjacent hot zones, and extract the temperature and load state of each hot zone in the adjacent hot zones as the input feature set of the coupling strength model.

[0029] Step S202: For each group of adjacent hot zones, based on temperature and load conditions, construct a coupling strength model and calculate the coupling strength between adjacent hot zones. The calculation formula for the coupling strength model is as follows:

[0030] ;

[0031] Among them, G 12 F1 and F2 represent the coupling strength of hot zone 2 to hot zone 1, respectively; A1 and A2 represent the temperatures of adjacent hot zones 1 and 2, respectively; e1 and e2 represent positive constants to avoid division by zero error; and a1 and a2 represent the weights of temperature and load state, respectively.

[0032] Step S203: Summarize the coupling strength of each adjacent thermal zone and calculate the average coupling strength to construct a standard matrix of coupling strength between adjacent thermal zones. The standard matrix of coupling strength is represented as follows:

[0033] ;

[0034] Where H represents the standard matrix of coupling strength, and G ij The coupling strength is represented by the average value of the coupling strength between hot zone j and hot zone i, and N represents the total number of hot zones. The diagonal elements in the standard coupling strength matrix are set to 0, and the elements of non-adjacent hot zones are 0.

[0035] The standard coupling strength matrix is ​​an N×N sparse matrix, where the diagonal elements are always set to 0, indicating that the hot zone has no coupling effect on itself; the coupling strength between non-adjacent hot zones is recorded as 0, and only the non-zero coupling values ​​of hot zones with spatial adjacency are retained as the basic parameter table for subsequent compensation control and disturbance assessment, which is used to support the fine power adjustment and temperature control setting optimization of hot zones.

[0036] It achieves quantitative modeling of the coupling relationship between hot zones, no longer relying on manual experience to determine the relationship, but calculating the coupling strength through temperature and load differences, thus improving the objectivity and adaptability of the model;

[0037] The introduction of a standard coupling strength matrix effectively supports the assessment and coordinated control of thermal disturbances, providing highly reliable basic data support for subsequent dual compensation factor modeling.

[0038] Coupled modeling fully considers the spatial layout characteristics of the actual annealing furnace, and establishes dynamic coupling relationships only for adjacent hot zones to avoid redundant calculations and misleading interference, thereby improving control accuracy and response efficiency.

[0039] The coupling formula has a clear structure and the physical meaning of the parameters is clear. It is easy to calibrate and deploy according to the actual equipment parameters and has good industrial implementation capability and system portability.

[0040] By characterizing the thermal perturbation path using a sparse coupling matrix, a modeling transition from "local thermal control" to "global coordination" is achieved, providing a theoretical basis for efficient collaborative temperature control across multiple thermal zones.

[0041] Furthermore, step S300 includes:

[0042] Step S301: Set a training period of several consecutive days, obtain the operation record of the annealing furnace, and input the operation parameters collected at each collection time point in a certain operation record into the time series model for temperature prediction to obtain the predicted temperature corresponding to each collection time point.

[0043] Step S302: Obtain the temperature and load state of each hot zone in the annealing furnace at different sampling time points, obtain the hot zone state matrix of each hot zone, calculate the coupling strength of each adjacent hot zone based on the coupling strength model, generate the coupling strength matrix, subtract the coupling strength matrix from the standard coupling strength matrix, summarize the coupling strength difference at each sampling time point, and calculate the average difference and variance of the coupling strength.

[0044] Step S303: Summarize the predicted temperature and actual temperature of a certain hot zone at each data collection time point, and calculate the average temperature control deviation using the following formula:

[0045]

[0046] Where Fp represents the average temperature control deviation, and F' d and F d Let represent the predicted temperature and temperature corresponding to the d-th data collection time point, respectively, and b represent the total number of data collection time points;

[0047] Step S304: Obtain the temperature correction value applied by the central control system during the control process of each hot zone at different sampling time points, summarize the temperature correction values ​​of all sampling time points, calculate the average temperature correction value and set it as the first compensation factor;

[0048] Step S305: Combine the average difference and variance of the coupling strength of a certain adjacent hot zone with the average temperature control deviation of the target hot zone of the adjacent hot zone to construct a training sample of the hot zone compensation factor. Summarize the training samples of the first compensation factor corresponding to all operation records of the hot zone. Using the training samples as input and the first compensation factor as output, establish the formula of the first compensation factor as follows:

[0049] ;

[0050] Where Q1 represents the first compensation factor, L1 and L2 represent the average difference and variance of coupling strength, respectively, k1, k2, and k3 represent the weights of the average difference, variance, and average temperature control deviation of coupling strength, respectively, and k4 represents the deviation value of the first compensation factor formula. The least squares method is used to fit the training samples to obtain the values ​​of k1, k2, k3, and k4, and these values ​​are input into the first compensation factor formula to establish the final first compensation factor formula.

[0051] A quantitative mapping relationship between temperature control deviation and coupling disturbance was established. By co-modeling coupling strength deviation and actual temperature control deviation, the impact of coupling disturbance on the control effect of the target hot zone was accurately evaluated.

[0052] An adaptive compensation adjustment modeling mechanism has been implemented, which no longer relies on fixed empirical coefficients for parameter tuning, thereby improving the adaptability and universality of the compensation factor.

[0053] The least squares fitting technique is used to ensure strong model convergence and interpretability. The weight parameters have physical meaning, which facilitates industrial deployment and subsequent updates and maintenance.

[0054] Based on historical operational data of hot zones, it is trained and has personalized modeling capabilities, which can establish differentiated compensation strategies for different hot zones and improve the accuracy of energy efficiency control.

[0055] The introduction of the first compensation factor effectively reduces the deviation between temperature prediction and actual control, further enhancing the system's dynamic response capability and stability in strongly coupled, multi-disturbance scenarios.

