Temperature control method based on dynamic simulation of water-cooled wall of whole furnace

Abstract

The invention provides a temperature control method based on dynamic simulation of a water-cooled wall of a whole furnace, and relates to the technical field of safety protection of water-cooled walls. The method comprises the following steps: collecting structure parameters and circulation parameters of a whole-furnace water-cooled wall; establishing a heat exchange model, simulating temperature distribution of the water cooling wall, and constructing a dynamic simulation model; identifying a risk area; constructing a prediction model to predict the prediction temperature of the risk area; and setting an adjustment threshold value and an early warning threshold value, executing dynamic adjustment of the cycle parameters and triggering alarm. According to the method, risk area identification, risk area temperature prediction and threshold setting are carried out on the whole-furnace water cooling wall, the limitation of a traditional method is exceeded, the potential of a modern automatic control technology in industrial application is shown, meanwhile, the scientificity and the intelligent level of whole-furnace water cooling wall temperature control are improved, and the method is suitable for popularization and application. And the enterprise operation efficiency is improved, and powerful support is provided for guaranteeing safe and stable operation of equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of water - wall safety protection, and particularly to a temperature control method based on dynamic simulation of the whole - furnace water - wall. Background Art

[0002] The whole - furnace water - wall is a commonly used heat - exchange device in high - temperature and high - pressure processes such as electric power and petrochemical industries. Its main function is to effectively transfer the heat generated by the combustion flame to the cooling water, thus ensuring the safe and stable operation of the furnace body. The water - wall usually uses water as the cooling medium, and the heat is carried away by the water flow inside it to prevent the water - wall material from being damaged due to overheating. In a power plant, the heat generated by the combustion of fuel is used to heat the circulating water through the water - wall, and the circulating water is converted into steam in the boiler and then used to drive a steam turbine for power generation. The whole - furnace water - wall structure is usually welded by steel pipes, which has good thermal conductivity and strength and can withstand high - temperature and high - pressure environments. The design and operation effect of the whole - furnace water - wall are affected by various factors, including the cooling water flow rate, the inlet water temperature, and the water flow state, etc. In order to improve the heat - exchange efficiency, the design of the water - wall usually requires good hydrodynamic performance to ensure that the cooling water can form a turbulent flow inside the pipeline to achieve the best heat - transfer effect. However, the intense working environment and complex fluid dynamics make the whole - furnace water - wall face many challenges in temperature control.

[0003] Traditional temperature control systems usually rely on a single temperature sensor for monitoring, resulting in inaccurate and limited data. For the whole - furnace water - wall spanning a large area, local temperature fluctuations often cannot be reflected by a single sensor, easily causing information lag or misjudgment, thus affecting the cooling effect of the entire system. The existing technologies do not fully consider the complex non - linear characteristics in fluid dynamics and heat conduction. When dealing with dynamically changing working conditions, the response speed is slow and the prediction accuracy is low, making it difficult to meet the requirements of real - time control. Summary of the Invention

[0004] The present invention provides a temperature control method based on dynamic simulation of the whole - furnace water - wall to solve the defects existing in the prior art.

[0005] The present invention provides a temperature control method based on dynamic simulation of the whole - furnace water - wall, including: Real - time collect the structural parameters and circulation parameters of the whole - furnace water - wall, and pre - process the structural parameters and circulation parameters to obtain pre - processed data.

[0006] According to the pre - processed data, combined with the theories of fluid dynamics and heat conduction, establish a heat - exchange model, simulate the temperature distribution of the water - wall, and construct a dynamic simulation model of the whole - furnace water - wall.

[0007] According to the temperature distribution of the water - wall and combined with the structural parameters, identify the areas prone to temperature anomalies as risk areas.

[0008] Collect the temperature data of the risk area in real time, construct a prediction model based on a convolutional neural network, and use the Bayesian optimization algorithm to optimize the hyperparameters of the prediction model. Input the preprocessed data and the real-time temperature data of the risk area, and output the predicted temperature data of the risk area at the next moment.

[0009] Set the adjustment threshold and warning threshold of the risk area according to the performance parameters of the whole furnace water wall. When the predicted temperature data reaches the adjustment threshold, introduce an adaptive adjustment mechanism to dynamically adjust the circulation parameters. When the predicted temperature reaches the warning threshold, trigger an alarm.

[0010] According to the temperature control method based on the dynamic simulation of the whole furnace water wall provided by the present invention, the structural parameters include geometric structure data and thermophysical parameters; the thermophysical parameters include thermal conductivity and specific heat capacity; the circulation parameters include flow velocity data, flow rate data and temperature data of the cooling water in the water wall water circulation.

