A heating furnace energy-saving monitoring and prediction method and system based on digital twin technology

Through digital twin technology, the energy efficiency of the heating furnace is simulated and optimized, the key factor parameters are identified, and the prediction model is established, which solves the problems of inaccurate energy efficiency analysis and inaccurate prediction in the existing technology, and the energy efficiency optimization and dynamic adjustment of the operating parameters of the heating furnace are achieved. , improves production efficiency and equipment life.

CN118500140BActive Publication Date: 2024-12-03JIANGSU SOUTH ENERGY SAVING TECHNOLOGY CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202410622824.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-20
Publication Date
2024-12-03
Estimated Expiration
2044-05-20

AI Technical Summary

Technical Problem

The prior art is difficult to accurately simulate and analyze the energy efficiency and energy consumption of heating furnaces under different working conditions, resulting in reduced energy efficiency and reduced production efficiency, and the inability to detect potential operation problems in a timely manner, improve downtime, reduce equipment life, and reduce future. Predictive accuracy of energy efficiency changes.

Method used

Using the energy-saving monitoring and prediction method of heating furnace based on digital twin technology, by obtaining the operating parameters of the heating furnace, building a digital twin model, simulating energy efficiency and energy consumption under different working conditions, generating energy efficiency images, identifying key factor parameters, and establishing an energy efficiency prediction model. Perform optimization design parameters adjustments to achieve energy efficiency optimization and prediction.

Benefits of technology

It improves the energy efficiency and energy saving effect of the heating furnace, reduces energy waste, promptly detects operational problems, extends equipment life, reduces operating costs, improves the accuracy of forecasting future energy efficiency changes, and achieves higher operating efficiency and cost-effectiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118500140B_ABST
    Figure CN118500140B_ABST
Patent Text Reader

Abstract

The present invention discloses a heating furnace energy-saving monitoring and prediction method and system based on digital twin technology, which relates to the technical field of heating furnaces, including the following steps: inputting the acquired relevant parameters of the heating furnace operation into the heating furnace digital twin model; generating a heating furnace energy efficiency image; obtaining a heating furnace energy efficiency characteristic image; identifying key factor parameters affecting the heating furnace energy efficiency; and using the established heating furnace energy efficiency prediction model to predict the heating furnace energy efficiency changes at future moments. The present invention can help optimize the operating parameters of the heating furnace by accurately simulating and analyzing the energy efficiency and energy consumption of the heating furnace under different working conditions, thereby improving energy efficiency and achieving energy saving. At the same time, the constructed energy efficiency prediction model can predict future energy efficiency changes based on real-time data and historical data, thereby improving the accuracy of prediction of the future status of the heating furnace.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of heating furnaces, and in particular to a method and system for monitoring and predicting energy conservation of a heating furnace based on digital twin technology. Background Art

[0002] At present, in the evaluation of the energy-saving monitoring results of heating furnaces in the petrochemical industry, the five indicators of exhaust temperature, furnace body outer surface temperature, flue gas oxygen content, excess air coefficient, and thermal efficiency are limited to qualified or unqualified evaluation, or in actual evaluation, only thermal efficiency is used for single indicator evaluation. Thermal efficiency only directly reflects the degree of thermal energy utilization of the heating furnace. Sometimes the thermal efficiency meets the standard but the local loss may not meet the standard. Therefore, it is the current trend of energy-saving development of process heating furnaces to monitor and predict the energy-saving operation of the heating furnace in real time, and to guide the operation and maintenance of the heating furnace through comprehensive indicator evaluation. Through real-time monitoring of big data, increasing the monitoring range and covering a wide area, the thermal efficiency of the heating furnace can be greatly improved to achieve the purpose of saving fuel and reducing waste gas emissions.

[0003] In the prior art, it is not convenient to accurately simulate and analyze the energy efficiency and energy consumption of the heating furnace under different working conditions, thereby reducing energy efficiency and achieving energy saving, and it is not convenient to test different operations without affecting actual production, thereby reducing production efficiency. At the same time, it is not convenient to predict the energy efficiency changes of the heating furnace through monitoring, and it is impossible to discover potential operating problems in time and perform preventive maintenance, which increases downtime and reduces equipment life. It is not convenient to predict the future energy efficiency changes of the heating furnace, which reduces the accuracy of the prediction of the future status of the heating furnace, and thus it is not convenient to respond more quickly to potential efficiency declines or increased energy consumption and take corresponding adjustment measures.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a heating furnace energy-saving monitoring and prediction method and system based on digital twin technology, which solves the problems raised in the above background technology that the existing technology is not convenient for accurately simulating and analyzing the energy efficiency and energy consumption of the heating furnace under different working conditions, thereby reducing energy efficiency and achieving energy saving, and is not convenient for testing different operations without affecting actual production, thereby reducing production efficiency. At the same time, it is not convenient to predict the energy efficiency changes of the heating furnace through monitoring, and potential operating problems cannot be discovered in time, and preventive maintenance can be performed, which increases downtime and reduces equipment life. It is not convenient to predict the future energy efficiency changes of the heating furnace, which reduces the accuracy of the prediction of the future status of the heating furnace, and thus it is not convenient to respond more quickly to potential efficiency declines or energy consumption increases and take corresponding adjustment measures.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] According to one aspect of the present invention, a heating furnace energy-saving monitoring and prediction method based on digital twin technology is provided. The heating furnace energy-saving monitoring and prediction method based on digital twin technology comprises the following steps:

[0008] S1. Obtain relevant parameters of the heating furnace operation, build a digital twin model of the heating furnace, and input the obtained relevant parameters of the heating furnace operation into the digital twin model of the heating furnace;

[0009] S2. Simulate the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model, and generate an energy efficiency image of the heating furnace;

[0010] S3, preprocessing the generated heating furnace energy efficiency image to obtain a heating furnace energy efficiency characteristic image;

[0011] S4, using an analysis algorithm to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database, and identifying key factor parameters that affect the heating furnace energy efficiency;

[0012] S5. Based on the identified key factor parameters affecting the energy efficiency of the heating furnace, a heating furnace energy efficiency prediction model is established, and the established heating furnace energy efficiency prediction model is used to predict the change of the heating furnace energy efficiency at future moments.

[0013] Furthermore, simulating the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model and generating the heating furnace energy efficiency loss image includes the following steps:

[0014] S21, loading the optimization tool and energy efficiency simulation tool of the heating furnace digital twin model;

[0015] S22. Based on the obtained relevant parameters of the heating furnace operation, simulate and analyze the digital twin model of the heating furnace;

[0016] S23. If the simulation analysis results indicate that the performance of the heating furnace is unstable under the preset operating conditions, use the optimization tool to adjust the design parameters of the heating furnace in the heating furnace digital twin model;

[0017] S24, after optimization, re-simulate and analyze to check whether the heating furnace structure meets the preset operating conditions. If not, continue to repeat S22 and S24 until the conditions are met;

[0018] S25. Use an energy efficiency simulation tool to perform energy efficiency loss detection on the optimized digital twin model of the heating furnace. If the detection result shows that the energy efficiency loss meets the preset standard, save and export the optimized digital twin model of the heating furnace to obtain an optimized energy efficiency model of the heating furnace during operation;

[0019] S26. Based on the obtained optimized energy efficiency model, use computer software to simulate the energy efficiency loss effect of the heating furnace under preset operating conditions, and generate an energy efficiency loss image of the heating furnace according to the simulation results.