[0056] Furthermore, step S400 includes:

[0057] Step S401: Collect all neighboring hot zones of a target hot zone. In the standard coupling strength matrix, collect the coupling strength of each neighboring hot zone to the target hot zone. Calculate the thermal disturbance influence weight of the neighboring hot zones on the target hot zone according to the following formula:

[0058] ;

[0059] Where, q rG represents the weight of the thermal disturbance influence of adjacent hot zones r on the target hot zone g. rg G represents the coupling strength between adjacent hot zones r and the target hot zone g. ng denoted as the coupling strength between adjacent hot zones n and the target hot zone g, and m represents the total number of adjacent hot zones;

[0060] Step S402: Obtain the temperature change value of each adjacent hot zone between two consecutive acquisition time points, and calculate the second compensation factor of the target hot zone according to the following second compensation factor formula:

[0061] ;

[0062] Where Q2 represents the second compensation factor, q ng This represents the weight of the thermal disturbance influence of adjacent hot zones n on the target hot zone g. This is expressed as the temperature change value of the adjacent thermal zone n;

[0063] The second compensation factor dynamically reflects the temperature fluctuation trend of adjacent hot zones, and has the characteristics of strong real-time performance and fast response. It improves the system's adaptability to sudden coupling disturbances. The thermal disturbance weight is derived based on the standard coupling strength matrix. The weight allocation is reasonable and matches the actual coupling degree between hot zones, ensuring that the calculation results have engineering significance.

[0064] The first compensation factor is based on historical statistical modeling, while the second compensation factor is based on real-time disturbance trend modeling. The two complement each other to construct a complete disturbance perception and compensation framework. The thermal disturbance weight is extracted based on the coupling matrix, which is applicable to any thermal zone arrangement structure and scale, and has good portability and scalability.

[0065] In industrial environments characterized by multiple hot zones, strong coupling, and frequent disturbances, the second compensation factor significantly reduces temperature control error fluctuations, effectively improving the stability and energy efficiency of the annealing furnace operation.

[0066] Furthermore, step S500 includes:

[0067] Step S501: Obtain the real-time operating parameters of the annealing furnace, input them into the time series model for temperature prediction, calculate the real-time predicted temperature corresponding to each acquisition time point, collect the real-time temperature at the acquisition time point, calculate the average real-time temperature control deviation, calculate the real-time average difference and real-time variance of the coupling strength, and input them into the first compensation factor formula to calculate the first compensation factor.

[0068] Step S502: Obtain the real-time temperature change value of each adjacent hot zone between two consecutive acquisition time points, and input it into the second compensation factor formula to calculate the second compensation factor;

[0069] Step S503: Obtain the preset target temperature setpoint F from the central control system. s The temperature setpoint executed by the central control system is calculated according to the following formula:

[0070] ;

[0071] Among them, F' s This represents the temperature setpoint executed by the central control system. The central control system executes the temperature setpoint and sends it to the annealing furnace controller through the temperature control command interface. The heater power output of the corresponding hot zone is adjusted according to the temperature setpoint.

[0072] A dynamic adaptive adjustment mechanism for control commands has been implemented. The set temperature is calculated based on a three-dimensional fusion of real-time prediction, historical deviation and disturbance trend, breaking through the traditional constant set value control method and improving the control sensitivity.

[0073] By integrating two types of compensation factors to cover multi-scale disturbance response, the first compensation factor is oriented towards statistical deviation modeling, while the second compensation factor is oriented towards disturbance trend modeling. The two work together to enable the setpoint to dynamically adapt to the system operating state.

[0074] Reduce steady-state deviation and dynamic overshoot caused by coupling disturbances in the temperature control system, improve temperature control stability and response speed, and significantly optimize the temperature control curve;

[0075] Enhance the system's anti-interference capability in highly complex thermal fields, making it suitable for industrial annealing scenarios with multiple hot zones and high-frequency disturbances, thereby improving product consistency and process stability;

[0076] This enables the transformation of temperature control from "setpoint-driven" to "model-driven," and has good industrial applicability and engineering practical value.

[0077] To better implement the above method, an energy consumption control system for annealing furnaces is also proposed. The system includes a hot zone state module, a coupling strength module, a first compensation factor module, a second compensation factor module, and a real-time control module.

[0078] Hot Zone Status Module: Acquires the internal structure diagram of the annealing furnace, determines and marks the location information of several hot zones, and arranges multiple sensors inside each hot zone; collects the operating parameters of each hot zone according to the preset acquisition time points, and constructs the hot zone status matrix;

[0079] Coupling strength module: Based on the thermal zone state matrix and the spatial arrangement of the thermal zones, construct a coupling strength model of adjacent thermal zones, calculate the coupling strength between each adjacent thermal zone, and construct a standard coupling strength matrix;

[0080] First compensation factor module: Compare the predicted temperature and actual temperature of each hot zone in the historical operation record, calculate the average temperature control deviation, combine the average difference and variance of the coupling strength of adjacent hot zones, construct training samples, and fit the first compensation factor formula based on the least squares method.

[0081] The second compensation factor module: statistically analyzes the set of adjacent hot zones for each target hot zone, calculates the thermal disturbance influence weight based on the coupling strength, collects the temperature change values ​​of adjacent hot zones, and constructs the second compensation factor;

[0082] Real-time control module: acquires the real-time operating parameters of the annealing furnace and inputs them into the temperature prediction model, calculates the real-time predicted temperature, and combines the real-time average temperature control deviation, the real-time average difference of coupling strength, and the real-time variance parameter, respectively inputting them into the formulas for the first compensation factor and the second compensation factor to calculate the first compensation factor and the second compensation factor. It also calculates the temperature control setpoint executed by the central control system, sends the temperature control setpoint to the annealing furnace controller through the command interface, and adjusts the heater power output of the corresponding hot zone.

[0083] Furthermore, the thermal zone state module includes thermal zone state variable units and temperature prediction model units:

[0084] Hot Zone State Variable Unit: Obtain the internal structure diagram of the annealing furnace, determine and mark the location information of each hot zone according to the internal structure diagram, arrange several sensors inside each hot zone, and monitor the operating parameters of each hot zone according to preset acquisition time points; obtain the historical operation record of each hot zone, collect the operating parameters corresponding to each acquisition time point in the historical operation record, calculate the load state at the acquisition time point, and combine the temperature and load state to construct the hot zone state variable;

[0085] Temperature prediction model unit: It collects the state variables generated by each hot zone at multiple sampling time points to form a hot zone state matrix containing time series, and uploads and stores the state matrix to the central control system; it obtains the historical hot zone state matrix in the central control system, uses the load state sequence and temperature of the historical hot zone state matrix as training data, and constructs a time series model for temperature prediction through a sliding window regression model. The time series prediction model takes the load state at multiple consecutive sampling time points as input and the temperature at the sampling time points as output.

