A method for energy-saving optimization control of furnace pressure of heating furnace based on furnace gas volume

Abstract

The present invention discloses a method for optimizing and controlling the furnace pressure of a heating furnace based on furnace gas volume, which relates to the field of heating furnace control technology. The method comprises: obtaining and preprocessing furnace gas volume data and furnace pressure data of a heat treatment area within the furnace of the heating furnace; constructing a furnace pressure combination prediction model based on the analysis results; adjusting the furnace pressure data based on the optimized furnace pressure combination prediction model; visually displaying the adjusted furnace pressure data and monitoring the operating status of the furnace in real time; and determining whether the monitoring results of the operating status of the furnace in the heating furnace meet the optimization requirements based on preset optimization criteria. The present invention can achieve accurate monitoring and detailed control of the operating status of the furnace in the heating furnace, facilitating real-time understanding of the working conditions within the furnace, thereby enabling appropriate adjustment measures to ensure the safe and efficient operation of the heating furnace.

Description

Technical Field

[0001] The present invention relates to the technical field of heating furnace control, and in particular to a method for energy-saving optimization control of a heating furnace hearth pressure based on furnace gas volume. Background Art

[0002] Heating furnaces, as devices specifically designed for heating objects, rely primarily on a variety of energy sources, such as electricity, natural gas, and liquefied petroleum gas, to provide heat. Their core function is to heat objects to the desired temperature, meeting the needs of a wide range of applications. Heating furnaces play a vital role in industrial production, scientific research, medical treatment, and food processing. With the rapid development of the global economy and the rapid advancement of science and technology, the application areas of heating furnaces continue to expand. They are now found not only in traditional manufacturing but also in emerging fields such as the preparation of new energy materials and thermal testing in the aerospace industry.

[0003] However, with the expansion of the application scope of heating furnaces, a series of challenges have also been brought about. The most prominent problem is the continuous increase in energy consumption and the significant increase in economic costs. This not only leads to a huge waste of resources, but also increases the economic burden of enterprises and even has a certain impact on the environment. Therefore, reducing the energy consumption of heating furnaces and reducing the economic costs of heating furnaces have become issues that need to be urgently addressed.

[0004] To reduce the energy consumption and economic costs of heating furnaces, optimization control is a common method. This is achieved by controlling the gas volume and pressure within the furnace chamber to achieve energy-saving optimization. However, due to the different areas within the furnace chamber, the required gas volume and pressure control also vary. This makes it difficult to accurately grasp the operating status of the heating furnace when adjusting the gas volume and pressure, making it impossible to adjust the gas volume and pressure in a timely manner. This not only reduces the production efficiency of the heating furnace, but also increases energy waste.

[0005] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0006] In response to the problems in the related art, the present invention proposes an energy-saving optimization control method for the furnace pressure of a heating furnace based on the furnace gas volume to overcome the above-mentioned technical problems existing in the existing related art.

[0007] To this end, the specific technical solutions adopted in the present invention are as follows:

[0008] A method for optimizing and controlling the furnace pressure of a heating furnace based on the amount of furnace gas, comprising the following steps:

[0009] S1. Obtaining and preprocessing furnace gas volume data and furnace pressure data of a heat treatment area inside a heating furnace, wherein the heat treatment area includes a heat exchange area, a preheating area, and a heating area;

[0010] S2. Analyze the furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area after pretreatment, construct a furnace pressure combination prediction model based on the analysis results, and optimize the furnace pressure combination prediction model;

[0011] S3. Adjusting furnace pressure data based on the optimized furnace pressure combination prediction model;

[0012] S4. Visually display the adjusted furnace pressure data and monitor the operating status of the heating furnace in real time;

[0013] S5. Based on the preset optimization criteria, determine whether the operating status monitoring results inside the heating furnace hearth meet the optimization requirements.

[0014] Furthermore, obtaining the furnace gas volume data and furnace pressure data of the heat treatment area inside the heating furnace and preprocessing them includes the following steps:

[0015] S11. Divide the heat treatment area of ​​the heating furnace into a heat exchange area, a preheating area, and a heating area according to the internal structure of the heating furnace, and arrange corresponding sensors in the heat treatment areas;

[0016] S12. Obtain furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area, and perform denoising, smoothing, and standardization processing.