[0020] Furthermore, if the simulation analysis results indicate that the performance of the heating furnace is unstable under the preset operating conditions, the optimization tool is used to adjust the design parameters of the heating furnace in the heating furnace digital twin model, including the following steps:

[0021] S231. Starting an optimization algorithm in an optimization tool of the heating furnace digital twin model;

[0022] S232. Based on the design parameters of the heating furnace in the digital twin model of the heating furnace, determine the size of the design variable set, and randomly select a set of initial design parameters as the initial design;

[0023] S233, for each set of design parameters of the heating furnace, randomly adjust the design variables, and update the design parameters of each set of heating furnaces;

[0024] S234, using simulation analysis tools to evaluate the performance of each group of heating furnace designs, and calculating the performance fitness by comparing the performance of each heating furnace design under operating conditions with the preset conditions;

[0025] S235, evaluating the design quality of each group of heating furnaces according to the calculated performance fitness;

[0026] S236, finding the heating furnace design with the best performance, and recording the performance adaptability and corresponding design parameters of the best heating furnace design;

[0027] S237. Adjust the parameters of other heating furnace designs according to the heating furnace design with the best performance, repeat steps S233 to S236 for iterative optimization, until the performance of the heating furnace design reaches or exceeds the preset operating conditions, and terminate the optimization process.

[0028] Further, preprocessing the generated heating furnace energy efficiency image to obtain the heating furnace energy efficiency characteristic image includes the following steps:

[0029] S31, removing noise from the generated heating furnace energy efficiency image by wavelet transform;

[0030] S32, extracting an image sequence from the denoised heating furnace energy efficiency image, and performing grayscale processing on each frame of the image sequence to obtain a grayscale image;

[0031] S33, using the Prewitt operator to calculate the edge gradient of each pixel in the grayscale image;

[0032] S34, using a morphological gradient method to locally screen and enhance edge gradients, and setting a threshold to filter edge gradients to obtain a gradient image;

[0033] S35, thinning and binarizing the gradient image, and taking the pixel points whose gradient values ​​are greater than the threshold as edge points;

[0034] S36, connecting adjacent edge points into a connected domain, and obtaining a final edge image as a heating furnace energy efficiency feature image.

[0035] Further, using an analysis algorithm to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database, identifying the key factor parameters affecting the heating furnace energy efficiency includes the following steps:

[0036] S41, obtaining a heating furnace energy efficiency characteristic image, and processing the obtained heating furnace energy efficiency characteristic images by normalization to calculate the normalized value of each characteristic;

[0037] S42, assigning corresponding weights to the normalized features according to the importance of each heating furnace energy efficiency feature;

[0038] S43, finding the ideal optimal value and the worst value of each heating furnace energy efficiency characteristic through the weighted characteristic value, which respectively constitute the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state;

[0039] S44. For each heating furnace energy efficiency characteristic, calculate the grey correlation coefficient between each heating furnace energy efficiency characteristic and an ideal heating furnace energy efficiency state and an unideal heating furnace energy efficiency state;

[0040] S45. Based on the grey correlation coefficient, the grey correlation degree between each heating furnace energy efficiency characteristic and the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state is calculated respectively;

[0041] S46. Use grey correlation to construct the relative closeness of the ideal heating furnace energy efficiency state, evaluate the advantages and disadvantages of each heating furnace energy efficiency characteristic, and identify the key factor parameters that affect the heating furnace energy efficiency.

[0042] Furthermore, the formulas for calculating the grey correlation between each heating furnace energy efficiency characteristic and the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state are as follows:

[0043]

[0044]

[0045] in, Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the ideal energy efficiency state of the heating furnace;

[0046] Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the non-ideal energy efficiency state of the heating furnace;

[0047] M represents the grey relational degree;

[0048] d represents the energy efficiency characteristics of the heating furnace;

[0049] W represents the sum of the furnace energy efficiency characteristics.

[0050] Furthermore, the formula for constructing the relative closeness of the ideal heating furnace energy efficiency state is:

[0051]

[0052] in, Indicates the relative closeness between the energy efficiency characteristics of the cth heating furnace and the ideal heating furnace energy efficiency state;

[0053] B represents relative closeness;

[0054] Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the ideal energy efficiency state of the heating furnace;

[0055] Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the non-ideal energy efficiency state of the heating furnace;

[0056] M represents the grey relational degree.

[0057] Furthermore, based on the identified key factor parameters affecting the energy efficiency of the heating furnace, a heating furnace energy efficiency prediction model is established, and the heating furnace energy efficiency change at a future moment is predicted using the established heating furnace energy efficiency prediction model, including the following steps:

[0058] S51. Collect historical data related to heating furnace energy efficiency;

[0059] S52, dividing the key factor parameters and historical data affecting the energy efficiency of the heating furnace into a training set and a test set;

[0060] S53. Construct a heating furnace energy efficiency prediction model, input key factor parameters that affect the heating furnace energy efficiency into the heating furnace energy efficiency prediction model, and obtain a predicted value of the heating furnace energy efficiency at a future time.

[0061] Furthermore, a heating furnace energy efficiency prediction model is constructed, and the key factor parameters affecting the heating furnace energy efficiency are input into the heating furnace energy efficiency prediction model. The heating furnace energy efficiency prediction value at a future moment is obtained, which includes the following steps:

[0062] S531, selecting a matching heating furnace energy efficiency prediction model structure, and determining the number of key factor parameters affecting the heating furnace energy efficiency in the input layer, hidden layer, and output layer respectively;

[0063] S532, calculating the input key factor parameters of the hidden layer according to the input key factor parameters, weights and biases of the input layer;

[0064] S533, calculating the input key factor parameters of the output layer according to the output key factor parameters, weights and biases of the hidden layer;

[0065] S534, importing the input key factor parameters of the output layer into the activation function for solving, obtaining the output key factor parameters of the output layer, and using the output key factor parameters of the output layer as the predicted value of the energy efficiency of the heating furnace at a future moment;

[0066] S535. Calculate the error between the predicted value and the actual value of the heating furnace energy efficiency using an error algorithm, and adjust the parameters of the heating furnace energy efficiency prediction model using a gradient descent algorithm.