[0011] According to the temperature control method based on the dynamic simulation of the whole furnace water wall provided by the present invention, the process of preprocessing the structural parameters and circulation parameters includes: Adopt the Kalman filter algorithm to remove the random noise in the structural parameters and circulation parameters, and use the Z-score method to identify and remove the outliers in the structural parameters and circulation parameters.

[0012] Adopt the moving average method to smooth the structural parameters and circulation parameters, and use data normalization to convert the structural parameters and circulation parameters to a unified range.

[0013] Adopt the interpolation method to process the missing values in the structural parameters and circulation parameters to obtain a complete data set, and use the complete data set as the preprocessed data.

[0014] According to the temperature control method based on the dynamic simulation of the whole furnace water wall provided by the present invention, the process of simulating the temperature distribution of the water wall includes: Use the hydrodynamic equation to obtain the velocity field and pressure field of the cooling water flowing inside the water wall.

[0015] According to the velocity field and pressure field, establish a heat conduction model in combination with Fourier's law.

[0016] According to the heat exchange principle, combine the heat conduction model with the hydrodynamic model to establish a heat exchange model of the water wall.

[0017] Set the boundary conditions and initial conditions. The boundary conditions include the temperature and flow rate at the inlet of the water wall and the temperature and flow rate at the outlet.

[0018] Use the finite difference method to solve the heat exchange model to obtain the temperature distribution of the water wall.

[0019] According to the temperature control method based on the dynamic simulation of the whole furnace water-cooled wall provided by the present invention, the process of constructing the dynamic simulation model of the whole furnace water-cooled wall includes: Set the three-dimensional simulation basic model framework according to the preprocessed data.

[0020] Combined with the fluid dynamics and heat conduction theories, establish a set of equations describing the change of the water-cooled wall temperature over time, including a flow equation and a heat conduction equation.

[0021] Take the temperature distribution of the water-cooled wall as the initial standard of the three-dimensional simulation basic model, and take the flow velocity and flow rate of the water-cooled wall water circulation as the boundary standard.

[0022] Set the time step and perform dynamic simulation on the three-dimensional simulation basic model.

[0023] Solve the set of equations by the finite element method to generate time series data of the water-cooled wall temperature, and obtain the dynamic simulation model of the whole furnace water-cooled wall.

[0024] According to the temperature control method based on the dynamic simulation of the whole furnace water-cooled wall provided by the present invention, the process of identifying the risk area includes: Divide the dynamic simulation model of the whole furnace water-cooled wall into regions.

[0025] Collect the temperature data of each region of the dynamic simulation model of the whole furnace water-cooled wall in real time, and generate the temperature time series curve of each region and the spatial distribution map of the whole furnace water-cooled wall.

[0026] According to the fluid dynamics combined with the spatial distribution map, obtain the flow state data in each region.

[0027] Establish a risk coefficient calculation model, and obtain the risk coefficient of each region according to the average temperature, peak temperature, flow state data and structural parameters of each region.

[0028] Take the region where the risk coefficient reaches the preset risk coefficient threshold as the risk area.

[0029] According to the temperature control method based on the dynamic simulation of the whole furnace water-cooled wall provided by the present invention, the process of constructing a prediction model based on a convolutional neural network includes: Collect the historical structural parameters, historical cycle parameters and historical temperature data of the risk area of the whole furnace water-cooled wall, and the temperature data of the risk area at the next moment corresponding to the historical temperature data.

[0030] Preprocess the collected historical structural parameters, historical cycle parameters, historical temperature data of the risk area and temperature data of the risk area at the next moment, and divide them into a training set and a test set.

[0031] Build a basic model of a convolutional neural network, including an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input layer is used to receive preprocessed input data, which includes historical structure parameters, historical cycle parameters, and historical temperature data of the risk area. The convolutional layer includes multiple convolutional kernels for feature extraction from the input data to generate feature maps. The pooling layer is used to reduce the spatial dimension of the feature maps. The fully connected layer is used to integrate the extracted features. The output layer is used to output a prediction result based on the integration result.

[0032] Use a training set to train the basic model of the convolutional neural network, retain the model parameters that meet the prediction accuracy, and obtain a prediction model.

[0033] According to the temperature control method based on the dynamic simulation of the whole furnace water wall provided by the present invention, the process of using the Bayesian optimization algorithm to optimize the hyperparameters of the prediction model includes: Define the hyperparameter space, take the learning rate, the number of convolutional layers, the size of the convolutional kernels, and the regularization parameter as the hyperparameters to be optimized, and set the value range for each hyperparameter.

[0034] Use the Gaussian process to randomly select several initial sample points in the hyperparameter space, and each initial sample point represents a combination of hyperparameters.

[0035] Take each initial sample point as the hyperparameters of the prediction model, calculate the corresponding objective function value, and the objective function value is the loss function.

[0036] Construct a surrogate model based on the initial sample points and their corresponding objective function values.

[0037] Find the next sample point in the hyperparameter space according to the surrogate model.