[0017] Furthermore, the furnace gas volume data and furnace pressure data of the heat exchange area, preheating area and heating area after pretreatment are analyzed, a furnace pressure combination prediction model is constructed based on the analysis results, and the furnace pressure combination prediction model is optimized, including the following steps:

[0018] S21. Calculate the pre-processed furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area to obtain the gas flow rate of the heat exchange area, the temperature data of the preheating area, and the combustion efficiency of the heating area;

[0019] S22. Constructing a heat exchange area prediction model, a preheating area prediction model, and a heating area prediction model based on the obtained heat exchange area gas flow rate, preheating area temperature data, and heating area combustion efficiency;

[0020] S23, integrating the heat exchange area prediction model, the preheating area prediction model, and the heating area prediction model, and constructing a furnace pressure combination prediction model through an improved combination algorithm;

[0021] S24. Implement evaluation and optimize the furnace pressure prediction model based on the evaluation results.

[0022] Furthermore, the following steps are included to calculate the furnace gas volume data and furnace pressure data of the pre-processed heat exchange area, preheating area and heating area to obtain the gas flow rate of the heat exchange area, the temperature data of the preheating area and the combustion efficiency of the heating area:

[0023] S211. Calculate the gas flow rate in the heat exchange area using a standard calculation method based on the furnace gas volume data and furnace pressure data in the heat exchange area after pretreatment;

[0024] S212, calculating the temperature data of the heat exchange area by applying a temperature calculation formula based on the furnace gas volume data and the furnace pressure data of the preheating area after pretreatment;

[0025] S213. Based on the furnace gas volume data and the furnace pressure data of the heating area after pretreatment, a heating area simulation is performed on the combustion process in the heating area to calculate the combustion efficiency of the heating area.

[0026] Furthermore, the temperature calculation formula is:

[0027]

[0028] Where, W It is expressed as the temperature value of the preheating area of ​​the heating furnace;

[0029] T 1 Expressed as the thermal resistance value of the heating furnace hearth;

[0030] T 2 Expressed as the thermal resistance value of the preheating area of ​​the heating furnace;

[0031] Expressed as the temperature loss value of the heating furnace hearth;

[0032] It is expressed as the temperature loss value of the preheating area of ​​the heating furnace;

[0033] Expressed as the loss factor of the heating furnace hearth;

[0034] Expressed as the loss factor of the preheating area of ​​the heating furnace.

[0035] Furthermore, based on the furnace gas volume data and furnace pressure data of the heating area after pretreatment, the combustion process in the heating area is simulated, and the calculation of the combustion efficiency of the heating area includes the following steps:

[0036] S2131. Based on the furnace gas volume data and furnace pressure data of the heating area after pretreatment and the principle of thermodynamic equilibrium, a combustion simulation model of the heating area is established, and an iterative solution method is used to solve the model to obtain a combustion simulation result.

[0037] S2132. Using the combustion simulation results as the boundary, a combustion efficiency simulation model is constructed using the theoretical air ratio method based on the combustion chemical reaction principle.

[0038] S2133. Input the furnace gas volume data and furnace pressure data of the heating area after pretreatment into the combustion efficiency simulation model to obtain the combustion efficiency of the heating area.

[0039] Furthermore, the heat exchange area prediction model, the preheating area prediction model, and the heating area prediction model are integrated, and the furnace pressure combined prediction model is constructed through an improved combination algorithm, including the following steps:

[0040] S231. Based on the heat exchange area prediction model, the preheating area prediction model, and the heating area prediction model, obtain a heat exchange area prediction result, a preheating area prediction result, and a heating area prediction result, and obtain a heat exchange area prediction dataset, a preheating area prediction dataset, and a heating area prediction dataset;

[0041] S232, dividing the heat exchange area prediction data set into a heat exchange area training set and a heat exchange area test set, and randomly dividing the heat exchange area training set into several sub-heat exchange area training sets;

[0042] S233, sequentially selecting any sub-heat exchange region training set from the plurality of sub-heat exchange region training sets as the final heat exchange region training set, and combining the heat exchange region prediction model to obtain a plurality of prediction results;

[0043] S234, vertically overlapping and splicing a plurality of prediction results into a heat exchange area prediction feature;

[0044] S235, processing the preheating region prediction model and the heating region prediction model to obtain a preheating region prediction feature and a heating region prediction feature;

[0045] S236. Construct a furnace pressure combined prediction model based on the heating area prediction characteristics, the preheating area prediction characteristics, and the heating area prediction characteristics.

[0046] Furthermore, based on the prediction features of the heating area, the prediction features of the preheating area, and the prediction features of the heating area, constructing a furnace pressure combined prediction model includes the following steps:

[0047] S2361, performing denoising, smoothing, and standardization processing on the heating area prediction features, the preheating area prediction features, and the heating area prediction features;

[0048] S2362. Based on the random forest model and combined with the lion group optimization algorithm, a furnace pressure combination prediction model is constructed;

[0049] S2363. Use the processed heating area prediction features, preheating area prediction features and heating area prediction features as training data to train the furnace pressure combination prediction model.