[0067] According to another aspect of the present invention, a heating furnace energy-saving monitoring and prediction system based on digital twin technology is also provided. The heating furnace energy-saving monitoring and prediction system based on digital twin technology includes:

[0068] A data acquisition module is used to acquire relevant parameters of the heating furnace operation, build a digital twin model of the heating furnace, and input the acquired relevant parameters of the heating furnace operation into the digital twin model of the heating furnace;

[0069] An image generation module is used to simulate the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model and generate an energy efficiency image of the heating furnace;

[0070] An image processing module is used to preprocess the generated heating furnace energy efficiency image to obtain a heating furnace energy efficiency characteristic image;

[0071] A data analysis module is used to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database by using an analysis algorithm to identify key factor parameters affecting the heating furnace energy efficiency;

[0072] A model building module is used to build a heating furnace energy efficiency prediction model based on the identified key factor parameters affecting the heating furnace energy efficiency, and use the built heating furnace energy efficiency prediction model to predict the heating furnace energy efficiency changes at future times;

[0073] Among them, the data acquisition module is connected with the image processing module through the image generation module, and the image processing module is connected with the model establishment module through the data analysis module.

[0074] The beneficial effects of the present invention are:

[0075] 1. The present invention can help optimize the operating parameters of the heating furnace by accurately simulating and analyzing the energy efficiency and energy consumption of the heating furnace under different working conditions, thereby improving energy efficiency and achieving energy saving. The use of a digital twin model to simulate the operation of the heating furnace can test different operating strategies without affecting actual production, which helps to find the optimal operating parameter settings, reduce energy waste, and maintain production efficiency. By monitoring and predicting changes in the energy efficiency of the heating furnace, potential operating problems can be discovered in a timely manner, and preventive maintenance can be performed to avoid sudden failures, reduce downtime, extend equipment life, and reduce maintenance costs. Based on precise data analysis and predictive models, decisions about the operation and maintenance of the heating furnace can be made more confidently, which helps to achieve higher operating efficiency and cost-effectiveness. At the same time, the constructed energy efficiency prediction model can predict future energy efficiency changes based on real-time data and historical data, improve the accuracy of predictions of future conditions, and thus respond more quickly to potential efficiency declines or increased energy consumption and take corresponding adjustment measures.

[0076] 2. The present invention simulates the performance of the heating furnace under different working conditions in the digital twin model, and adjusts the design parameters of the heating furnace according to the simulation results, thereby realizing dynamic optimization of the operating parameters of the heating furnace. By optimizing the design parameters of the heating furnace, unnecessary energy consumption can be reduced, thereby improving the overall efficiency. Energy efficiency loss detection of the optimized model is performed using an energy efficiency simulation tool, which helps to identify and eliminate energy efficiency loss points and achieve efficient use of energy. By calculating the performance fitness and evaluating the pros and cons of the heating furnace design based on this, the best design scheme can be selected. An optimized energy efficiency model is established and the energy efficiency loss under preset operating conditions is simulated based on this model. Accurate predictions can be provided for future operating performance, thereby reducing energy consumption and improving energy efficiency, which can significantly reduce operating costs and reduce environmental impacts.

[0077] 3. The present invention assigns energy efficiency characteristics to each heating furnace through normalization processing and weighting, and calculates the grey correlation coefficient and correlation degree under ideal and non-ideal conditions. It can accurately evaluate the influence of each energy efficiency characteristic on the total energy efficiency of the heating furnace, and construct the relative closeness of the ideal heating furnace energy efficiency state to help the operator understand the gap between the current heating furnace operating state and the optimal energy efficiency state, and adjust the operating strategy accordingly. By identifying the key factor parameters that affect the energy efficiency of the heating furnace, energy-saving measures can be formulated in a targeted manner.

[0078] 4. The present invention uses historical data to train and test the heating furnace energy efficiency prediction model, which can accurately predict the energy efficiency changes in the future. By identifying and analyzing the key factors and parameters that affect the heating furnace energy efficiency, the energy efficiency dynamics in the operation of the heating furnace can be better understood. The constructed heating furnace energy efficiency prediction model allows real-time monitoring of the operating status of the heating furnace and dynamically adjusts the operating parameters according to the prediction results. The dynamic adjustment and real-time monitoring mechanism helps to keep the heating furnace running in the best energy efficiency state, and respond quickly to emergencies. By accurately predicting the energy efficiency changes of the heating furnace, preventive measures can be taken before potential problems occur. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 creative work.

[0080] Figure 1 is a flow chart of a heating furnace energy-saving monitoring and prediction method based on digital twin technology according to an embodiment of the present invention;

[0081] Figure 2 It is a principle block diagram of a heating furnace energy-saving monitoring and prediction system based on digital twin technology according to an embodiment of the present invention.

[0082] In the figure:

[0083] 1. Data acquisition module; 2. Image generation module; 3. Image processing module; 4. Data analysis module; 5. Model building module. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0085] In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0086] According to an embodiment of the present invention, a heating furnace energy-saving monitoring and prediction method and system based on digital twin technology are provided.

[0087] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1As shown, according to the heating furnace energy-saving monitoring and prediction method based on digital twin technology according to an embodiment of the present invention, the heating furnace energy-saving monitoring and prediction method based on digital twin technology includes the following steps:

[0088] S1. Obtain relevant parameters of the heating furnace operation, build a digital twin model of the heating furnace, and input the obtained relevant parameters of the heating furnace operation into the digital twin model of the heating furnace;

[0089] Specifically, the relevant parameters of the heating furnace operation include:

[0090] 1) Physical parameters:

[0091] Temperature: The temperature inside the heating furnace and the material is one of the most important operating parameters.

[0092] Pressure: The pressure inside a furnace, especially in a closed or semi-closed furnace.

[0093] Flow rate: the flow rate of fuel, air or cooling medium, etc.

[0094] Material characteristics: type, size, weight, etc. of the heated material.

[0095] 2) Chemical parameters:

[0096] Fuel composition: The chemical composition of a fuel, which affects combustion efficiency and emissions.

[0097] Oxidation-reduction state: affects the combustion process and material heating quality.

[0098] 3) Operation parameters:

[0099] Burning Rate: The rate at which a fuel burns.

[0100] Heating rate: the rate at which a material is heated.

[0101] Furnace gas composition: the composition of the gas in the furnace that affects the combustion efficiency and material heating quality.

[0102] Furnace layout: The layout of materials in the furnace and its effect on heating efficiency.

[0103] Specifically, physical and chemical parameters can be monitored in real time by various sensors (such as temperature sensors, pressure sensors, flow meters, etc.) installed in the heating furnace and its surroundings.

[0104] Specifically, a digital twin model of the heating furnace is constructed through computer-aided design software (i.e., CAD software).

[0105] Specifically, select appropriate CAD software such as AutoCAD, Altium Designer, Eagle, KiCad, etc. according to needs, then set the relevant parameters of the heating furnace operation of the heating furnace in the software (these parameters are based on the measurement data of the actual heating furnace), add appropriate wiring and component layout to the digital twin model of the heating furnace, so that it is as close as possible to the design and appearance of the actual heating furnace, including the number of layers of the furnace body, the type of materials used (such as high-temperature resistant materials, thermal insulation materials), size and shape. Refine more details according to needs, such as the layout of heating elements, the design of flues, etc., to increase the authenticity of the model. Then, the actual measured heating furnace parameters are input into the digital twin model of the heating furnace, and all two-dimensional designs are converted into three-dimensional models (i.e., the digital twin model of the heating furnace) by using software, and various simulation tests are performed on this digital twin model of the heating furnace, such as analyzing the thermal efficiency and combustion uniformity of the heating furnace through thermal flow simulation, and performing structural strength analysis to evaluate the performance and safety of the heating furnace under actual operating conditions.