[0038] Train the prediction model with the hyperparameter combination represented by the new sample point, evaluate the objective function, and feedback it to the surrogate model.

[0039] Repeat the process of finding the next sample point, training, and evaluation until the preset number of repetitions is reached, and take the hyperparameter combination represented by the sample point with the minimum objective function as the hyperparameter combination of the prediction model.

[0040] According to the temperature control method based on the dynamic simulation of the whole furnace water wall provided by the present invention, the process of setting the adjustment threshold and the warning threshold for the risk area includes: collecting the performance parameters of the whole furnace water wall, and the performance parameters include the maximum safe temperature, the minimum safe temperature, and the expected normal operating temperature range. Take the expected normal operating temperature range as the adjustment threshold, and take the maximum safe temperature and the minimum safe temperature as the warning thresholds.

[0041] According to the temperature control method based on the dynamic simulation of the full furnace water wall provided by the present invention, the process of dynamically adjusting the circulation parameters includes: increasing the cooling water flow rate of the water wall, enhancing the heat exchange capacity, and reducing the local temperature of the water wall. Adjusting the circulation pressure of the cooling water, increasing the flow rate of the cooling water passing through the water wall, and optimizing the cooling effect.

[0042] The temperature control method, device, and storage medium based on the dynamic simulation of the full furnace water wall provided by the present invention can provide comprehensive and real system state information by collecting the structural parameters and circulation parameters of the full furnace water wall in real time, laying a foundation for subsequent data analysis and modeling. Combining fluid dynamics and heat conduction theory, by establishing a heat exchange model and simulating the temperature distribution of the full furnace water wall, it can more accurately identify potential temperature abnormal areas, improve the depth of understanding of the behavior of the cooling system, and help operators intervene in advance before potential risks occur, thereby reducing the possibility of accidents. By real-time monitoring the temperature data of the risk area and combining the constructed convolutional neural network prediction model, adding the Bayesian optimization algorithm for hyperparameter optimization to ensure the accuracy and stability of temperature prediction. The prediction method based on deep learning can capture complex patterns in temperature changes, so as to provide a more sensitive and effective response in a real-time changing environment. When the temperature data output by the prediction model approaches or exceeds the set adjustment threshold, an adaptive adjustment mechanism is automatically introduced to dynamically adjust the circulation parameters to ensure that the temperature of the water wall always remains within the safe range. This not only increases the flexibility and intelligence of the cooling system, but also significantly enhances the overall safety of the equipment, effectively avoiding equipment damage or safety accidents caused by temperature abnormalities. When the predicted temperature in the risk area reaches the warning threshold, an alarm will be immediately triggered to quickly notify the operator to take corresponding emergency measures. This makes temperature control not only limited to the analysis of historical and current data, but also provides a scientific basis for real-time processing and response, forming a closed loop of data monitoring, analysis, and response, exceeding the limitations of traditional methods, and demonstrating the potential of modern automation control technology in industrial applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0044] Figure 1 It is a schematic flowchart of the temperature control method based on the dynamic simulation of the full furnace water wall provided by the embodiments of the present invention; Figure 2 It is a schematic flowchart of simulating the temperature distribution of the water wall in the embodiments of the present invention; Figure 3 It is a schematic flow chart of constructing a dynamic simulation model of the whole furnace water-cooled wall in an embodiment of the present invention. Specific embodiments

[0045] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts belong to the scope of protection of the present invention.

[0046] The following will be combined with Figures 1 - 3 Describe the temperature control method of the present invention based on dynamic simulation of the whole furnace water-cooled wall.

[0047] Figure 1 It is a schematic structural diagram of the temperature control method based on dynamic simulation of the whole furnace water-cooled wall provided by an embodiment of the present invention.

[0048] As Figure 1 shown, the temperature control method based on dynamic simulation of the whole furnace water-cooled wall provided by an embodiment of the present invention includes: Collect the structural parameters and circulation parameters of the whole furnace water-cooled wall in real time, and preprocess the structural parameters and circulation parameters to obtain preprocessed data.

[0049] The structural parameters include geometric structure data and thermophysical parameters. The thermophysical parameters include thermal conductivity and specific heat capacity. The circulation parameters include flow velocity data, flow rate data of the water circulation in the water-cooled wall, and temperature data of the cooling water.

[0050] The process of preprocessing the structural parameters and circulation parameters includes: Adopt the Kalman filter algorithm to remove the random noise in the structural parameters and circulation parameters, and use the Z-score method to identify and remove the outliers in the structural parameters and circulation parameters.

[0051] Adopt the moving average method to smooth the structural parameters and circulation parameters, and use data normalization to convert the structural parameters and circulation parameters to a unified range.

[0052] Adopt the interpolation method to process the missing values in the structural parameters and circulation parameters to obtain a complete data set, and use the complete data set as the preprocessed data.