[0086] Furthermore, the coupling strength module includes units for calculating coupling strength and units for establishing the standard coupling strength matrix:

[0087] Calculate the coupling strength unit: Based on the historical hot zone state matrix and combined with the spatial arrangement of each hot zone in the annealing furnace, determine the coupling relationship set of adjacent hot zones, extract the temperature and load state of each hot zone in the adjacent hot zones as the input feature set of the coupling strength model; for each group of adjacent hot zones, construct the coupling strength model based on the temperature and load state, and calculate the coupling strength of the adjacent hot zones.

[0088] Establish a standard matrix unit for coupling strength: summarize the coupling strength of each adjacent thermal zone and calculate the average value of the coupling strength to construct a standard matrix of coupling strength between adjacent thermal zones. The diagonal elements of the standard matrix are set to 0, and the elements of non-adjacent thermal zones are set to 0.

[0089] Furthermore, the first compensation factor module includes a unit for constructing training samples and a unit for establishing the first compensation factor formula:

[0090] Constructing training sample units: A training period of several consecutive days is preset. Operating records of the annealing furnace are acquired. In a given operating record, the operating parameters collected at each sampling time point are input into the time-series model for temperature prediction to obtain the predicted temperature corresponding to each sampling time point. The temperature and load state of each hot zone in the annealing furnace at different sampling time points are obtained, resulting in a hot zone state matrix for each hot zone. Based on the coupling strength model, the coupling strength of each adjacent hot zone is calculated, generating a coupling strength matrix. The coupling strength matrix is ​​then subtracted from the standard coupling strength matrix to obtain the result for each sampling time point. The coupling strength differences at each point are summarized to calculate the average coupling strength difference and variance. The predicted temperature and temperature corresponding to a certain hot zone at each sampling time point are summarized to calculate the average temperature control deviation. The temperature correction value applied by the central control system during the control process of each hot zone at different sampling time points is obtained, the temperature correction values ​​of all sampling time points are summarized, the average temperature correction value is calculated and set as the first compensation factor. The average coupling strength difference and variance of a certain adjacent hot zone are combined with the average temperature control deviation of the target hot zone of the adjacent hot zone to construct the training sample of the hot zone compensation factor.

[0091] Establish the first compensation factor formula unit: Summarize the training samples of the first compensation factor corresponding to all operation records of the hot zone, use the training samples as input and the first compensation factor as output to establish the first compensation factor formula, perform least squares fitting based on the training samples to obtain the values ​​of k1, k2, k3 and k4, and input them into the first compensation factor formula to establish the final first compensation factor formula.

[0092] Compared with the prior art, the beneficial effects of the present invention are: by constructing a thermal zone coupling strength model and a standard coupling matrix, the spatial thermal disturbance relationship between each thermal zone is clearly characterized, avoiding the neglect or empirical estimation of thermal coupling in traditional temperature control methods, and enhancing the integrity and synergy of multi-thermal zone temperature control regulation;

[0093] The first compensation factor is based on historical temperature control deviation and coupled disturbance modeling, which effectively corrects the model prediction error. The second compensation factor responds to the temperature changes of adjacent hot zones and quickly compensates for sudden disturbances. The combination of the two takes into account both "long-term trends" and "short-term disturbances", which improves control accuracy and steady-state capability.

[0094] A load-state driven sliding window prediction model is adopted to predict the temperature trend before control, overcoming the time lag problem caused by traditional temperature control methods that rely on static setting or feedback adjustment, and responding to heat load changes in advance.

[0095] Real-time calculation of temperature control deviation, coupling disturbance, and compensation value, and integration into the control setpoint, realizes the intelligent decision-making capability of the central control system, reduces the burden of manual intervention and parameter adjustment, and enables precise temperature control and energy consumption control, reducing overheating, underheating, and repeated heating; it improves the consistency and pass rate of product heat treatment, and indirectly brings about a reduction in production costs and energy savings. Attached Figure Description

[0096] Figure 1 This is a schematic flowchart of an energy consumption control method for an annealing furnace according to the present invention;

[0097] Figure 2 This is a schematic diagram of the energy consumption control system for an annealing furnace according to the present invention. Detailed Implementation

[0098] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0099] Please see Figure 1 The present invention provides a technical solution: an energy consumption control method for annealing furnaces, the method comprising:

[0100] Step S100: Obtain the internal structure diagram of the annealing furnace, determine and mark the location information of several hot zones, and arrange multiple sensors inside each hot zone; collect the operating parameters of each hot zone according to the preset acquisition time points, and construct the hot zone state matrix.

[0101] Step S100 includes:

[0102] Step S101: Obtain the internal structure diagram of the annealing furnace, determine and mark the location information of each hot zone according to the internal structure diagram, arrange several sensors inside each hot zone, and monitor the operating parameters of each hot zone according to the preset acquisition time points;

[0103] Step S102: Obtain the historical operation record for each hot zone, collect the operation parameters corresponding to each collection time point in the historical operation record, obtain the temperature of the heated object, and calculate the temperature difference between the collected time point and the previous collected time point. The power feedback value at the acquisition time point is calculated using the following formula:

[0104] ;

[0105] Where A1 represents the power feedback value, D represents the material mass, E represents the IoT specific heat capacity, and y represents the time difference between the current acquisition time point and the previous acquisition time point. The power command value at the acquisition time point is calculated according to the following formula:

[0106] ;

[0107] Where A2 represents the power command value, B represents the average current between the current sampling point and the previous sampling point, and C represents the average voltage between the current sampling point and the previous sampling point; the load status at the sampling point is calculated according to the following formula:

[0108] ;

[0109] Where A represents the load state at the acquisition time point, F is the temperature monitored at the acquisition time point, and the temperature and load state are combined to construct the thermal zone state variable S=(A, F).

[0110] Step S103: Collect the state variables generated by each hot zone at multiple acquisition time points to form a hot zone state matrix containing time series, and upload and store the state matrix to the central control system.