[0106] S2. Simulate the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model, and generate an energy efficiency image of the heating furnace;

[0107] Specifically, the energy efficiency image of the heating furnace is generated through computer graphics technology. Computer graphics technology refers to the technology of using computer technology to generate, process, analyze and display images, especially three-dimensional images. Computer graphics technology plays a key role in simulating the energy efficiency and energy consumption of the heating furnace under different working conditions and generating corresponding images.

[0108] Specifically, the use of computer graphics technology to generate heating furnace energy efficiency images includes:

[0109] Create a 3D model of the furnace: Create a detailed 3D model of the furnace in CAD software, ensuring that the model accurately represents the furnace internal structure, heating element layout, and any critical microstructures.

[0110] Physical simulation: Use physical simulation software (such as ANSYS, Autodesk Simulation) to simulate the wear phenomenon of the heating furnace in the actual operating environment. This should include applying environmental and mechanical parameters such as temperature changes, mechanical stress, thermal stress, and simulating chemical corrosion or physical wear that may affect the life of the heating furnace.

[0111] Data processing and visualization: The simulation data is processed using computer graphics software (such as Blender, Maya, 3ds Max). These software can create high-quality visual effects to assist in visualizing the wear and tear of the heating furnace.

[0112] Add realism: Adjust material properties and lighting effects in graphics software to simulate the real surface characteristics and wear of the furnace and its components. These visual effects can increase the depth and realism of the image.

[0113] Rendered loss images: Use the software's rendering capabilities to transform simulation and visualization results into high-resolution furnace loss images.

[0114] S3, preprocessing the generated heating furnace energy efficiency image to obtain a heating furnace energy efficiency characteristic image;

[0115] Specifically, the heating furnace energy efficiency characteristic images are the results of processing and transforming the original images. Through these images, specific features related to the heating furnace energy efficiency can be intuitively observed, such as thermal maps of heat distribution, regional markings of heat energy loss, etc.

[0116] S4, using an analysis algorithm to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database, and identifying key factor parameters that affect the heating furnace energy efficiency;

[0117] Specifically, the key parameters affecting the energy efficiency of the heating furnace include:

[0118] 1) Design parameters:

[0119] Furnace body materials: The materials used in the furnace body (such as refractory bricks, insulation materials) have an important influence on its thermal insulation performance and energy efficiency.

[0120] Furnace structure: The size, shape and internal structure design of the heating furnace have a significant impact on the thermal efficiency and uniformity of material heating.

[0121] Heating element layout: The layout and distribution of heating elements (such as heating wires, combustion nozzles) directly affect the efficiency of heat energy transfer.

[0122] 2) Operation parameters:

[0123] Temperature setting: The operating temperature of the heating furnace has a direct impact on energy consumption and product quality.

[0124] Loading: The amount and layout of the material being heated will affect the heating efficiency and the temperature distribution within the furnace.

[0125] Combustion control: Fuel type, supply rate and combustion efficiency are key factors affecting energy consumption.

[0126] Furnace atmosphere: In certain heating processes, the furnace atmosphere (such as the ratio of oxygen, nitrogen and hydrogen) has an important influence on the heating effect and energy efficiency of the material.

[0127] 3) Maintenance status:

[0128] Furnace insulation performance: The thermal insulation performance of the furnace body decreases over time, affecting energy efficiency.

[0129] Heating element wear: Heating elements wear out over time, affecting heating efficiency.

[0130] Ash accumulation and pollution: Ash accumulation and pollution inside the furnace body will affect the heat exchange efficiency and combustion efficiency.

[0131] 4) Other factors:

[0132] External environmental conditions: such as ambient temperature, humidity, etc. may also affect the energy efficiency of the heating furnace.

[0133] Operating habits: The operating habits and proficiency of the operator will also affect the energy efficiency of the heating furnace.

[0134] S5. Based on the identified key factor parameters affecting the energy efficiency of the heating furnace, a heating furnace energy efficiency prediction model is established, and the established heating furnace energy efficiency prediction model is used to predict the change of the heating furnace energy efficiency at future moments.

[0135] Preferably, simulating the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model and generating the heating furnace energy efficiency loss image includes the following steps:

[0136] S21, loading the optimization tool and energy efficiency simulation tool of the heating furnace digital twin model;

[0137] Specifically, optimization tools are used to simulate and optimize the layout of the internal structure of the heating furnace to achieve predetermined energy efficiency and performance goals. Such tools involve calculating and adjusting the layout of heating elements, the insulation level inside the furnace, the density and size of the heating area, and the placement and spacing of materials, with the aim of improving the thermal efficiency of the heating furnace, reducing heat energy losses, and optimizing the temperature distribution in the furnace. Through these optimizations, the overall operating performance of the heating furnace can be enhanced, energy consumption can be reduced, and the quality of processed materials can be improved.

[0138] Specifically, energy efficiency simulation tools are used to simulate the energy efficiency performance of heating furnaces under various conditions and configurations. Through these tools, users can predict the energy efficiency of heating furnaces under different operating conditions and identify potential areas for energy efficiency improvement. Including:

[0139] Thermodynamic simulation: Simulate heat transfer, heat loss and thermal efficiency during heating processes.

[0140] Fluid Dynamics Simulation (CFD): Analyze the airflow pattern, temperature distribution and combustion efficiency within the furnace.

[0141] Structural Analysis: Evaluate the performance of the furnace structure at high temperatures, as well as the thermal stability and thermal expansion of the materials.

[0142] S22. Based on the obtained relevant parameters of the heating furnace operation, simulate and analyze the digital twin model of the heating furnace;

[0143] S23. If the simulation analysis results indicate that the performance of the heating furnace is unstable under the preset operating conditions, use the optimization tool to adjust the design parameters of the heating furnace in the heating furnace digital twin model;

[0144] S24, after optimization, re-simulate and analyze to check whether the heating furnace structure meets the preset operating conditions. If not, continue to repeat S22 and S24 until the conditions are met;

[0145] S25. Use an energy efficiency simulation tool to perform energy efficiency loss detection on the optimized digital twin model of the heating furnace. If the detection result shows that the energy efficiency loss meets the preset standard, save and export the optimized digital twin model of the heating furnace to obtain an optimized energy efficiency model of the heating furnace during operation;

[0146] S26. Based on the obtained optimized energy efficiency model, use computer software to simulate the energy efficiency loss effect of the heating furnace under preset operating conditions, and generate an energy efficiency loss image of the heating furnace according to the simulation results.

[0147] Specifically, the computer software is graphics software, which refers to software tools specifically used to create, edit and analyze images and graphics. In the heating furnace energy efficiency loss image, graphics software can be used to process and visualize simulation results, making the analysis results more intuitive and easy to understand. Including:

[0148] Blender: An open source 3D graphics software that can be used to create complex 3D models, animations, and visualizations.