[0053] Through various sensors and monitoring devices installed on the water-cooled wall, the flow rate, temperature, and pressure parameters of the cooling water, as well as the material properties and pipeline structure of the water-cooled wall, are accurately obtained. Through real-time monitoring, detailed operation status data can be obtained. By performing data cleaning, removing outliers and missing values, the effectiveness and accuracy of the data are ensured. Techniques such as standardization and normalization are used to reduce the dimensional differences of different parameters, making the model construction more robust. The preprocessed data can comprehensively reflect the actual working state of the water-cooled wall, laying a solid foundation for establishing a heat exchange model.

[0054] Based on the preprocessed data, combined with the theories of fluid dynamics and heat conduction, a heat exchange model is established to simulate the temperature distribution of the water-cooled wall, and a dynamic simulation model of the entire furnace water-cooled wall is constructed.

[0055] Figure 2 It is a schematic flow chart of simulating the temperature distribution of the water-cooled wall in the embodiment of the present invention.

[0056] As Figure 2 shown, the process of simulating the temperature distribution of the water-cooled wall includes: Using the fluid dynamics equation, the velocity field and pressure field of the cooling water flowing inside the water-cooled wall are obtained.

[0057] Based on the velocity field and pressure field, a heat conduction model is established in combination with Fourier's law.

[0058] According to the heat exchange principle, the heat conduction model is combined with the fluid dynamics model to establish a heat exchange model of the water-cooled wall.

[0059] Boundary conditions and initial conditions are set. The boundary conditions include the temperature and flow rate at the inlet of the water-cooled wall and the temperature and flow rate at the outlet.

[0060] The finite difference method is used to solve the heat exchange model to obtain the temperature distribution of the water-cooled wall.

[0061] Figure 3 It is a schematic flow chart of constructing a dynamic simulation model of the entire furnace water-cooled wall in the embodiment of the present invention.

[0062] As Figure 3 shown, the process of constructing a dynamic simulation model of the entire furnace water-cooled wall includes: Set the framework of the three-dimensional simulation basic model according to the preprocessed data.

[0063] Combined with the theories of fluid dynamics and heat conduction, a set of equations describing the change of the water-cooled wall temperature over time is established. The set of equations includes a flow equation and a heat conduction equation.

[0064] The temperature distribution of the water-cooled wall is used as the initial standard of the three-dimensional simulation basic model, and the flow velocity and flow rate of the water-cooled wall water circulation are used as the boundary standards.

[0065] Set the time step and perform dynamic simulation on the three-dimensional simulation basic model.

[0066] Solve the system of equations by the finite element method to generate time series data of the water wall temperature and obtain the dynamic simulation model of the whole furnace water wall.

[0067] Combined with fluid dynamics and heat conduction theory, construct a heat exchange model to realize the temperature distribution simulation of the whole furnace water wall. By analyzing the flow characteristics and heat transfer process of the cooling water, the model can depict the temperature change trend at each position. It not only provides important reference data for actual operation, but also can immediately reflect the possible temperature abnormal areas. Through continuously updated preprocessing data and model output, the temperature distribution of the whole furnace water wall can be captured in real time, thus prompting the system to identify and warn of potential risks in advance. It provides a scientific basis for subsequent risk area definition and temperature prediction.

[0068] Based on the temperature distribution of the water wall and combined with the structural parameters, identify the areas prone to temperature anomalies as risk areas.

[0069] The process of identifying risk areas includes: Divide the dynamic simulation model of the whole furnace water wall into regions.

[0070] Collect the temperature data of each region of the dynamic simulation model of the whole furnace water wall in real time to generate the temperature time series curve of each region and the spatial distribution map of the whole furnace water wall.

[0071] Based on fluid dynamics and combined with the spatial distribution map, obtain the flow state data in each region.

[0072] Establish a risk coefficient calculation model, and obtain the risk coefficient of each region according to the average temperature, peak temperature, flow state data and structural parameters of each region.

[0073] Regard the regions whose risk coefficients reach the preset risk coefficient threshold as risk areas.

[0074] According to the simulation results of the heat exchange model, the system can identify the areas prone to temperature anomalies and define them as risk areas. By real-time collecting the temperature data of these risk areas, the local temperature state can be grasped in the first time, improving the sensitivity to temperature fluctuations. It can effectively focus the attention on the key risk areas, avoid indiscriminate monitoring of the whole water wall, and save resources and time. By focusing on monitoring these areas, a faster response can be made, improving the effectiveness and pertinence of temperature control.

[0075] Collect the temperature data of the risk area in real time, construct a prediction model based on a convolutional neural network, and use the Bayesian optimization algorithm to optimize the hyperparameters of the prediction model. Input the preprocessed data and the real-time temperature data of the risk area, and output the predicted temperature data of the risk area at the next moment.