[0111] Step S104: Obtain the historical thermal zone state matrix in the central control system. Use the load state sequence and temperature of the historical thermal zone state matrix as training data. Construct a time series model for temperature prediction, F, through a sliding window regression model. t =f(A t-n A t-n+1 A t The time-series prediction model takes the load state at multiple consecutive sampling time points as input and the temperature at the t-th sampling time point as output, where Ft Let A be the temperature at the t-th sampling time point. t-n A t-n+1 A t These represent the load status at the tn, t-n+1, ​​..., t-th data collection time points, respectively, where n represents the window length;

[0112] For example, taking an industrial annealing furnace as an example, the furnace body is divided into 3 hot zones (Z1, Z2, Z3). Each hot zone is equipped with sensors to collect the following operating parameters: current (unit: A), voltage (unit: V), material mass (unit: kg), specific heat capacity (unit: kJ / kg·℃), and real-time temperature (unit: ℃). The collection cycle is once every 1 minute. This example shows the data records for 5 consecutive collection time points, i.e. t1-t5.

[0113] The data records for five consecutive acquisition time points in hot zone Z2 are shown in Table 1:

[0114] Table 1

[0115]

[0116] The load status of the Z2 hot zone at each sampling point is calculated as follows: t2=87.76%, t3=94.79%, t4=98.38%, t5=99.18%.

[0117] Step S200: Based on the thermal zone state matrix and the spatial arrangement of the thermal zones, construct a coupling strength model for adjacent thermal zones, calculate the coupling strength between each adjacent thermal zone, and construct a standard coupling strength matrix;

[0118] Step S200 includes:

[0119] Step S201: Based on the historical hot zone state matrix of step S104, and combined with the spatial arrangement relationship of each hot zone in the annealing furnace, determine the coupling relationship set of adjacent hot zones, and extract the temperature and load state of each hot zone in the adjacent hot zones as the input feature set of the coupling strength model.

[0120] Step S202: For each group of adjacent hot zones, based on temperature and load conditions, construct a coupling strength model and calculate the coupling strength between adjacent hot zones. The calculation formula for the coupling strength model is as follows:

[0121] ;

[0122] Among them, G 12F1 and F2 represent the coupling strength of hot zone 2 to hot zone 1, respectively; A1 and A2 represent the temperatures of adjacent hot zones 1 and 2, respectively; e1 and e2 represent positive constants to avoid division by zero error; and a1 and a2 represent the weights of temperature and load state, respectively.

[0123] Step S203: Summarize the coupling strength of each adjacent thermal zone and calculate the average coupling strength to construct a standard matrix of coupling strength between adjacent thermal zones. The standard matrix of coupling strength is represented as follows:

[0124] ;

[0125] Where H represents the standard matrix of coupling strength, and G ij The coupling strength is represented by the average value of the coupling strength between hot zone j and hot zone i, and N represents the total number of hot zones. The diagonal elements in the standard coupling strength matrix are set to 0, and the elements of non-adjacent hot zones are 0.

[0126] For example, according to the thermal zone state matrix, at time t3, the data for the three thermal zones (Z1, Z2, Z3) are as follows: Z1 temperature is 715°C, load status is 77.76%; Z2 temperature is 730°C, load status is 94.79%; Z3 temperature is 735°C, load status is 100.00%.

[0127] According to the furnace body arrangement, the adjacent pairs are (Z1,Z2),(Z2,Z1),(Z2,Z3),(Z3,Z2);

[0128] G is calculated based on the coupling strength model. 12 (Z1←Z2) = 0.5243, G 21 (Z2←Z1) = 0.3660, G 23 (Z2←Z3) = 0.4799, G 32 (Z3←Z2) = 0.5213;

[0129] The average coupling strength of each adjacent thermal zone was calculated, and a 3×3 standard coupling matrix was constructed according to the thermal zone numbering order Z1→Z2→Z3:

[0130] .

[0131] Step S300: Compare the predicted temperature and actual temperature of each hot zone in the historical operation record, calculate the average temperature control deviation, combine the average difference and variance of the coupling strength of adjacent hot zones, construct training samples, and fit the formula of the first compensation factor based on the least squares method.

[0132] Step S300 includes:

[0133] Step S301: Set a training period of several consecutive days, obtain the operation record of the annealing furnace, and input the operation parameters collected at each collection time point in a certain operation record into the time series model for temperature prediction to obtain the predicted temperature corresponding to each collection time point.

[0134] Step S302: Obtain the temperature and load state of each hot zone in the annealing furnace at different sampling time points, obtain the hot zone state matrix of each hot zone, calculate the coupling strength of each adjacent hot zone based on the coupling strength model, generate the coupling strength matrix, subtract the coupling strength matrix from the standard coupling strength matrix, summarize the coupling strength difference at each sampling time point, and calculate the average difference and variance of the coupling strength.

[0135] Step S303: Summarize the predicted temperature and actual temperature of a certain hot zone at each data collection time point, and calculate the average temperature control deviation using the following formula:

[0136]

[0137] Where Fp represents the average temperature control deviation, and F' d and F d Let represent the predicted temperature and temperature corresponding to the d-th data collection time point, respectively, and b represent the total number of data collection time points;

[0138] Step S304: Obtain the temperature correction value applied by the central control system during the control process of each hot zone at different sampling time points, summarize the temperature correction values ​​of all sampling time points, calculate the average temperature correction value and set it as the first compensation factor;

[0139] Step S305: Combine the average difference and variance of the coupling strength of a certain adjacent hot zone with the average temperature control deviation of the target hot zone of the adjacent hot zone to construct a training sample of the hot zone compensation factor. Summarize the training samples of the first compensation factor corresponding to all operation records of the hot zone. Using the training samples as input and the first compensation factor as output, establish the formula of the first compensation factor as follows:

[0140] ;

[0141] Where Q1 represents the first compensation factor, L1 and L2 represent the average difference and variance of coupling strength, respectively, k1, k2, and k3 represent the weights of the average difference, variance, and average temperature control deviation of coupling strength, respectively, and k4 represents the deviation value of the first compensation factor formula. The least squares method is used to fit the training samples to obtain the values ​​of k1, k2, k3, and k4, and these values ​​are input into the first compensation factor formula to establish the final first compensation factor formula.