[0149] Maya or 3ds Max: These software are widely used for 3D modeling, animation, and visual effects, and can help show the internal structure and working principles of the heating furnace in detail.

[0150] MATLAB's graphics processing capabilities: Although MATLAB is primarily a numerical computing software, its powerful graphics processing and data visualization capabilities are also very suitable for analyzing and displaying simulation data.

[0151] Preferably, if the simulation analysis results indicate that the performance of the heating furnace is unstable under the preset operating conditions, using the optimization tool to adjust the design parameters of the heating furnace in the heating furnace digital twin model includes the following steps:

[0152] S231. Starting an optimization algorithm in an optimization tool of the heating furnace digital twin model;

[0153] Specifically, the optimization algorithm is the Fruit Fly Optimization Algorithm (FOA), which is a new global optimization evolutionary algorithm derived from the evolution of fruit fly foraging behavior. Fruit flies have superior sense of smell and vision than other species. Fruit fly groups effectively collect various odors floating in the air through their sense of smell, and move toward food. Then they use their keen vision to distinguish the location of food and companions, gather at locations with high concentrations of food smell, and then use their sense of smell to fly out in random directions to find food, and repeat this cycle until they find food.

[0154] S232. Based on the design parameters of the heating furnace in the digital twin model of the heating furnace, determine the size of the design variable set (i.e., the size of the fruit fly population), and randomly select a set of initial design parameters therefrom as the initial design (i.e., initialization of the fruit fly population);

[0155] S233, for each set of design parameters of the heating furnace (i.e., individual positions of the fruit flies), randomly adjust the design variables (i.e., random search of the fruit flies), and update the design parameters of each set of heating furnaces (i.e., update the individual positions of the fruit flies);

[0156] S234. Evaluate the performance of each set of heating furnace designs using simulation analysis tools (i.e., finite element analysis tools), and calculate the performance fitness (i.e., the individual fruit fly flavor concentration determination value) by comparing the performance of each heating furnace design under operating conditions with the differences between the preset conditions;

[0157] S235, evaluating the design quality of each group of heating furnaces according to the calculated performance fitness;

[0158] S236, finding the heating furnace design with the best performance (i.e., the optimal fruit fly individual), and recording the performance fitness and corresponding design parameters of the best heating furnace design;

[0159] S237. Adjust the parameters of other heating furnace designs according to the heating furnace design with the best performance, repeat steps S233 to S236 for iterative optimization, until the performance of the heating furnace design reaches or exceeds the preset operating conditions, and terminate the optimization process.

[0160] Preferably, preprocessing the generated heating furnace energy efficiency image to obtain the heating furnace energy efficiency characteristic image comprises the following steps:

[0161] S31, removing noise from the generated heating furnace energy efficiency image by wavelet transform;

[0162] Specifically, wavelet transform is a powerful mathematical tool for signal processing and image analysis, especially in the fields of noise removal, signal compression and feature extraction. It can provide a localized analysis of the time (or space) and frequency of a signal or image, and can analyze the local area of ​​the signal at different scales, thereby capturing the details of various frequency components.

[0163] S32, extracting an image sequence from the denoised heating furnace energy efficiency image, and performing grayscale processing on each frame of the image sequence to obtain a grayscale image;

[0164] S33, using the Prewitt operator to calculate the edge gradient of each pixel in the grayscale image;

[0165] Specifically, the Prewitt operator is an operator in image processing technology used for edge detection. It is mainly used to calculate the edge gradient of each pixel in the image in order to identify the edge part of the image. It achieves this goal by performing a convolution operation on the image. Specifically, it uses two 3x3 kernels (or filters) to calculate the gradient of the image in the horizontal and vertical directions respectively.

[0166] S34, using a morphological gradient method to locally screen and enhance edge gradients, and setting a threshold to filter edge gradients to obtain a gradient image;

[0167] Specifically, the morphological gradient method is a technique based on mathematical morphology in image processing, which is used to highlight the edges or object boundaries in an image. This method can enhance the edges in an image by processing the shape and structure of the image, making the edges clearer, which helps image analysis and object recognition. Morphological operations rely on structural elements (a predefined shape) to detect corresponding shapes in the image.

[0168] S35, thinning and binarizing the gradient image, and taking the pixel points whose gradient values ​​are greater than the threshold as edge points;

[0169] S36, connecting adjacent edge points into a connected domain, and obtaining a final edge image as a heating furnace energy efficiency feature image.

[0170] Preferably, using an analysis algorithm to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database, and identifying the key factor parameters affecting the heating furnace energy efficiency includes the following steps:

[0171] S41, obtaining a heating furnace energy efficiency characteristic image, and processing the obtained heating furnace energy efficiency characteristic images by normalization to calculate the normalized value of each characteristic;

[0172] Specifically, normalization is a data preprocessing method that aims to adjust the range of numerical data so that it is within a specific interval, such as (0, 1) or (-1, 1), so that data of different dimensions or magnitudes can be compared and analyzed. In image processing and machine learning, normalization can help improve the convergence speed and accuracy of the algorithm, and also prevent certain features from having too much impact on the model due to their large numerical range.

[0173] S42, assigning corresponding weights to the normalized features according to the importance of each heating furnace energy efficiency feature;

[0174] S43, finding the ideal optimal value and the worst value of each heating furnace energy efficiency characteristic through the weighted characteristic value, which respectively constitute the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state;

[0175] S44. For each heating furnace energy efficiency characteristic, calculate the grey correlation coefficient between each heating furnace energy efficiency characteristic and an ideal heating furnace energy efficiency state and an unideal heating furnace energy efficiency state;

[0176] S45. Based on the grey correlation coefficient, the grey correlation degree between each heating furnace energy efficiency characteristic and the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state is calculated respectively;

[0177] S46. Use grey correlation to construct the relative closeness of the ideal heating furnace energy efficiency state, evaluate the advantages and disadvantages of each heating furnace energy efficiency characteristic, and identify the key factor parameters that affect the heating furnace energy efficiency.

[0178] Specifically, the analysis algorithm is the TOP-SIS algorithm based on grey correlation, which is a decision analysis algorithm that combines grey correlation analysis and TOPSIS method. Grey correlation analysis is an analysis method used to process incomplete information and is used for system analysis of small samples and incomplete information. It determines the similarity between factors by calculating the grey correlation between each factor. TOPSIS method is a multi-attribute decision analysis method.

[0179] Specifically, the TOPSIS algorithm based on grey correlation combines the advantages of these two methods. Grey correlation analysis is used to calculate the correlation between each energy efficiency index (i.e., each heating furnace energy efficiency characteristic) and the ideal energy efficiency state (i.e., high energy efficiency, low loss) and the non-ideal energy efficiency state (i.e., low energy efficiency, high loss). These energy efficiency indicators may include thermal efficiency, energy consumption level, temperature uniformity, etc., reflecting the energy efficiency and performance of the heating furnace during operation.