[0076] The process of constructing a prediction model based on a convolutional neural network includes: Collect the historical structural parameters, historical circulation parameters of the entire furnace water wall, and the historical temperature data of the risk area, as well as the temperature data of the risk area at the next moment corresponding to the historical temperature data.

[0077] Preprocess the collected historical structural parameters, historical circulation parameters, historical temperature data of the risk area, and temperature data of the risk area at the next moment, and divide them into a training set and a test set.

[0078] Construct a basic convolutional neural network model, including an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input layer is used to receive the preprocessed input data, and the input data includes historical structural parameters, historical circulation parameters, and historical temperature data of the risk area. The convolutional layer includes multiple convolutional kernels, which are used to extract features from the input data to generate a feature map. The pooling layer is used to reduce the spatial dimension of the feature map. The fully connected layer is used to integrate the extracted features. The output layer is used to output the prediction result according to the integration result.

[0079] Use the training set to train the basic convolutional neural network model, retain the model parameters that meet the prediction accuracy, and obtain the prediction model.

[0080] The process of using the Bayesian optimization algorithm to optimize the hyperparameters of the prediction model includes: Define the hyperparameter space, take the learning rate, the number of convolutional layers, the size of the convolutional kernel, and the regularization parameter as the hyperparameters to be optimized, and set the value range for each hyperparameter.

[0081] Use the Gaussian process to randomly select several initial sample points in the hyperparameter space, and each initial sample point represents a set of hyperparameter combinations.

[0082] Take each initial sample point as the hyperparameters of the prediction model, calculate the corresponding objective function value, and the objective function value is the loss function.

[0083] Construct a surrogate model according to the initial sample points and their corresponding objective function values.

[0084] Find the next sample point in the hyperparameter space according to the surrogate model.

[0085] Train the prediction model with the hyperparameter combination represented by the new sample point, evaluate the objective function, and feedback it to the surrogate model.

[0086] Repeat the process of finding the next sample point, training, and evaluation until the preset number of repetitions is reached. Take the hyperparameter combination represented by the sample point with the minimum objective function as the hyperparameter combination of the prediction model.

[0087] Constructing a temperature prediction model based on a convolutional neural network can utilize historical data and real-time collected data to learn complex patterns of temperature changes. By introducing the Bayesian optimization algorithm to optimize the hyperparameters of the model, it ensures that it can maintain a high prediction accuracy under various working conditions. The realization of the prediction function helps to give early warnings and make adjustments before the temperature reaches the threshold. It realizes the early prediction of temperature changes and significantly improves the response speed compared with traditional methods. When the prediction result shows that the set adjustment threshold is about to be reached, the system can take active measures to reduce potential risks.

[0088] Set the adjustment threshold and warning threshold for the risk area according to the performance parameters of the whole furnace water wall. When the predicted temperature data reaches the adjustment threshold, introduce an adaptive adjustment mechanism to dynamically adjust the circulation parameters. When the predicted temperature reaches the warning threshold, trigger an alarm.

[0089] The process of setting the adjustment threshold and warning threshold for the risk area includes: collecting the performance parameters of the whole furnace water wall, and the performance parameters include the maximum safe temperature, the minimum safe temperature, and the expected normal operating temperature range. Take the expected normal operating temperature range as the adjustment threshold, and take the maximum safe temperature and the minimum safe temperature as the warning thresholds.

[0090] The process of dynamically adjusting the circulation parameters includes: increasing the cooling water flow rate of the water wall, enhancing the heat exchange capacity, and reducing the local temperature of the water wall. Adjust the circulation pressure of the cooling water, increase the flow rate of the cooling water through the water wall, and optimize the cooling effect.

[0091] When the predicted temperature reaches the set adjustment threshold, introduce an adaptive adjustment mechanism to dynamically adjust the circulation parameters. Enable the system to flexibly adjust key parameters such as flow rate and pressure according to real-time data, and take corresponding measures in a timely manner when the temperature is abnormal, greatly enhancing the safety and stability of the system. At the same time, the set warning threshold ensures that an alarm can be triggered when the temperature is too high, quickly notifying the system operator to take emergency measures. Through the active temperature control and risk management mechanism, this solution can effectively prevent the occurrence of equipment damage or safety accidents, and improve the operation reliability and life of the whole furnace water wall.

[0092] Example 1: Target water wall A, geometric structure data: water wall height: 15m, water wall diameter: 0.5m. Thermal property parameters: thermal conductivity: 50W / (m·K), specific heat capacity: 4200J / (kg·K). Circulation parameters: water circulation flow rate data: 2.5m / s, flow rate data: 30m³ / h, cooling water temperature data: 85°C.

[0093] The Kalman filter algorithm was used to remove random noise, and smooth flow velocity data was obtained.