[0142] For example, set the data for 3 consecutive days as the training period, sample 5 time points each day, for a total of 15 sample data points, and the sliding window length is 3;

[0143] Taking the 5th time point on the 3rd day of the Z2 hot zone as an example: the load status in the sliding window was 92.06%, 94.03%, and 94.67% respectively, the predicted temperature was 739.5, and the actual measured temperature was 738.

[0144] The states of Z1, Z2, and Z3 at the 5th time point on the 3rd day are shown in Table 2:

[0145] Table 2

[0146]

[0147] G was calculated 21 (Z2←Z1)=0.4991, G 23 (Z2←Z3) = 0.6839, the average value is 0.5915, the corresponding standard coupling matrix value is 0.4087, and the coupling strength difference is 0.1828;

[0148] The following data is used as a set of training samples, as shown in Table 3:

[0149] Table 3

[0150]

[0151] The least squares method was used to fit multiple sets of running data, and the fitting coefficients k1, k2, k3, and k4 were 12, 20, 0.6, and 0.05, respectively.

[0152] Step S400: Calculate the set of adjacent hot zones for each target hot zone, calculate the thermal disturbance influence weight based on the coupling strength, collect the temperature change values ​​of adjacent hot zones, and construct the second compensation factor;

[0153] Step S400 includes:

[0154] Step S401: Collect all neighboring hot zones of a target hot zone. In the standard coupling strength matrix, collect the coupling strength of each neighboring hot zone to the target hot zone. Calculate the thermal disturbance influence weight of the neighboring hot zones on the target hot zone according to the following formula:

[0155] ;

[0156] Where, q r G represents the weight of the thermal disturbance influence of adjacent hot zones r on the target hot zone g. rg G represents the coupling strength between adjacent hot zones r and the target hot zone g. ngdenoted as the coupling strength between adjacent hot zones n and the target hot zone g, and m represents the total number of adjacent hot zones;

[0157] Step S402: Obtain the temperature change value of each adjacent hot zone between two consecutive acquisition time points, and calculate the second compensation factor of the target hot zone according to the following second compensation factor formula:

[0158] ;

[0159] Where Q2 represents the second compensation factor, q ng This represents the weight of the thermal disturbance influence of adjacent hot zones n on the target hot zone g. This is expressed as the temperature change value of the adjacent thermal zone n;

[0160] For example, G 21 The standard coupling value for (Z2←Z1) is 0.3353, G 23 The standard coupling value of (Z2←Z3) is 0.4821, and the calculated thermal disturbance influence weights are 0.4103 and 0.5897, respectively.

[0161] Step S500: Obtain the real-time operating parameters of the annealing furnace and input them into the temperature prediction model to calculate the real-time predicted temperature. Combine the real-time temperature control deviation average value, the real-time coupling strength average difference, and the real-time variance parameter, and input them into the formulas for the first compensation factor and the second compensation factor respectively to calculate the first compensation factor and the second compensation factor. Calculate the temperature control setpoint executed by the central control system, send the temperature control setpoint to the annealing furnace controller through the command interface, and adjust the heater power output of the corresponding hot zone.

[0162] Step S500 includes:

[0163] Step S501: Obtain the real-time operating parameters of the annealing furnace, input them into the time series model for temperature prediction, calculate the real-time predicted temperature corresponding to each acquisition time point, collect the real-time temperature at the acquisition time point, calculate the average real-time temperature control deviation, calculate the real-time average difference and real-time variance of the coupling strength, and input them into the first compensation factor formula to calculate the first compensation factor.

[0164] Step S502: Obtain the real-time temperature change value of each adjacent hot zone between two consecutive acquisition time points, and input it into the second compensation factor formula to calculate the second compensation factor;

[0165] Step S503: Obtain the preset target temperature setpoint F from the central control system. s The temperature setpoint executed by the central control system is calculated according to the following formula:

[0166] ;

[0167] Among them, F' s This represents the temperature setpoint executed by the central control system. The central control system executes the temperature setpoint and sends it to the annealing furnace controller through the temperature control command interface. The heater power output of the corresponding hot zone is adjusted according to the temperature setpoint.

[0168] For example, the real-time data for Z2 is shown in Table 4:

[0169] Table 4

[0170]

[0171] The calculated real-time temperature control deviation is 2.5.

[0172] Assume that at time t, the temperature of adjacent hot zone Z1 is 716, and the load condition is 92.93%; the temperature of adjacent hot zone Z3 is 745, and the load condition is 45.85%.

[0173] The calculated coupling strengths are 0.5072 and 0.6761, respectively. The average real-time coupling strength is 0.5917, the standard coupling matrix value is 0.4087, the average difference is 0.183, the variance is 0.0406, and the first compensation factor is calculated to be 3.833 according to the first compensation factor formula.

[0174] The temperature change of the adjacent hot zone Z1 is +2; the temperature change of the adjacent hot zone Z3 is +4. The calculated second compensation factor is 3.1794. The preset target temperature setting is 740, so the execution temperature setting is 747.01. The central control system sends 747.01 to the hot zone Z2 controller through the temperature control command interface. The controller dynamically adjusts the heater output power according to this temperature setting.

[0175] To better implement the above method, an energy consumption control system for annealing furnaces is also proposed. The system includes a hot zone state module, a coupling strength module, a first compensation factor module, a second compensation factor module, and a real-time control module.

[0176] Hot Zone Status Module: Acquires the internal structure diagram of the annealing furnace, determines and marks the location information of several hot zones, and arranges multiple sensors inside each hot zone; collects the operating parameters of each hot zone according to the preset acquisition time points, and constructs the hot zone status matrix;

[0177] The hot zone state module includes a hot zone state variable unit and a temperature prediction model unit:

[0178] Hot Zone State Variable Unit: Obtain the internal structure diagram of the annealing furnace, determine and mark the location information of each hot zone according to the internal structure diagram, arrange several sensors inside each hot zone, and monitor the operating parameters of each hot zone according to preset acquisition time points; obtain the historical operation record of each hot zone, collect the operating parameters corresponding to each acquisition time point in the historical operation record, calculate the load state at the acquisition time point, and combine the temperature and load state to construct the hot zone state variable;

[0179] Temperature prediction model unit: It collects the state variables generated by each hot zone at multiple sampling time points to form a hot zone state matrix containing time series, and uploads and stores the state matrix to the central control system; it obtains the historical hot zone state matrix in the central control system, uses the load state sequence and temperature of the historical hot zone state matrix as training data, and constructs a time series model for temperature prediction through a sliding window regression model. The time series prediction model takes the load state at multiple consecutive sampling time points as input and the temperature at the sampling time points as output.