[0050] Furthermore, the evaluation is performed and the furnace pressure prediction model is optimized based on the evaluation results, including the following steps:

[0051] S241, selecting furnace pressure data as a prediction factor from the processed heat treatment area furnace gas volume data and furnace pressure data;

[0052] S242, performing noise reduction on the selected principal component factors to obtain auxiliary data;

[0053] S243, dividing the auxiliary data into a training set and a test set, initializing the furnace pressure prediction model using an experimental method, and selecting the optimal setting result;

[0054] S244. Optimize the constructed furnace pressure combination prediction model using a furnace pressure optimization algorithm.

[0055] Furthermore, based on the preset optimization criteria, determining whether the operating status monitoring results inside the heating furnace hearth meet the optimization requirements includes the following steps:

[0056] S51, using the internal pressure data of the heating furnace within a preset range as a preset optimization standard;

[0057] S52, comparing the monitoring results with the preset optimization standard to determine whether the operating state inside the heating furnace meets the optimization requirements;

[0058] S53. If there is no deviation between the monitoring result and the preset optimization standard, it means that the control effect of the furnace pressure meets the requirements;

[0059] If there is a deviation between the monitoring results and the preset optimization standard, it means that the control effect of the furnace pressure does not meet the requirements. The furnace pressure combination prediction model is used to calculate and adjust the furnace pressure data until there is no deviation between the monitoring results and the preset optimization standard.

[0060] The beneficial effects of the present invention are:

[0061] 1. The present invention collects the furnace gas volume data and furnace pressure data of the heat treatment area inside the heating furnace and pre-processes them, so as to realize the accurate monitoring and detailed control of the internal operating status of the heating furnace, which helps to understand the working conditions inside the furnace in real time and discover potential operating problems in time, so as to take corresponding adjustment measures to ensure the safe and efficient operation of the heating furnace.

[0062] 2. By analyzing the furnace gas volume data and furnace pressure data in the heat treatment area, the present invention can accurately predict the internal change trend of the furnace pressure. It can not only better understand the operating status inside the furnace, but also provide solid data support and accurate basis for subsequent energy-saving optimization, thereby effectively reducing energy consumption and improving the operating efficiency of the heating furnace.

[0063] 3. Through the visual display of the furnace pressure control results, the present invention can intuitively understand the operating status inside the heating furnace and capture any abnormal conditions in real time, which not only significantly improves the efficiency and timeliness of production management, but also greatly reduces production costs. At the same time, by continuously optimizing the furnace pressure control, it can achieve more efficient energy utilization, reduce unnecessary energy consumption, and promote green, low-carbon and efficient production. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 The present invention is a flowchart of a method for optimizing and controlling the furnace pressure of a heating furnace based on the furnace gas volume according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and the advantages of the present invention.

[0067] According to an embodiment of the present invention, a method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume is provided.

[0068] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1As shown, according to the energy-saving optimization control method of the heating furnace hearth pressure based on the furnace gas amount according to an embodiment of the present invention, the energy-saving optimization control method of the heating furnace hearth pressure based on the furnace gas amount includes the following steps:

[0069] S1. Obtaining furnace gas volume data and furnace pressure data of a heat treatment area inside a heating furnace and performing preprocessing, wherein the heat treatment area includes a heat exchange area, a preheating area, and a heating area.

[0070] In the description of the present invention, obtaining the furnace gas volume data and the furnace pressure data of the heat treatment area inside the heating furnace and performing preprocessing includes the following steps:

[0071] S11. Divide the heat treatment area of ​​the heating furnace hearth into a heat exchange area, a preheating area, and a heating area according to the internal structure of the heating furnace hearth, and arrange corresponding sensors in the heat treatment area.

[0072] It should be noted that the internal structure of the heating furnace hearth is divided into heat exchange area, preheating area and heating area according to their different functions and roles; the heat exchange area is usually located at the entrance of the furnace, used for heat transfer and preheating objects; the preheating area is located after the heat exchange area, used for further preheating objects; the heating area is located after the preheating area, used to heat the objects to the required temperature; corresponding sensors are arranged inside each area for real-time monitoring of the pressure and furnace gas volume of the area. These sensors can be temperature sensors, pressure sensors, etc.

[0073] S12. Obtain furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area, and perform denoising, smoothing, and standardization processing.

[0074] It should be noted that the acquired furnace gas volume data and furnace pressure data are first subjected to wavelet denoising; the furnace gas volume data and furnace pressure data are denoised by the wavelet denoising method, and the furnace gas volume data and furnace pressure data are subjected to wavelet transform to be decomposed into wavelet coefficients of different sizes and frequencies; and the obtained wavelet coefficients are subjected to threshold processing; the wavelet coefficients after threshold processing are subjected to inverse wavelet transform to remove the noise components and restore the furnace gas volume data and furnace pressure data.