[0180] Preferably, the formula for calculating the grey correlation between each heating furnace energy efficiency characteristic and the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state is:

[0181]

[0182]

[0183] in, Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the ideal energy efficiency state of the heating furnace;

[0184] Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the non-ideal energy efficiency state of the heating furnace;

[0185] M represents the grey relational degree;

[0186] d represents the energy efficiency characteristics of the heating furnace;

[0187] W represents the sum of the furnace energy efficiency characteristics.

[0188] Preferably, the formula for constructing the relative closeness of the ideal heating furnace energy efficiency state is:

[0189]

[0190] in, Indicates the relative closeness between the energy efficiency characteristics of the cth heating furnace and the ideal heating furnace energy efficiency state;

[0191] B represents relative closeness;

[0192] Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the ideal energy efficiency state of the heating furnace;

[0193] Represents the grey correlation between the energy efficiency characteristics of the cth heating furnace and the non-ideal energy efficiency state of the heating furnace;

[0194] M represents the grey relational degree.

[0195] Preferably, based on the identified key factor parameters affecting the energy efficiency of the heating furnace, a heating furnace energy efficiency prediction model is established, and using the established heating furnace energy efficiency prediction model to predict the change of the heating furnace energy efficiency at a future moment includes the following steps:

[0196] S51. Collect historical data related to heating furnace energy efficiency;

[0197] Specifically, historical data includes:

[0198] 1) Operation parameter data:

[0199] Temperature records: operating temperature of the heating furnace and temperature distribution inside the furnace.

[0200] Time record: the length of time for each stage such as heating, insulation, cooling, etc.

[0201] Load data: type, quantity and distribution of material in the heating furnace.

[0202] Fuel consumption: Type of fuel used (e.g. natural gas, electricity) and amount consumed.

[0203] 2) Performance index data:

[0204] Energy consumption data: energy consumption per unit product or per unit time.

[0205] Production efficiency: The output of the furnace, and how quickly it reaches the required temperature.

[0206] Thermal efficiency: the energy utilization rate of a heating furnace, that is, the ratio of effective heating energy to total energy consumption.

[0207] 3) Maintenance and fault records:

[0208] Maintenance Records: A furnace maintenance log including records of service, repairs, and parts replacement.

[0209] Fault history: fault type, time, handling measures and recovery time.

[0210] 4) Environmental conditions data:

[0211] Ambient temperature: The external temperature conditions when the heating furnace is operating.

[0212] Humidity Record: Humidity level of the operating environment.

[0213] Other environmental factors: such as air flow, spatial conditions of the working area, etc.

[0214] 5) Operator records:

[0215] Operating habits: operating modes, habits and efficiency of different operators.

[0216] Shift data: Time and efficiency differences between operating shifts.

[0217] 6) Product quality data:

[0218] Yield rate: the rate of qualified products under different operating conditions.

[0219] Product quality indicators: measurement data of the physical and chemical properties of the product after heating.

[0220] S52, dividing the key factor parameters and historical data affecting the energy efficiency of the heating furnace into a training set and a test set;

[0221] S53. Construct a heating furnace energy efficiency prediction model, input key factor parameters that affect the heating furnace energy efficiency into the heating furnace energy efficiency prediction model, and obtain a predicted value of the heating furnace energy efficiency at a future time.

[0222] It needs to be explained that, for example, the collected historical data such as operating parameter data, performance indicator data and environmental condition data are first divided into a test set, and the key factor parameters affecting the energy efficiency of the heating furnace such as design parameters, operating parameters and other factors are divided into a training set. Then, the key factor parameters affecting the energy efficiency of the heating furnace such as design parameters, operating parameters and other factors are input into the heating furnace energy efficiency prediction model (i.e., the multi-layer perceptron model), and the input key factor parameters of the output layer in the multi-layer perceptron model (i.e., design parameters, operating parameters and other factors, etc.) are imported into the activation function for solution to obtain the output key factor parameters of the output layer (i.e., design parameters, operating parameters and other factors, etc.), and the output key factor parameters of the output layer (i.e., design parameters, operating parameters and other factors, etc.) are used as the predicted value of the energy efficiency of the heating furnace at the future moment, and finally, the back propagation algorithm is used to calculate the error between the predicted value and the actual value of the energy efficiency of the heating furnace.

[0223] Specifically, the heating furnace energy efficiency prediction model is a multilayer perceptron model. Multilayer perceptron (MLP) is an artificial neural network model, which consists of multiple neuron layers, each of which is fully connected to the previous and next layers. In MLP, the input layer receives input data, each input node represents a feature of the data, and the input data is passed through the hidden layer, which consists of multiple neurons. Each neuron receives input from the previous layer and applies an activation function to perform nonlinear transformation on the input. Finally, the output layer receives the output of the hidden layer and generates the final prediction result.

[0224] Preferably, constructing a heating furnace energy efficiency prediction model, inputting key factor parameters affecting the heating furnace energy efficiency into the heating furnace energy efficiency prediction model, and obtaining a predicted value of the heating furnace energy efficiency at a future time includes the following steps:

[0225] S531, selecting a matching heating furnace energy efficiency prediction model structure, and determining the number of key factor parameters affecting the heating furnace energy efficiency in the input layer, hidden layer, and output layer (i.e., the number of elements in the multilayer perceptron model);

[0226] S532, calculating the input key factor parameters of the hidden layer according to the input key factor parameters of the input layer (i.e., elements in the multilayer perceptron model), weights and biases;

[0227] Specifically, the formula for calculating the input key factor parameter of the hidden layer is:

[0228]

[0229] in, Represented as the input key factor parameters of the hidden layer;

[0230] Represented as the weight of the input layer;

[0231] j b Represented as the input key factor parameter of the input layer;

[0232] Represented as the bias of the input layer;

[0233] h represents the number of key factor parameters of the input layer;

[0234] i represents the number of key factor parameters of the hidden layer;

[0235] b and a represent the bth key factor parameter of the input layer and the ath key factor parameter of the hidden layer, respectively.

[0236] S533, calculating the input key factor parameters of the output layer according to the output key factor parameters, weights and biases of the hidden layer;

[0237] Specifically, the formula for calculating the input key factor parameters of the output layer is:

[0238]

[0239] in, Represented as the input key factor parameters of the output layer;

[0240] Represented as the weight of the hidden layer;

[0241] l a Represented as the output key factor parameters of the hidden layer;

[0242] Represented as the bias of the hidden layer;

[0243] n represents the number of key factor parameters of the output layer;

[0244] i represents the number of key factor parameters of the hidden layer;

[0245] r and a represent the rth key factor parameter of the output layer and the ath key factor parameter of the hidden layer, respectively.

[0246] S534, importing the input key factor parameters of the output layer into the activation function for solving, obtaining the output key factor parameters of the output layer, and using the output key factor parameters of the output layer as the predicted value of the energy efficiency of the heating furnace at a future moment;

[0247] S535. Calculate the error between the predicted value and the actual value of the heating furnace energy efficiency using an error algorithm, and adjust the parameters of the heating furnace energy efficiency prediction model using a gradient descent algorithm.