[0180] Coupling strength module: Based on the thermal zone state matrix and the spatial arrangement of the thermal zones, construct a coupling strength model of adjacent thermal zones, calculate the coupling strength between each adjacent thermal zone, and construct a standard coupling strength matrix;

[0181] The coupling strength module includes a unit for calculating coupling strength and a unit for establishing the standard matrix of coupling strength.

[0182] Calculate the coupling strength unit: Based on the historical hot zone state matrix and combined with the spatial arrangement of each hot zone in the annealing furnace, determine the coupling relationship set of adjacent hot zones, extract the temperature and load state of each hot zone in the adjacent hot zones as the input feature set of the coupling strength model; for each group of adjacent hot zones, construct the coupling strength model based on the temperature and load state, and calculate the coupling strength of the adjacent hot zones.

[0183] Establish a standard matrix unit for coupling strength: summarize the coupling strength of each adjacent thermal zone and calculate the average value of the coupling strength to construct a standard matrix of coupling strength between adjacent thermal zones. The diagonal elements of the standard matrix are set to 0, and the elements of non-adjacent thermal zones are set to 0.

[0184] First compensation factor module: Compare the predicted temperature and actual temperature of each hot zone in the historical operation record, calculate the average temperature control deviation, combine the average difference and variance of the coupling strength of adjacent hot zones, construct training samples, and fit the first compensation factor formula based on the least squares method.

[0185] The first compensation factor module includes a training sample construction unit and a first compensation factor formula establishment unit:

[0186] Constructing training sample units: A training period of several consecutive days is preset. Operating records of the annealing furnace are acquired. In a given operating record, the operating parameters collected at each sampling time point are input into the time-series model for temperature prediction to obtain the predicted temperature corresponding to each sampling time point. The temperature and load state of each hot zone in the annealing furnace at different sampling time points are obtained, resulting in a hot zone state matrix for each hot zone. Based on the coupling strength model, the coupling strength of each adjacent hot zone is calculated, generating a coupling strength matrix. The coupling strength matrix is ​​then subtracted from the standard coupling strength matrix to obtain the result for each sampling time point. The coupling strength differences at each point are summarized to calculate the average coupling strength difference and variance. The predicted temperature and temperature corresponding to a certain hot zone at each sampling time point are summarized to calculate the average temperature control deviation. The temperature correction value applied by the central control system during the control process of each hot zone at different sampling time points is obtained, the temperature correction values ​​of all sampling time points are summarized, the average temperature correction value is calculated and set as the first compensation factor. The average coupling strength difference and variance of a certain adjacent hot zone are combined with the average temperature control deviation of the target hot zone of the adjacent hot zone to construct the training sample of the hot zone compensation factor.

[0187] Establish the first compensation factor formula unit: Summarize the training samples of the first compensation factor corresponding to all operation records of the hot zone, use the training samples as input and the first compensation factor as output to establish the first compensation factor formula, perform least squares fitting based on the training samples to obtain the values ​​of k1, k2, k3 and k4, and input them into the first compensation factor formula to establish the final first compensation factor formula.

[0188] The second compensation factor module: statistically analyzes the set of adjacent hot zones for each target hot zone, calculates the thermal disturbance influence weight based on the coupling strength, collects the temperature change values ​​of adjacent hot zones, and constructs the second compensation factor;

[0189] Real-time control module: acquires the real-time operating parameters of the annealing furnace and inputs them into the temperature prediction model, calculates the real-time predicted temperature, and combines the real-time average temperature control deviation, the real-time average difference of coupling strength, and the real-time variance parameter, respectively inputting them into the formulas for the first compensation factor and the second compensation factor to calculate the first compensation factor and the second compensation factor. It also calculates the temperature control setpoint executed by the central control system, sends the temperature control setpoint to the annealing furnace controller through the command interface, and adjusts the heater power output of the corresponding hot zone.

[0190] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for energy consumption control applied to an annealing furnace, characterized in that, The method comprises: Step S100: obtaining an internal structure diagram of the annealing furnace, determining position information of a plurality of heat zones and marking, arranging a plurality of sensors inside each heat zone; collecting operating parameters of each heat zone according to a preset collection time point, and constructing a heat zone state matrix; Step S200: based on the heat zone state matrix and the spatial arrangement of the heat zone, a coupling strength model of adjacent heat zones is constructed, the coupling strength between each adjacent heat zone is calculated, and a coupling strength standard matrix is constructed; Step S300: comparing the predicted temperature of each heat zone in the historical operation record with the temperature, calculating the temperature control deviation average value, combining the average difference and variance of the coupling strength of adjacent heat zones, constructing a training sample and fitting a first compensation factor formula based on the least square method; Step S400: statistics of each target heat zone adjacent heat zone set, according to the coupling strength, calculate the heat disturbance influence weight, collect the temperature change value of adjacent heat zone, construct the second compensation factor; Step S500: obtaining the real-time operating parameters of the annealing furnace and inputting into the temperature prediction model, calculating the real-time predicted temperature, combining the real-time temperature control deviation average value, the real-time average difference and the real-time variance parameters of the coupling strength, respectively inputting into the first compensation factor and the second compensation factor formula, calculating the first compensation factor and the second compensation factor, and calculating the temperature control set value executed by the central control system, the temperature control set value is sent to the annealing furnace controller through the instruction interface, and the heater power output of the corresponding heat zone is adjusted.