[0075] Secondly, the window size in the moving average method is selected according to the characteristics and periodicity of the furnace gas volume data and the furnace pressure data, that is, the number of data points used in the smoothing process; the continuous data points within the window size are summed and divided by the window size to obtain the moving average value of the window; the window is slid to the next position of the data sequence in turn, and the previous steps are repeated to calculate the new moving average value. By continuously sliding the window and calculating the moving average value, the entire data sequence can be smoothed to make the data more stable and continuous; for data points located at the boundary of the data sequence, since a complete window cannot be formed, it is necessary to use data outside the boundary to fill it, use the moving average value of the incomplete window, etc.; according to the actual situation and smoothing effect, the window size in the moving average method and possible boundary processing methods can be adjusted to obtain better smoothing effect and data feature retention.

[0076] Finally, the mean and standard deviation of the smoothed gas volume data and furnace pressure data are calculated and converted into a unified format with similar scale and range using the Z-score standardization calculation formula. The Z-score standardization calculation formula is:

[0077]

[0078] Where, Z Expressed as standard scores;

[0079] X It is expressed as the value of a specific data among the furnace gas volume data and the furnace pressure data;

[0080] It is expressed as the mean of furnace gas volume data and furnace pressure data;

[0081] Expressed as the standard deviation of furnace gas volume data and furnace pressure data.

[0082] S2. Analyze the furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area after pretreatment, construct a furnace pressure combination prediction model based on the analysis results, and optimize the furnace pressure combination prediction model.

[0083] In the description of the present invention, the furnace gas volume data and furnace pressure data of the heat exchange area, preheating area and heating area after pretreatment are analyzed, a furnace pressure combination prediction model is constructed based on the analysis results, and the furnace pressure combination prediction model is optimized, including the following steps:

[0084] S21. Calculate the furnace gas volume data and furnace pressure data of the pre-processed heat exchange area, preheating area and heating area to obtain the gas flow rate of the heat exchange area, the temperature data of the preheating area and the combustion efficiency of the heating area.

[0085] In the description of the present invention, the following steps are involved in calculating the gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area after pretreatment to obtain the gas flow rate of the heat exchange area, the temperature data of the preheating area, and the combustion efficiency of the heating area:

[0086] S211. Based on the furnace gas volume data and furnace pressure data of the heat exchange area after pretreatment, the gas flow rate of the heat exchange area is calculated using a standard calculation method.

[0087] It should be noted that the standard calculation formula is:

[0088]

[0089] Where, S Expressed as the gas flow rate in the heat exchange area;

[0090] N Expressed as the furnace gas volume in the heat exchange area;

[0091] V Expressed as the cross-sectional area of ​​gas flow in the heat exchange area.

[0092] S212. Calculate the temperature data of the heat exchange area by applying a temperature calculation formula based on the furnace gas volume data and the furnace pressure data of the preheating area after pretreatment.

[0093] In the description of the present invention, the temperature calculation formula is:

[0094]

[0095] Where, W It is expressed as the temperature value of the preheating area of ​​the heating furnace;

[0096] T 1 Expressed as the thermal resistance value of the heating furnace hearth;

[0097] T 2 Expressed as the thermal resistance value of the preheating area of ​​the heating furnace;

[0098] Expressed as the temperature loss value of the heating furnace hearth;

[0099] It is expressed as the temperature loss value of the preheating area of ​​the heating furnace;

[0100] Expressed as the loss factor of the heating furnace hearth;

[0101] Expressed as the loss factor of the preheating area of ​​the heating furnace.

[0102] S213. Based on the furnace gas volume data and the furnace pressure data of the heating area after pretreatment, a heating area simulation is performed on the combustion process in the heating area to calculate the combustion efficiency of the heating area.

[0103] In the description of the present invention, based on the furnace gas volume data and furnace pressure data of the heating area after pretreatment, the combustion process in the heating area is simulated, and the heating area combustion efficiency is calculated, which includes the following steps:

[0104] S2131. Based on the furnace gas volume data and furnace pressure data of the heating area after pretreatment and the principle of thermodynamic equilibrium, a combustion simulation model of the heating area is established, and an iterative solution method is used to solve it to obtain the combustion simulation results.

[0105] It should be noted that the principle of thermodynamic equilibrium is a process commonly used to describe combustion. It is based on the principles of thermodynamics and chemical equilibrium theory, and describes the combustion process by taking the chemical reactions between fuel, oxygen, and combustion products to a state of equilibrium. The established combustion simulation model is converted into a set of mathematical equations, and the combustion simulation results are obtained by linearizing the nonlinear equations and then iteratively approximating the true solution.