[0094] The Z-score method was used to identify and remove outliers. An outlier (3.5 m / s) was found in the flow velocity data and has been removed.

[0095] After moving average processing, the flow velocity data became: 2.4 m / s, 2.5 m / s, 2.6 m / s.

[0096] After data normalization, the range of the flow velocity data was adjusted to [0, 1], and after conversion, it became: 0.0, 0.5, 1.0.

[0097] The interpolation method was used to handle missing values, and a complete data set was obtained.

[0098] The hydrodynamic equations were used to obtain the velocity field and pressure field of the cooling water flowing inside the water wall. At a certain moment, the velocity field was: v(x) = 2.5 - 0.1x (m / s), where x is the height of the water wall.

[0099] Based on the velocity field and pressure field, a heat conduction model was established in combination with Fourier's law.

[0100] Boundary conditions were set: inlet temperature: 85 °C, flow rate: 30 m³ / h, outlet temperature: 75 °C, flow rate: 30 m³ / h.

[0101] The finite difference method was used to solve the heat exchange model, and the temperature distribution of the water wall was obtained as: T(x) = 85 - 10(x / 15), where T is the temperature (°C) and x is the height (m).

[0102] The dynamic simulation model of the whole furnace water wall was divided into regions, divided into 5 regions (each 3 m as a region).

[0103] Temperature data of each region was collected in real time. The generated temperature time series curve shows: Region 1: 82 °C, Region 2: 80 °C, Region 3: 78 °C, Region 4: 76 °C, Region 5: 75 °C.

[0104] Based on hydrodynamics combined with the spatial distribution map, the flow state data was obtained, and it was found that the flow state in Region 3 was weak.

[0105] The risk coefficient calculation model obtained: Risk coefficient of Region 1: 0.2, Risk coefficient of Region 2: 0.3, Risk coefficient of Region 3: 0.6 (exceeding the threshold, marked as a risk region), Risk coefficient of Region 4: 0.4, Risk coefficient of Region 5: 0.2.

[0106] Historical structure parameters (data for the past week): Geometric structure data: Height of the water wall: 20 m, Diameter of the water wall: 0.6 m. Thermal property parameters: Thermal conductivity: 55 W / (m·K), Specific heat capacity: 3900 J / (kg·K). Historical cycle parameters (flow rate and flow velocity): Flow velocity data (m / s): [2.8, 3.0, 3.1, 2.9, 2.7, 3.2, 3.0], Flow rate data (m³ / h): [35, 40, 38, 37, 40, 41, 39], Historical temperature data in the risk area (°C): [87, 86, 85, 88, 87, 89, 90], Temperature data at the next moment in the risk area (predicted, °C): [87, 88, 90, 91, 92, 90, 89].

[0107] Preprocess the historical data, remove noise, check for outliers, and normalize the data. The results are as follows: Normalized historical flow velocity: [0.0, 0.08, 0.1, 0.04, -0.08, 0.16, 0.08] (schematic data).

[0108] Normalized historical temperature data: [0.0, 0.02, 0.04, 0.06, 0.05, 0.07, 0.08].

[0109] Divide the data into a training set and a test set: Training set: The first 5 records of the historical flow velocity and temperature data.

[0110] Test set: The last 2 records of the historical flow velocity and temperature data.

[0111] Build a basic convolutional neural network model: Network structure: Input layer: Receives the preprocessed data, including historical structure parameters, cycle parameters, and historical temperature data in the risk area. Convolutional layer: Uses 3 convolutional kernels to extract features for detecting the relationship between flow velocity and temperature. Pooling layer: Uses max pooling to reduce the feature dimension. Fully connected layer: Integrates the extracted features and outputs the predicted temperature at the next moment in the risk area. Output layer: Generates the prediction result for the temperature in the risk area at the next moment.

[0112] Use the training set to train the convolutional neural network model and retain the model parameters with a prediction accuracy of over 95%. Example output of the trained model: Predicted values (°C): [89, 90], corresponding to the temperature in the risk area of the test set.

[0113] Define the hyperparameter space: Hyperparameters to be optimized include: Learning rate: Range (0.001, 0.1), Number of convolutional layers: 2 to 5 layers, Convolutional kernel size: 3 to 7, Regularization parameter: Range (0.01, 0.1).

[0114] Randomly select several combinations of hyperparameters for preliminary evaluation: Sample point 1: Learning rate 0.01, number of convolutional layers 3, convolutional kernel size 5, regularization parameter 0.05.

[0115] Sample point 2: Learning rate 0.005, number of convolutional layers 4, convolutional kernel size 7, regularization parameter 0.01.

[0116] Train the models corresponding to each sample point and calculate the loss function. The records are as follows: Loss value of sample point 1: 0.025.

[0117] Loss value of sample point 2: 0.020.