[0248] Specifically, the error algorithm is a back propagation algorithm, which is an algorithm used to train neural networks. According to the value of the loss function, the error is back propagated from the output layer to the hidden layer and the input layer. For the output layer, the relationship between the output error and the input of the output layer, that is, the gradient of the loss function, is calculated. Then the error is assigned to the previous layer, and the gradient of each layer is calculated in the same way until the input layer is reached.

[0249] Specifically, the gradient descent algorithm is used to minimize functions, especially in machine learning and deep learning to minimize the loss function. It reduces the value of the objective function by iteratively adjusting the parameters.

[0250] According to another embodiment of the present invention, Figure 2 As shown, a heating furnace energy-saving monitoring and prediction system based on digital twin technology is also provided. The heating furnace energy-saving monitoring and prediction system based on digital twin technology includes:

[0251] Data acquisition module 1, used to acquire relevant parameters of the heating furnace operation, build a digital twin model of the heating furnace, and input the acquired relevant parameters of the heating furnace operation into the digital twin model of the heating furnace;

[0252] Image generation module 2, used to simulate the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model, and generate an energy efficiency image of the heating furnace;

[0253] An image processing module 3 is used to preprocess the generated heating furnace energy efficiency image to obtain a heating furnace energy efficiency characteristic image;

[0254] The data analysis module 4 is used to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database by using an analysis algorithm to identify key factor parameters affecting the heating furnace energy efficiency;

[0255] Model building module 5, used to establish a heating furnace energy efficiency prediction model based on the identified key factor parameters affecting the heating furnace energy efficiency, and use the established heating furnace energy efficiency prediction model to predict the heating furnace energy efficiency changes at future moments;

[0256] The data acquisition module 1 is connected to the image processing module 3 via the image generation module 2 , and the image processing module 3 is connected to the model building module 5 via the data analysis module 4 .

[0257] To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention simulates the performance of the heating furnace under different working conditions in the digital twin model, and adjusts the design parameters of the heating furnace according to the simulation results, so as to realize the dynamic optimization of the operating parameters of the heating furnace. By optimizing the design parameters of the heating furnace, unnecessary energy consumption is reduced, thereby improving the overall efficiency. The energy efficiency loss detection of the optimized model is carried out by using the energy efficiency simulation tool, which is helpful to identify and eliminate the energy efficiency loss points and realize the efficient utilization of energy. By calculating the performance fitness and evaluating the advantages and disadvantages of the heating furnace design based on this, the best design scheme can be selected. An optimized energy efficiency model is established and the energy efficiency loss under preset operating conditions is simulated according to this model. It can provide accurate predictions for future operating performance, thereby reducing energy consumption and improving energy efficiency, which can significantly reduce operating costs and reduce environmental impact. The present invention assigns each heating furnace energy efficiency feature by normalization processing and weight, and calculates the grey correlation coefficient and correlation degree under ideal and non-ideal conditions, so as to accurately evaluate the influence of each energy efficiency feature on the total energy efficiency of the heating furnace, and the relative closeness of the ideal heating furnace energy efficiency state can help the operator understand the gap between the current heating furnace operation state and the optimal energy efficiency state, and adjust the operation strategy accordingly, and by identifying the key factor parameters affecting the heating furnace energy efficiency, energy-saving measures can be formulated in a targeted manner. The present invention uses historical data to train and test the heating furnace energy efficiency prediction model, which can accurately predict the energy efficiency changes at future moments, and by identifying and analyzing the key factor parameters affecting the heating furnace energy efficiency, the energy efficiency dynamics in the operation of the heating furnace can be better understood. The constructed heating furnace energy efficiency prediction model allows the operation state of the heating furnace to be monitored in real time, and the operation parameters are dynamically adjusted according to the prediction results. The dynamic adjustment and real-time monitoring mechanism helps to keep the heating furnace running in the optimal energy efficiency state, and respond quickly to emergencies. By accurately predicting the energy efficiency changes of the heating furnace, preventive measures can be taken before potential problems occur.

[0258] 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 principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A heating furnace energy-saving monitoring and prediction method based on digital twin technology, characterized in that: The heating furnace energy-saving monitoring and prediction method based on digital twin technology includes the following steps: S1. Obtain relevant parameters of the heating furnace operation, build a digital twin model of the heating furnace, and input the obtained relevant parameters of the heating furnace operation into the digital twin model of the heating furnace; S2. Simulate the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model, and generate an energy efficiency image of the heating furnace; S3, preprocessing the generated heating furnace energy efficiency image to obtain a heating furnace energy efficiency characteristic image; S4, using an analysis algorithm to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database, and identifying key factor parameters that affect the heating furnace energy efficiency; S5. Based on the identified key factor parameters affecting the energy efficiency of the heating furnace, a heating furnace energy efficiency prediction model is established, and the established heating furnace energy efficiency prediction model is used to predict the change of the heating furnace energy efficiency at future moments; The step of simulating the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model and generating the heating furnace energy efficiency loss image includes the following steps: S21, loading the optimization tool and energy efficiency simulation tool of the heating furnace digital twin model; S22. Based on the obtained relevant parameters of the heating furnace operation, simulate and analyze the digital twin model of the heating furnace; S23. If the simulation analysis results indicate that the performance of the heating furnace is unstable under the preset operating conditions, use the optimization tool to adjust the design parameters of the heating furnace in the heating furnace digital twin model; S24, after optimization, re-simulate and analyze to check whether the heating furnace structure meets the preset operating conditions. If not, continue to repeat S22 and S24 until the conditions are met; S25. Use an energy efficiency simulation tool to perform energy efficiency loss detection on the optimized digital twin model of the heating furnace. If the detection result shows that the energy efficiency loss meets the preset standard, save and export the optimized digital twin model of the heating furnace to obtain an optimized energy efficiency model of the heating furnace during operation; S26. Based on the obtained optimized energy efficiency model, use computer software to simulate the energy efficiency loss effect of the heating furnace under preset operating conditions, and generate an energy efficiency loss image of the heating furnace according to the simulation results; If the simulation analysis results indicate that the performance of the heating furnace is unstable under the preset operating conditions, using the optimization tool to adjust the design parameters of the heating furnace in the heating furnace digital twin model includes the following steps: S231. Starting an optimization algorithm in an optimization tool of the heating furnace digital twin model; S232. Based on the design parameters of the heating furnace in the digital twin model of the heating furnace, determine the size of the design variable set, and randomly select a set of initial design parameters as the initial design; S233, for each group of heating furnace design parameters, randomly adjust the design variables, and update the design parameters of each group of heating furnaces; S234, using simulation analysis tools to evaluate the performance of each group of heating furnace designs, and calculating the performance fitness by comparing the performance of each heating furnace design under operating conditions with the preset conditions; S235, evaluating the pros and cons of each group of heating furnace designs based on the calculated performance fitness; S236, finding the heating furnace design with the best performance, and recording the performance adaptability and corresponding design parameters of the best heating furnace design; S237. Adjust the parameters of other heating furnace designs according to the heating furnace design with the best performance, repeat steps S233 to S236 for iterative optimization, until the performance of the heating furnace design reaches or exceeds the preset operating conditions, and then terminate the optimization process.