[0106] S2132. Using the combustion simulation results as the boundary, based on the combustion chemical reaction principle, a combustion efficiency simulation model is constructed using the theoretical air ratio method.

[0107] It should be noted that the principle of combustion chemical reaction is that fuel and oxygen react under appropriate conditions to produce energy, heat, light and various chemical products; according to the theoretical air ratio method, the combustion efficiency can be calculated by comparing the chemical reaction amount of fuel and the theoretically required air; the combustion efficiency simulation model is based on the oxygen in the furnace gas volume, actual combustion conditions and fuel characteristics, and calculates the amount of fuel that is not completely burned during the combustion process and the oxygen content in the exhaust gas generated. By using the results of the combustion simulation as boundary conditions, the proportion of chemical energy converted into effective energy in the actual combustion process is calculated, usually expressed as a percentage, thereby constructing a combustion efficiency simulation model.

[0108] S2133. Input the furnace gas volume data and furnace pressure data of the heating area after pretreatment into the combustion efficiency simulation model to obtain the combustion efficiency of the heating area.

[0109] S22. Construct a heat exchange area prediction model, a preheating area prediction model, and a heating area prediction model based on the obtained heat exchange area gas flow rate, preheating area temperature data, and heating area combustion efficiency.

[0110] It should be noted that based on the obtained gas flow rate of the heat exchange area, the temperature data of the preheating area and the combustion efficiency of the heating area, the convolutional neural network is used to construct the heat exchange area prediction model, the preheating area prediction model and the heating area prediction model respectively; and the heat exchange area prediction model, the preheating area prediction model and the heating area prediction model are trained using the gas flow rate of the heat exchange area, the temperature data of the preheating area and the combustion efficiency of the heating area.

[0111] S23. Integrate the heat exchange area prediction model, the preheating area prediction model, and the heating area prediction model, and construct a furnace pressure combination prediction model through an improved combination algorithm.

[0112] In the description of the present invention, the heat exchange area prediction model, the preheating area prediction model and the heating area prediction model are integrated, and the furnace pressure combined prediction model is constructed by an improved combination algorithm, which includes the following steps:

[0113] S231. Based on the heat exchange area prediction model, the preheating area prediction model and the heating area prediction model, obtain the heat exchange area prediction result, the preheating area prediction result and the heating area prediction result, and obtain the heat exchange area prediction data set, the preheating area prediction data set and the heating area prediction data set.

[0114] S232. Divide the heat exchange area prediction data set into a heat exchange area training set and a heat exchange area test set, and randomly divide the heat exchange area training set into several sub-heat exchange area training sets.

[0115] S233. Sequentially select any sub-heat exchange region training set from the plurality of sub-heat exchange region training sets as the final heat exchange region training set, and combine with the heat exchange region prediction model to obtain a plurality of prediction results.

[0116] S234. Vertically overlap and splice a plurality of prediction results into a heat exchange area prediction feature.

[0117] S235 . Process the preheating region prediction model and the heating region prediction model to obtain preheating region prediction features and heating region prediction features.

[0118] It should be noted that the preheating area prediction data set is divided into a preheating area training set and a preheating area test set, and the preheating area training set is randomly divided into several sub-preheating area training sets; any sub-preheating area training set in the several sub-preheating area training sets after division is selected in turn as the final preheating area training set, and combined with the preheating area prediction model, several prediction results of the final training set trained by the preheating area prediction model and a prediction result on the final test set are obtained; several prediction results are vertically overlapped and spliced ​​into preheating area prediction features.

[0119] The heating area prediction dataset is divided into a heating area training set and a heating area test set, and the heating area training set is randomly divided into several sub-heating area training sets; any sub-heating area training set in the divided sub-heating area training sets is selected in turn as the final heating area training set, and combined with the heating area prediction model, several prediction results of the final training set trained by the heating area prediction model and a prediction result on the final test set are obtained; several prediction results are vertically overlapped and spliced ​​into heating area prediction features.

[0120] S236. Construct a furnace pressure combined prediction model based on the heating area prediction characteristics, the preheating area prediction characteristics, and the heating area prediction characteristics.

[0121] In the description of the present invention, based on the heating area prediction characteristics, the preheating area prediction characteristics and the heating area prediction characteristics, constructing the furnace pressure combined prediction model includes the following steps:

[0122] S2361. De-noise, smooth and standardize the heating area prediction features, preheating area prediction features and heating area prediction features.

[0123] S2362. Based on the random forest model and combined with the lion group optimization algorithm, a furnace pressure combination prediction model is constructed.