[0118] Construct a Gaussian process model based on the initial sample points and their objective function values to search the hyperparameter space.

[0119] Find new combination points and train. Repeat the process until the set number of training rounds is reached, and finally determine the combination of hyperparameters.

[0120] Collect the performance parameters of the whole furnace water wall: Maximum safe temperature: 97°C, minimum safe temperature: 75°C, normal operating temperature range: 80°C to 90°C.

[0121] Adjust the threshold (normal range) to 80°C to 90°C.

[0122] Set the warning threshold to 75°C (minimum safety) and 97°C (maximum safety).

[0123] When the predicted temperature reaches the adjusted threshold (90°C), dynamically adjust the circulation parameters of the water wall: Increase the cooling water flow rate: Increase from 2.5 m / s to 3.0 m / s to enhance the heat exchange capacity. Increase the circulation pressure to increase the flow rate and optimize the cooling effect.

[0124] Set an alarm mechanism. When the predicted value of the temperature data is close to the warning threshold (97°C), trigger an alarm: Output the warning message: "Warning! The temperature in water wall area 3 is approaching the safety limit. Please immediately check and adjust the cooling system."

[0125] In summary, this embodiment provides a temperature control method based on the dynamic simulation of the full furnace water wall. By collecting the structural parameters and circulation parameters of the full furnace water wall in real time, it can provide comprehensive and real system state information, laying a foundation for subsequent data analysis and modeling. Combining fluid dynamics and heat conduction theory, by establishing a heat exchange model to simulate the temperature distribution of the full furnace water wall, it can more accurately identify possible temperature abnormal areas, enhancing the depth of understanding of the behavior of the cooling system, helping operators intervene in advance before potential risks occur, thereby reducing the likelihood of accidents. By monitoring the temperature data of the risk area in real time and combining the constructed convolutional neural network prediction model, adding the Bayesian optimization algorithm for hyperparameter optimization to ensure the accuracy and stability of temperature prediction. The prediction method based on deep learning can capture complex patterns in temperature changes, thus providing a more sensitive and effective response in a real-time changing environment. When the temperature data output by the prediction model approaches or exceeds the set adjustment threshold, an adaptive adjustment mechanism is automatically introduced to dynamically adjust the circulation parameters to ensure that the temperature of the water wall always remains within the safe range. This not only increases the flexibility and intelligence of the cooling system but also significantly enhances the overall safety of the equipment, effectively avoiding equipment damage or safety accidents caused by temperature abnormalities. When the predicted temperature in the risk area reaches the warning threshold, an alarm will be immediately triggered to quickly notify the operator to take corresponding emergency measures. This makes the temperature control not only limited to the analysis of historical and current data but also provides a scientific basis for real-time processing and response, forming a closed loop of data monitoring, analysis, and response, transcending the limitations of traditional methods and demonstrating the potential of modern automation control technology in industrial applications.

[0126] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0127] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A temperature control method based on dynamic simulation of the whole furnace water-cooled wall, characterized in that: include: Collecting structural parameters and circulation parameters of the whole furnace water-cooled wall in real time, and preprocessing the structural parameters and the circulation parameters to obtain preprocessing data; According to the preprocessed data, combined with fluid dynamics and heat conduction theory, a heat exchange model is established to simulate the temperature distribution of the water-cooled wall, and a dynamic simulation model of the water-cooled wall of the whole furnace is constructed; According to the temperature distribution of the water-cooled wall and the structural parameters, an area prone to temperature anomaly is identified as a risk area; The temperature data of the risk area is collected in real time, a prediction model based on a convolutional neural network is constructed, and the hyperparameters of the prediction model are optimized using a Bayesian optimization algorithm, the preprocessed data and the real-time temperature data of the risk area are input, and the predicted temperature data of the risk area at the next moment is output; The adjustment threshold and warning threshold of the risk area are set according to the performance parameters of the water-cooled wall of the entire furnace. When the predicted temperature data reaches the adjustment threshold, an adaptive adjustment mechanism is introduced to dynamically adjust the circulation parameters; when the predicted temperature reaches the warning threshold, an alarm is triggered.

2. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The structural parameters include geometric structure data and thermophysical parameters; the thermophysical parameters include thermal conductivity and specific heat capacity; the circulation parameters include flow rate data, flow rate data and temperature data of cooling water in the water-cooled wall water circulation.

3. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of preprocessing the structural parameters and the cycle parameters includes: A Kalman filter algorithm is used to remove random noise in the structural parameters and the circulation parameters, and a Z-score method is used to identify and remove abnormal values ​​in the structural parameters and the circulation parameters; The structural parameters and the cyclic parameters are smoothed by a moving average method, and the structural parameters and the cyclic parameters are converted to a uniform range by data normalization; An interpolation method is used to process missing values ​​in the structural parameters and the circulation parameters to obtain a complete data set, and the complete data set is used as the preprocessed data.

4. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of simulating the temperature distribution of the water wall includes: Use fluid dynamics equations to obtain the velocity field and pressure field of cooling water flowing inside the water wall; According to the velocity field and the pressure field, a heat conduction model is established in combination with Fourier's law; According to the heat exchange principle, the heat conduction model is combined with the fluid dynamics model to establish a heat exchange model of the water-cooled wall; Setting boundary conditions and initial conditions, wherein the boundary conditions include the temperature and flow rate of the water wall inlet and the temperature and flow rate of the water wall outlet; The heat exchange model is solved using the finite difference method to obtain the temperature distribution of the water-cooled wall.

5. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of building a dynamic simulation model of the entire furnace water wall includes: Setting a three-dimensional simulation basic model framework according to the preprocessed data; Combining fluid dynamics and heat conduction theory, a set of equations describing the change of water-cooled wall temperature over time is established, wherein the set of equations includes a flow equation and a heat conduction equation; The temperature distribution of the water-cooled wall is used as the initial standard of the three-dimensional simulation basic model, and the flow rate and flow rate of the water circulation of the water-cooled wall are used as the boundary standard; Setting a time step to dynamically simulate the three-dimensional simulation basic model; The equation group is solved by the finite element method to generate time series data of the water-cooled wall temperature and obtain a dynamic simulation model of the water-cooled wall of the entire furnace.

6. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of identifying the risk areas includes: Divide the dynamic simulation model of the whole furnace water-cooled wall into regions; Collect temperature data of each area of ​​the dynamic simulation model of the whole furnace water-cooled wall in real time, generate temperature time series curves of each area and spatial distribution diagram of the whole furnace water-cooled wall; According to fluid dynamics combined with the spatial distribution map, flow state data in each area is obtained; A risk factor calculation model is established to obtain the risk factor of each area based on the average temperature, peak temperature, flow state data and structural parameters of each area; The area whose risk factor reaches the preset risk factor threshold is regarded as the risk area.

7. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of building a prediction model based on a convolutional neural network includes: Collect historical structural parameters, historical circulation parameters and historical temperature data of the risk area of ​​the whole furnace water-cooled wall, and the temperature data of the risk area at the next moment corresponding to the historical temperature data; Preprocess the collected historical structural parameters, historical cycle parameters, historical temperature data of risk areas, and temperature data of risk areas at the next moment, and divide them into training sets and test sets; Construct a convolutional neural network basic model, including an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer; the input layer is used to receive preprocessed input data, and the input data includes historical structural parameters, historical circulation parameters and historical temperature data of risk areas; the convolution layer includes multiple convolution kernels, which are used to extract features from the input data and generate feature maps; the pooling layer is used to reduce the spatial dimension of the feature map; the fully connected layer is used to integrate the extracted features; the output layer is used to output prediction results according to the integration results; The convolutional neural network basic model is trained using the training set, and the model parameters that meet the prediction accuracy are retained to obtain a prediction model.

8. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of optimizing the hyperparameters of the prediction model using the Bayesian optimization algorithm includes: Define the hyperparameter space, take the learning rate, number of convolutional layers, convolution kernel size and regularization parameter as the hyperparameters that need to be optimized, and set the value range for each hyperparameter; Using a Gaussian process to randomly select a number of initial sample points in the hyperparameter space, each of the initial sample points represents a set of hyperparameter combinations; Taking each of the initial sample points as a hyperparameter of the prediction model, calculating a corresponding objective function value, wherein the objective function value is a loss function; Constructing a proxy model according to the initial sample points and their corresponding objective function values; According to the proxy model, searching for the next sample point in the hyperparameter space; Training the prediction model on the hyperparameter combination represented by the new sample point, evaluating the objective function, and feeding back to the proxy model; The process of finding the next sample point, training and evaluating is repeated until a preset number of repetitions is reached, and the hyperparameter combination represented by the sample point with the smallest objective function is used as the hyperparameter combination of the prediction model.

9. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of setting the adjustment threshold and warning threshold of the risk area includes: collecting performance parameters of the water-cooled wall of the entire furnace, the performance parameters including the maximum safe temperature, the minimum safe temperature, and the expected normal operating temperature range; using the expected normal operating temperature range as the adjustment threshold, and using the maximum safe temperature and the minimum safe temperature as the warning threshold.

10. The temperature control method based on dynamic simulation of the whole furnace water wall according to claim 1 is characterized in that: The process of dynamically adjusting the circulation parameters includes: increasing the cooling water flow rate of the water-cooled wall, improving the heat exchange capacity, and reducing the local temperature of the water-cooled wall; adjusting the circulation pressure of the cooling water, increasing the flow rate of the cooling water through the water-cooled wall, and optimizing the cooling effect.

Images