2. The energy consumption control method for an annealing furnace according to claim 1, wherein The step S100 comprises the following steps: Step S101: obtaining an internal structure diagram of the annealing furnace, determining the position information of each heat zone according to the internal structure diagram and marking, arranging a plurality of sensors inside each heat zone, and monitoring the operating parameters of each heat zone according to a preset collection time point; Step S102: Obtain the historical operation record of each thermal zone, collect the operation parameters corresponding to each collection time point in the historical operation record, obtain the temperature of the heated object, and calculate the temperature difference of the heated object between the collection time point and the previous collection time point as The power feedback value of the collection time point is calculated according to the following formula: ； Wherein, Af represents the power feedback value, D represents the material quality, E represents the material quality, y represents the time difference between the collection time point and the last collection time point, and the power instruction value of the collection time point is calculated according to the following formula: ； Wherein, Az represents the power instruction value, B represents the average current of the collection time point and the last collection time point, C represents the average voltage of the collection time point and the last collection time point; the load state of the collection time point is calculated according to the following formula: ； Wherein, A represents the load state of the collection time point, the temperature monitored at the collection time point is F, the temperature and the load state are combined, and the heat zone state variable S=(A,F) is constructed; Step S103: collecting the state variables generated by each heat zone at a plurality of collection time points to form a heat zone state matrix containing time sequence, and uploading and storing the state matrix to the central control system; Step S104: acquire a historical hot area state matrix in the central control system, take a load state sequence and a temperature of the historical hot area state matrix as training data, and construct a time series model for temperature prediction by a sliding window regression model as F t =f(A t-n ,A t-n+1 ,...,A t ), the time series model takes load states of consecutive multiple sampling time points as input, and takes a temperature at a tthacquisition time point as output, wherein F t represents the temperature at the tthacquisition time point, A t-n , A t-n+1 ,..., A t respectively represent load states at t-n, t-n+1,..., t acquisition time points, and n represents a window length.

3. The energy consumption control method for an annealing furnace according to claim 2, wherein The step S200 comprises the following steps: Step S201: based on the historical heat zone state matrix of step S104, and combining the spatial arrangement relationship of each heat zone in the annealing furnace, the coupling relationship set of adjacent heat zones is determined, the temperature and load state of each heat zone in the adjacent heat zone are extracted as the input feature set of the coupling strength model; Step S202: for each set of adjacent thermal zones, based on temperature and load state, a coupling strength model is constructed, and the coupling strength of the adjacent thermal zones is calculated, and the calculation formula of the coupling strength model is: ； where G 12 represents the coupling strength of hot zone 2 to hot zone 1, F1and F2represent the temperatures of adjacent hot zones 1 and 2, respectively, A1and A2represent the load states of adjacent hot zones 1 and 2, respectively, e1and e2represent positive constants to avoid division by zero, and a1and a2represent the weight values of the temperatures and load states, respectively. Step S203: the coupling strength of each adjacent thermal zone is summarized and the average value of the coupling strength is calculated, and a coupling strength standard matrix of the adjacent thermal zones is constructed, and the coupling strength standard matrix is expressed as ； where H represents a coupling strength standard matrix, G ij represents a coupling strength average value of the coupling strength from the hot zone j to the hot zone i, N represents the total number of hot zones, diagonal elements in the coupling strength standard matrix are set to 0, and elements of non-adjacent hot zones are 0.

4. The energy consumption control method for an annealing furnace according to claim 3, wherein The step S300 includes the following steps: Step S301: a plurality of consecutive days are preset as a training period, and the operation records of the annealing furnace are obtained, and in a certain operation record, the operation parameters collected at each collection time point are input into the time series model of temperature prediction to obtain the predicted temperature corresponding to each collection time point; Step S302: the temperature and load state corresponding to each thermal zone at different collection time points in the annealing furnace are obtained, the thermal zone state matrix of each thermal zone is obtained, the coupling strength of each adjacent thermal zone is calculated based on the coupling strength model, the coupling strength matrix is generated, the coupling strength matrix is subtracted from the coupling strength standard matrix, the coupling strength difference value at each collection time point is summarized, and the average difference value and the variance of the coupling strength are calculated; Step S303: the predicted temperature and the temperature corresponding to each collection time point of a certain thermal zone are summarized, and the temperature control deviation average value is calculated according to the following formula: wherein Fp represents the average value of the temperature control deviation, F d and F d respectively represent the predicted temperature and the temperature at the dth acquisition time point, and b represents the total number of acquisition time points. Step S304: the temperature correction value applied in the central control system control process of each thermal zone at different collection time points is obtained, the temperature correction values of all sampling time points are summarized, the temperature correction average value is calculated and set as the first compensation factor; Step S305: the coupling strength average difference value and the variance of a certain adjacent thermal zone are combined with the temperature control deviation average value of the target thermal zone of the adjacent thermal zone, a training sample of the thermal zone compensation factor is constructed, the training samples of the first compensation factor corresponding to all operation records of the thermal zone are summarized, the training sample is taken as the input, the first compensation factor is taken as the output, and the first compensation factor formula is established as: ； Wherein, Q1 represents the first compensation factor, L1 and L2 represent the coupling strength average difference value and the variance respectively, k1, k2, k3 represent the coupling strength average difference value, the variance and the temperature control deviation average value respectively, k4 represents the bias value of the first compensation factor formula, the least square fitting is carried out according to the training sample to obtain the numerical value of k1, k2, k3 and k4, and the numerical value is input into the first compensation factor formula to establish the final first compensation factor formula.

5. The energy consumption control method for an annealing furnace according to claim 4, wherein The step S400 includes the following steps: Step S401: all adjacent thermal zone sets of a certain target thermal zone are counted, the coupling strength of each adjacent thermal zone to the target thermal zone is collected in the coupling strength standard matrix, and the thermal disturbance influence weight of the adjacent thermal zone to the target thermal zone is calculated according to the following formula: ； where q r represents the thermal disturbance influence weight of the adjacent thermal zone r on the target thermal zone g, G rg represents the coupling strength of the adjacent thermal zone r on the target thermal zone g, G ng represents the coupling strength of the adjacent thermal zone n on the target thermal zone g, and m represents the total number of adjacent thermal zones; Step S402: the temperature change value of each adjacent thermal zone between two consecutive collection time points is obtained, and the second compensation factor of the target thermal zone is calculated according to the following second compensation factor formula: ； wherein Q2 represents a second compensation factor, q ng represents a thermal disturbance influence weight of the adjacent thermal zone n on the target thermal zone g, represents a temperature change value of the adjacent thermal zone n.