[0124] It should be noted that feature extraction and feature selection are performed on the heating area prediction features, preheating area prediction features and heating area prediction features to construct a feature set for prediction, and a furnace pressure combination prediction model is constructed based on the random forest model; the lion group optimization algorithm is introduced into the furnace pressure combination prediction model to optimize the prediction features of the furnace pressure combination prediction model; among them, the lion group optimization algorithm is a heuristic optimization algorithm based on group behavior, which is inspired by the social behavior and hunting strategy of lions. The algorithm simulates the foraging behavior of lion groups, and finds the optimal prediction features through the cooperation and competition of heating area prediction features, preheating area prediction features and heating area prediction features.

[0125] S2363. Use the processed heating area prediction features, preheating area prediction features and heating area prediction features as training data to train the furnace pressure combination prediction model.

[0126] S24. Implement evaluation and optimize the furnace pressure prediction model based on the evaluation results.

[0127] In the description of the present invention, performing the evaluation and optimizing the furnace pressure prediction model according to the evaluation results includes the following steps:

[0128] S241, selecting furnace pressure data as a prediction factor from the processed heat treatment area furnace gas volume data and furnace pressure data;

[0129] S242, performing noise reduction on the selected principal component factors to obtain auxiliary data;

[0130] S243, dividing the auxiliary data into a training set and a test set, initializing the furnace pressure prediction model using an experimental method, and selecting the optimal setting result;

[0131] S244. Optimize the constructed furnace pressure combination prediction model using a furnace pressure optimization algorithm.

[0132] S3. Adjust the furnace pressure data based on the optimized furnace pressure combination prediction model.

[0133] It should be noted that, based on the optimized furnace pressure combination prediction model, adjusting the furnace pressure data includes the following steps:

[0134] The current heat exchange area gas flow rate, preheating area temperature data and heating area combustion efficiency are obtained, and the current heat exchange area gas flow rate, preheating area temperature data and heating area combustion efficiency are normalized; the normalized heat exchange area gas flow rate, preheating area temperature data and heating area combustion efficiency are input into the optimized furnace pressure combination prediction model to obtain furnace pressure prediction data; the furnace pressure prediction data is analyzed, and the heat exchange area gas flow rate, preheating area temperature data and heating area combustion efficiency are adjusted according to the energy-saving optimization standard to make the furnace pressure prediction data more accurate.

[0135] Among them, when the furnace pressure prediction data is lower than the energy-saving optimization standard, the furnace pressure can be increased by adjusting any one of the factors among the gas flow rate, temperature and combustion efficiency. Specifically, increasing the gas flow rate will lead to an increase in furnace pressure, increasing the temperature will also increase the furnace pressure, and improving the combustion efficiency will also lead to an increase in furnace pressure.

[0136] When the predicted furnace pressure data is higher than the energy-saving optimization standard, the furnace pressure can be reduced by adjusting any one of the factors including gas flow rate, temperature and combustion efficiency. Specifically, reducing the gas flow rate will lead to a decrease in furnace pressure, reducing the temperature will also lead to a decrease in furnace pressure, and reducing the combustion efficiency will also lead to a decrease in furnace pressure.

[0137] The energy-saving optimization standard of the heating furnace hearth usually takes into account the gas flow rate, temperature and combustion efficiency in the furnace. Therefore, controlling the furnace pressure within the range of 80% to 120% of the normal working pressure is an effective way to achieve energy-saving optimization.

[0138] In addition, factors affecting furnace pressure include the following:

[0139] By changing the gas flow rate, the flow state of the gas in the furnace is adjusted, thereby affecting the pressure in the furnace. A higher gas flow rate will increase the kinetic energy of the gas in the furnace, resulting in an increase in pressure. Conversely, a lower gas flow rate will reduce the pressure in the furnace.

[0140] By changing the temperature, the kinetic energy of the gas molecules is changed, thereby changing the frequency and force of collisions between the gas molecules and the container wall; high temperature increases the speed and pressure of the gas molecules, while low temperature reduces the speed and pressure of the gas molecules;

[0141] By changing the combustion efficiency, the fuel consumption rate and the amount of combustion products generated can be changed, thereby affecting the pressure inside the furnace; improving the combustion efficiency can reduce fuel consumption and the generation of by-products, reduce the gas volume in the furnace, and reduce the furnace pressure; while reducing the combustion efficiency increases the gas volume in the furnace and increases the furnace pressure.

[0142] S4. Visualize the adjusted furnace pressure data and monitor the operating status inside the heating furnace in real time.

[0143] It should be noted that the furnace pressure control results are visualized in the form of real-time monitoring charts; corresponding alarm thresholds are set based on the monitored furnace pressure data, that is, an alarm is triggered when the pressure exceeds or falls below the set threshold.