2. According to claim 1, a heating furnace energy-saving monitoring and prediction method based on digital twin technology is characterized in that: The preprocessing of the generated heating furnace energy efficiency image to obtain the heating furnace energy efficiency characteristic image comprises the following steps: S31, removing noise from the generated heating furnace energy efficiency image by wavelet transform; S32, extracting an image sequence from the denoised heating furnace energy efficiency image, and performing grayscale processing on each frame of the image sequence to obtain a grayscale image; S33, using the Prewitt operator to calculate the edge gradient of each pixel in the grayscale image; S34, using a morphological gradient method to locally screen and enhance edge gradients, and setting a threshold to filter edge gradients to obtain a gradient image; S35, thinning and binarizing the gradient image, and taking the pixel points whose gradient values ​​are greater than the threshold as edge points; S36, connecting adjacent edge points into a connected domain, and obtaining a final edge image as a heating furnace energy efficiency feature image.

3. The heating furnace energy-saving monitoring and prediction method based on digital twin technology according to claim 1 is characterized in that: The method of analyzing the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database by using the analysis algorithm to identify the key factor parameters affecting the heating furnace energy efficiency includes the following steps: S41, obtaining a heating furnace energy efficiency characteristic image, and processing the obtained heating furnace energy efficiency characteristic images by normalization to calculate the normalized value of each characteristic; S42, assigning corresponding weights to the normalized features according to the importance of each heating furnace energy efficiency feature; S43, finding the ideal optimal value and the worst value of each heating furnace energy efficiency characteristic through the weighted characteristic value, which respectively constitute the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state; S44. For each heating furnace energy efficiency characteristic, calculate the grey correlation coefficient between each heating furnace energy efficiency characteristic and an ideal heating furnace energy efficiency state and an unideal heating furnace energy efficiency state; S45. Based on the grey correlation coefficient, the grey correlation degree between each heating furnace energy efficiency characteristic and the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state is calculated respectively; S46. Use grey correlation to construct the relative closeness of the ideal heating furnace energy efficiency state, evaluate the advantages and disadvantages of each heating furnace energy efficiency characteristic, and identify the key factor parameters that affect the heating furnace energy efficiency.

4. The heating furnace energy-saving monitoring and prediction method based on digital twin technology according to claim 3 is characterized in that: The formula for calculating the grey correlation between each heating furnace energy efficiency characteristic and the ideal heating furnace energy efficiency state and the non-ideal heating furnace energy efficiency state is: ; ; in, Indicates c The grey correlation between the energy efficiency characteristics of a heating furnace and the ideal energy efficiency state of the heating furnace; Indicates c The grey correlation between the energy efficiency characteristics of heating furnaces and the non-ideal energy efficiency status of heating furnaces; M represents the grey relational degree; d Indicates the energy efficiency characteristics of the heating furnace; W Represents the sum of the furnace energy efficiency characteristics.

5. The heating furnace energy-saving monitoring and prediction method based on digital twin technology according to claim 4 is characterized in that: The formula for constructing the relative closeness of the ideal heating furnace energy efficiency state is: ; in, Indicates c The relative closeness of the energy efficiency characteristics of a heating furnace to the ideal energy efficiency state of the heating furnace; B Indicates relative closeness; Indicates c The grey correlation between the energy efficiency characteristics of a heating furnace and the ideal energy efficiency state of the heating furnace; Indicates c The grey correlation between the energy efficiency characteristics of heating furnaces and the non-ideal energy efficiency status of heating furnaces; M Represents grey relational degree.

6. The heating furnace energy-saving monitoring and prediction method based on digital twin technology according to claim 1 is characterized in that: The method of establishing a heating furnace energy efficiency prediction model based on the identified key factor parameters affecting the heating furnace energy efficiency, and using the established heating furnace energy efficiency prediction model to predict the heating furnace energy efficiency change at a future moment includes the following steps: S51. Collect historical data related to heating furnace energy efficiency; S52, dividing the key factor parameters and historical data affecting the energy efficiency of the heating furnace into a training set and a test set; S53. Construct a heating furnace energy efficiency prediction model, input key factor parameters that affect the heating furnace energy efficiency into the heating furnace energy efficiency prediction model, and obtain a predicted value of the heating furnace energy efficiency at a future time.

7. The heating furnace energy-saving monitoring and prediction method based on digital twin technology according to claim 6 is characterized in that: The construction of the heating furnace energy efficiency prediction model, inputting the key factor parameters affecting the heating furnace energy efficiency into the heating furnace energy efficiency prediction model, and obtaining the heating furnace energy efficiency prediction value at a future moment includes the following steps: S531, selecting a matching heating furnace energy efficiency prediction model structure, and determining the number of key factor parameters affecting the heating furnace energy efficiency in the input layer, hidden layer, and output layer respectively; S532, calculating the input key factor parameters of the hidden layer according to the input key factor parameters, weights and biases of the input layer; S533, calculating the input key factor parameters of the output layer according to the output key factor parameters, weights and biases of the hidden layer; S534, importing the input key factor parameters of the output layer into the activation function for solving, obtaining the output key factor parameters of the output layer, and using the output key factor parameters of the output layer as the predicted value of the energy efficiency of the heating furnace at a future moment; S535. Calculate the error between the predicted value and the actual value of the heating furnace energy efficiency using an error algorithm, and adjust the parameters of the heating furnace energy efficiency prediction model using a gradient descent algorithm.

8. A heating furnace energy-saving monitoring and prediction system based on digital twin technology, used to implement the heating furnace energy-saving monitoring and prediction method based on digital twin technology according to any one of claims 1 to 7, characterized in that: The heating furnace energy-saving monitoring and prediction system based on digital twin technology includes: A data acquisition module is used to acquire relevant parameters of the heating furnace operation, build a digital twin model of the heating furnace, and input the acquired relevant parameters of the heating furnace operation into the digital twin model of the heating furnace; An image generation module is used to simulate the energy efficiency and energy consumption of the heating furnace under different working conditions in the heating furnace digital twin model and generate an energy efficiency image of the heating furnace; An image processing module is used to preprocess the generated heating furnace energy efficiency image to obtain a heating furnace energy efficiency characteristic image; A data analysis module is used to analyze the obtained heating furnace energy efficiency characteristic image with the corresponding heating furnace energy efficiency characteristic image in the database by using an analysis algorithm to identify key factor parameters affecting the heating furnace energy efficiency; A model building module is used to build a heating furnace energy efficiency prediction model based on the identified key factor parameters affecting the heating furnace energy efficiency, and use the built heating furnace energy efficiency prediction model to predict the heating furnace energy efficiency changes at future times; Among them, the data acquisition module is connected with the image processing module through the image generation module, and the image processing module is connected with the model establishment module through the data analysis module.

Citation Information

Patent Citations

  • Heating furnace energy-saving monitoring and predicting system and method based on digital twin

    CN116244953A