6. The energy consumption control method for an annealing furnace according to claim 5, wherein The step S500 includes the following steps: Step S501: Obtain the real-time running parameters of the annealing furnace, input them into the time sequence model of temperature prediction, calculate the real-time predicted temperature corresponding to each collection time point, collect the real-time temperature at the collection time point, calculate the real-time temperature control deviation average value, calculate the real-time average difference value and real-time variance of coupling strength, and input them into the first compensation factor formula to calculate the first compensation factor; Step S502: Obtain the real-time temperature change value of each adjacent hot zone between two continuous collection time points, and input it into the second compensation factor formula to calculate the second compensation factor; Step S503: Obtain the target temperature set value F preset by the central control system s and calculate the temperature set value executed by the central control system according to the following formula: ； F’ = F + F s The temperature set value is sent to the annealing furnace controller through the temperature control instruction interface, and the heater power output of the corresponding heating zone is adjusted according to the temperature set value.

7. An energy consumption control system applied to an annealing furnace for implementing the energy consumption control method applied to an annealing furnace according to any one of claims 1 to 6, characterized in that, The system comprises a hot zone state module, a coupling strength module, a first compensation factor module, a second compensation factor module and a real-time control module; The hot zone state module: obtains the internal structure diagram of the annealing furnace, determines the position information of a plurality of hot zones and marks them, and arranges a plurality of sensors inside each hot zone; According to the preset collection time points, the running parameters of each hot zone are collected, and a hot zone state matrix is constructed; The coupling strength module: based on the hot zone state matrix and the spatial arrangement of the hot zones, a coupling strength model of adjacent hot zones is constructed, the coupling strength between each adjacent hot zone is calculated, and a coupling strength standard matrix is constructed; The first compensation factor module: compares the predicted temperature and the temperature of each hot zone in the historical running record, calculates the temperature control deviation average value, combines the average difference value and variance of the coupling strength of adjacent hot zones, constructs a training sample and fits the first compensation factor formula based on the least square method; The second compensation factor module: statistics the adjacent hot zone set of each target hot zone, calculates the thermal disturbance influence weight according to the coupling strength, collects the temperature change value of the adjacent hot zone, and constructs the second compensation factor; The real-time control module: obtains the real-time running parameters of the annealing furnace and inputs them into the temperature prediction model to calculate the real-time predicted temperature, combines the real-time temperature control deviation average value, the real-time average difference value and the real-time variance parameters of the coupling strength, respectively inputs them into the first compensation factor and the second compensation factor formula, calculates the first compensation factor and the second compensation factor, and calculates the temperature control set value executed by the central control system, which is sent to the annealing furnace controller through the instruction interface, and the heater power output of the corresponding hot zone is adjusted.

8. The energy consumption control system for an annealing furnace according to claim 7, wherein The hot zone state module comprises a hot zone state variable unit and a temperature prediction model unit: The hot zone state variable unit: obtains the internal structure diagram of the annealing furnace, determines the position information of each hot zone according to the internal structure diagram and marks it, arranges a plurality of sensors inside each hot zone, and monitors the running parameters of each hot zone according to the preset collection time points; Obtain the historical running record of each hot zone, collect the running parameters corresponding to each collection time point in the historical running record, calculate the load state at the collection time point, combine the temperature and the load state, and construct the hot zone state variable; The temperature prediction model unit: collects the state variables generated by each thermal zone at multiple collection time points to form a thermal zone state matrix containing a time sequence, and uploads and stores the state matrix to the central control system; obtains a historical thermal zone state matrix in the central control system, takes the load state sequence and the temperature of the historical thermal zone state matrix as training data, and constructs a time sequence model for temperature prediction by a sliding window regression model, wherein the time sequence model takes the load state of a plurality of continuous sampling time points as input and takes the temperature at the collection time point as output.

9. The energy consumption control system for an annealing furnace according to claim 7, wherein The coupling strength module includes a calculation coupling strength unit and a coupling strength standard matrix establishing unit: The calculation coupling strength unit: determines a coupling relationship set of adjacent thermal zones based on the historical thermal zone state matrix and in combination with the spatial arrangement relationship of each thermal zone in the annealing furnace, extracts the temperature and load state of each thermal zone in the adjacent thermal zones as an input feature set of the coupling strength model; For each set of adjacent thermal zones, a coupling strength model is constructed based on the temperature and load state to calculate the coupling strength of the adjacent thermal zones; The coupling strength standard matrix establishing unit: aggregates and calculates the coupling strength average value of each adjacent thermal zone to construct a coupling strength standard matrix of the adjacent thermal zones, wherein the diagonal elements in the coupling strength standard matrix are set to 0 and the elements of non-adjacent thermal zones are 0.

10. The energy consumption control system for an annealing furnace according to claim 7, wherein The first compensation factor module includes a training sample constructing unit and a first compensation factor formula establishing unit: The training sample constructing unit: presets a plurality of consecutive days as a training period, obtains the operation record of the annealing furnace, inputs the operation parameters collected at each collection time point into the time sequence model for temperature prediction to obtain the predicted temperature corresponding to each collection time point; The temperature and load state corresponding to each thermal zone at different collection time points are obtained to obtain the thermal zone state matrix of each thermal zone, the coupling strength of each adjacent thermal zone is calculated based on the coupling strength model to generate a coupling strength matrix, the coupling strength matrix is subtracted from the coupling strength standard matrix to obtain the coupling strength difference value at each collection time point, and the coupling strength average difference value and the coupling strength variance are calculated; The predicted temperature and the temperature corresponding to each collection time point of a certain thermal zone are aggregated to calculate the temperature control deviation average value; the temperature correction value applied in the central control system control process of each thermal zone at different collection time points is obtained, the temperature correction values at all sampling time points are aggregated, the temperature correction average value is calculated and set as the first compensation factor; the coupling strength average difference value and the coupling strength variance of a certain adjacent thermal zone are combined with the temperature control deviation average value of the target thermal zone of the adjacent thermal zone to construct the training sample of the thermal zone compensation factor; The first compensation factor formula establishing unit: collects all the training samples of the first compensation factor corresponding to all the operation records of the hot area, takes the training samples as input, takes the first compensation factor as output, establishes the first compensation factor formula, performs least square fitting according to the training samples, obtains the values of k1, k2, k3 and k4, and inputs the values into the first compensation factor formula to establish the final first compensation factor formula.

Images