[0144] S5. Based on the preset optimization criteria, determine whether the operating status monitoring results inside the heating furnace hearth meet the optimization requirements.

[0145] In the description of the present invention, based on the preset optimization criteria, determining whether the operating status monitoring results inside the heating furnace hearth meet the optimization requirements includes the following steps:

[0146] S51. Using the internal pressure data of the heating furnace within a preset range as a preset optimization standard.

[0147] It should be noted that the preset range of the pressure data inside the heating furnace is generally [0, 30Pa], which is usually set according to the process requirements and the design specifications inside the heating furnace to ensure that the pressure inside the furnace is within a safe range and can meet the production energy-saving optimization needs.

[0148] S52. Compare the monitoring results with the preset optimization standards to determine whether the operating status inside the heating furnace meets the optimization requirements.

[0149] S53. If there is no deviation between the monitoring result and the preset optimization standard, it means that the control effect of the furnace pressure meets the requirements.

[0150] If there is a deviation between the monitoring results and the preset optimization standard, it means that the control effect of the furnace pressure does not meet the requirements. The furnace pressure combination prediction model is used to calculate and adjust the furnace pressure data until there is no deviation between the monitoring results and the preset optimization standard.

[0151] In summary, with the help of the above technical solutions of the present invention, by collecting the furnace gas volume data and furnace pressure data of the heat treatment area inside the furnace of the heating furnace and performing preprocessing, it is possible to accurately monitor and carefully control the operating status of the furnace inside the heating furnace, which helps to understand the working conditions inside the furnace in real time, timely discover potential operating problems, and take corresponding adjustment measures to ensure the safe and efficient operation of the heating furnace. By analyzing the furnace gas volume data and furnace pressure data of the heat treatment area, it is possible to accurately predict the internal change trend of the furnace pressure, which not only can better understand the operating status inside the furnace, but also can provide solid data support and accurate basis for subsequent energy-saving optimization, thereby effectively reducing energy consumption and improving the operating efficiency of the heating furnace. Through the visual display of the furnace pressure control results, it is possible to intuitively understand the operating status of the furnace inside the heating furnace and capture any abnormal conditions in real time, which not only significantly improves the efficiency and timeliness of production management, but also greatly reduces production costs. At the same time, by continuously optimizing the furnace pressure control, it is possible to achieve more efficient energy utilization, reduce unnecessary energy consumption, and promote the realization of green, low-carbon, and efficient production.

[0152] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing and controlling the furnace pressure of a heating furnace based on the amount of furnace gas, characterized in that: The heating furnace pressure energy-saving optimization control method based on furnace gas volume comprises the following steps: S1. Obtaining and preprocessing furnace gas volume data and furnace pressure data of a heat treatment area inside a heating furnace, wherein the heat treatment area includes a heat exchange area, a preheating area, and a heating area; S2. Analyze the furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area after pretreatment, construct a furnace pressure combination prediction model based on the analysis results, and optimize the furnace pressure combination prediction model; S3. Adjusting furnace pressure data based on the optimized furnace pressure combination prediction model; S4. Visually display the adjusted furnace pressure data and monitor the operating status of the heating furnace in real time; S5. Based on the preset optimization criteria, determine whether the operating status monitoring results inside the heating furnace hearth meet the optimization requirements; The S2 comprises the following steps: S21. Calculate the pre-processed furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area to obtain the gas flow rate of the heat exchange area, the temperature data of the preheating area, and the combustion efficiency of the heating area; S22. Constructing a heat exchange area prediction model, a preheating area prediction model, and a heating area prediction model based on the obtained heat exchange area gas flow rate, preheating area temperature data, and heating area combustion efficiency; S23, integrating the heat exchange area prediction model, the preheating area prediction model, and the heating area prediction model, and constructing a furnace pressure combination prediction model through an improved combination algorithm; S24. Conduct an evaluation and optimize the furnace pressure prediction model based on the evaluation results; The S21 includes the following steps: S211. Calculate the gas flow rate in the heat exchange area using a standard calculation method based on the pre-processed furnace gas volume data and furnace pressure data in the heat exchange area; S212, calculating the temperature data of the heat exchange area by applying a temperature calculation formula based on the furnace gas volume data and the furnace pressure data of the preheating area after pretreatment; S213, based on the pre-processed furnace gas volume data and furnace pressure data of the heating area, performing a heating area simulation on the combustion process in the heating area, and calculating the heating area combustion efficiency; The S23 includes the following steps: S231. Based on the heat exchange area prediction model, the preheating area prediction model, and the heating area prediction model, obtain a heat exchange area prediction result, a preheating area prediction result, and a heating area prediction result, and obtain a heat exchange area prediction dataset, a preheating area prediction dataset, and a heating area prediction dataset; S232, dividing the heat exchange area prediction data set into a heat exchange area training set and a heat exchange area test set, and randomly dividing the heat exchange area training set into several sub-heat exchange area training sets; S233, sequentially selecting any sub-heat exchange region training set from the plurality of sub-heat exchange region training sets as the final heat exchange region training set, and combining the heat exchange region prediction model to obtain a plurality of prediction results; S234, vertically overlapping and splicing a plurality of prediction results into a heat exchange area prediction feature; S235, processing the preheating region prediction model and the heating region prediction model to obtain a preheating region prediction feature and a heating region prediction feature; S236. Construct a furnace pressure combined prediction model based on the heating area prediction characteristics, the preheating area prediction characteristics, and the heating area prediction characteristics.

2. The method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume according to claim 1, characterized in that: The method of obtaining the furnace gas volume data and the furnace pressure data of the heat treatment area in the furnace of the heating furnace and performing preprocessing includes the following steps: S11. Divide the heat treatment area of ​​the heating furnace into a heat exchange area, a preheating area, and a heating area according to the internal structure of the heating furnace, and arrange corresponding sensors in the heat treatment areas; S12. Obtain furnace gas volume data and furnace pressure data of the heat exchange area, preheating area, and heating area, and perform denoising, smoothing, and standardization processing.

3. The method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume according to claim 1, characterized in that: The temperature calculation formula is: Where, W It is expressed as the temperature value of the preheating area of ​​the heating furnace; T 1 Expressed as the thermal resistance value of the heating furnace hearth; T 2 Expressed as the thermal resistance value of the preheating area of ​​the heating furnace; Expressed as the temperature loss value of the heating furnace hearth; It is expressed as the temperature loss value of the preheating area of ​​the heating furnace; Expressed as the loss factor of the heating furnace hearth; Expressed as the loss factor of the preheating area of ​​the heating furnace.

4. The method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume according to claim 3, characterized in that: The heating area simulation is performed on the combustion process in the heating area based on the furnace gas volume data and the furnace pressure data of the heating area after pretreatment, and the calculation of the heating area combustion efficiency includes the following steps: S2131. Based on the furnace gas volume data and furnace pressure data of the heating area after pretreatment and the principle of thermodynamic equilibrium, a combustion simulation model of the heating area is established, and an iterative solution method is used to solve the model to obtain a combustion simulation result. S2132. Using the combustion simulation results as the boundary, a combustion efficiency simulation model is constructed using the theoretical air ratio method based on the combustion chemical reaction principle. S2133. Input the furnace gas volume data and furnace pressure data of the heating area after pretreatment into the combustion efficiency simulation model to obtain the combustion efficiency of the heating area.

5. The method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume according to claim 4, characterized in that: The construction of the furnace pressure combined prediction model based on the heating area prediction characteristics, the preheating area prediction characteristics and the heating area prediction characteristics includes the following steps: S2361, performing denoising, smoothing, and standardization processing on the heating area prediction features, the preheating area prediction features, and the heating area prediction features; S2362. Based on the random forest model and combined with the lion group optimization algorithm, a furnace pressure combination prediction model is constructed; S2363. Use the processed heating area prediction features, preheating area prediction features and heating area prediction features as training data to train the furnace pressure combination prediction model.

6. The method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume according to claim 5, characterized in that: The implementation of the evaluation and optimization of the furnace pressure prediction model based on the evaluation results include the following steps: S241, selecting furnace pressure data as a prediction factor from the processed heat treatment area furnace gas volume data and furnace pressure data; S242, performing noise reduction on the selected principal component factors to obtain auxiliary data; S243, dividing the auxiliary data into a training set and a test set, initializing the furnace pressure prediction model using an experimental method, and selecting the optimal setting result; S244. Optimize the constructed furnace pressure combination prediction model using a furnace pressure optimization algorithm.

7. The method for energy-saving optimization control of furnace pressure of a heating furnace based on furnace gas volume according to claim 1, characterized in that: The method of judging whether the monitoring result of the operating status inside the heating furnace hearth meets the optimization requirements based on the preset optimization criteria includes the following steps: S51, using the internal pressure data of the heating furnace within a preset range as a preset optimization standard; S52, comparing the monitoring results with the preset optimization standard to determine whether the operating state inside the heating furnace meets the optimization requirements; S53. If there is no deviation between the monitoring result and the preset optimization standard, it means that the control effect of the furnace pressure meets the requirements; If there is a deviation between the monitoring results and the preset optimization standard, it means that the control effect of the furnace pressure does not meet the requirements. The furnace pressure combination prediction model is used to calculate and adjust the furnace pressure data until there is no deviation between the monitoring results and the preset optimization standard.

Images