A fuel energy-saving regulating device and intelligent control method thereof

Abstract

The present invention discloses a fuel energy-saving regulating device and an intelligent control method thereof, comprising: a magnetization processing module magnetizes fuel based on magnetization technology; a detection module detects the combustion efficiency of the magnetized fuel when it is burned in a boiler; a comparison module compares the combustion efficiency with a preset combustion efficiency threshold; a generation module generates a first instruction for detecting boiler equipment when the comparison module determines that the combustion efficiency is less than the preset combustion efficiency threshold; the first instruction is executed to obtain the detection result of the boiler equipment, and when the boiler equipment is determined to be normal according to the detection result, a second instruction for adjusting the magnetization parameters of the magnetization processing module is generated. The molecular structure of the fuel gas is effectively changed, so that the fuel is fully burned and the fuel has a higher performance, thereby effectively improving the heating efficiency, reducing the heating time, and achieving the purpose of reducing the use of fuel. Based on the more complete combustion of the fuel, the exhaust gas emissions of the combustion chamber are optimized, and the atmospheric pollution to the environment is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel energy saving, and in particular to a fuel energy saving regulating device and an intelligent control method thereof. Background Art

[0002] At present, the production concept of low carbon, energy saving and environmental protection is advocated in the fields of thermal energy application involving fuel combustion, such as boilers, incineration, smelting, ceramics, brick factories, glass manufacturing, printing and dyeing, ships, catering, and household gas. In the existing technology, the fuel cannot be fully burned during the combustion process, resulting in low combustion efficiency. At the same time, a large amount of carbon deposits are generated at the burner combustion port, causing atmospheric pollution to the environment. There is a lack of effective monitoring of the fuel during the combustion process, and the combustion process cannot be adjusted in time. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the purpose of the present invention is to propose a fuel energy-saving regulating device and an intelligent control method thereof, which can effectively change the molecular structure of the fuel, make the fuel fully burn and give full play to the higher performance of the fuel, thereby effectively improving the heating efficiency, reducing the heating time, and achieving the purpose of reducing the amount of fuel used. Based on the more complete combustion of the fuel, the exhaust gas emissions of the combustion chamber are optimized and the atmospheric pollution to the environment is reduced. The combustion efficiency of the magnetized fuel during combustion in the boiler is monitored, and the magnetization parameters of the magnetization processing module are adjusted in time to improve the combustion efficiency of the fuel.

[0004] To achieve the above object, the embodiment of the present invention provides a fuel energy-saving adjustment device, comprising:

[0005] A magnetization processing module, used for performing magnetization processing on the fuel based on magnetization technology;

[0006] A detection module, used to detect the combustion efficiency of the magnetized fuel when it is burned in the boiler;

[0007] A comparison module, for comparing the combustion efficiency with a preset combustion efficiency threshold;

[0008] Generate modules for:

[0009] When the comparison module determines that the combustion efficiency is less than a preset combustion efficiency threshold, a first instruction for detecting the boiler equipment is generated;

[0010] The first instruction is executed to obtain the detection result of the boiler equipment, and when it is determined that the boiler equipment is normal according to the detection result, a second instruction for adjusting the magnetization parameter of the magnetization processing module is generated.

[0011] According to some embodiments of the present invention, the magnetization parameters include magnetic field strength and duration.

[0012] According to some embodiments of the present invention, the detection module includes:

[0013] A construction module for building and training a combustion efficiency detection model;

[0014] Output modules for:

[0015] Detecting combustion parameters during combustion in a fuel boiler after magnetization treatment;

[0016] The combustion parameters are input into the combustion efficiency detection model, and the combustion efficiency of the fuel when it is burned in the boiler is output.

[0017] According to some embodiments of the present invention, the combustion parameters include superheater wall temperature, furnace flue gas pressure, main steam pressure, main steam temperature, reheater wall temperature, reheater steam pressure, reheater steam temperature, furnace flue gas temperature, superheater desuperheater inlet flow, main steam flow, total air volume and oxygen supply.

[0018] According to some embodiments of the present invention, the building block comprises:

[0019] An acquisition module, used to acquire sample combustion parameters and corresponding sample combustion efficiency when the fuel is burned in the boiler;

[0020] Establish a module for classifying the working conditions of sample combustion parameters based on a K-nearest neighbor classifier, and obtain several types of working condition data sets based on the classification results and the corresponding sample combustion efficiencies; use the various types of working condition data sets as input to establish initial models for various types of working conditions;

[0021] The optimization module is used to optimize the initial models of various working conditions to obtain the combustion efficiency detection model.

[0022] According to some embodiments of the present invention, the optimization module includes:

[0023] The first determination module is used to:

[0024] For the initial models of various working conditions, determine the parameters that need to be optimized, including the number of neurons, learning rate and number of training iterations, and determine their respective optimization ranges;

[0025] Initialize PSO parameters, including the initial velocity and position of particles, learning weights, number of training times and scale;

[0026] Determine the fitness function of the particle, use the improved error function of the prediction model as the fitness function of the particle, and find the optimal model parameters;

[0027] The judgment module is used to:

[0028] Compare the fitness values ​​of particles, find the individual optimal position and the global optimal position, and update the optimal fitness value;

[0029] It is determined whether the maximum number of iterations has been reached. If so, the optimal parameters are passed to the initial model for training and prediction to obtain a combustion efficiency detection model.

[0030] According to some embodiments of the present invention, a boiler device includes a superheater, a furnace, a reheater, and a superheater desuperheater.

[0031] According to some embodiments of the present invention, the second determining module is further included, which is used to:

[0032] When the magnetized fuel is burned in the boiler, the current oxygen concentration is detected; according to the current oxygen concentration and the combustion efficiency of the fuel when burning in the boiler, the introduction strategy of the amount of oxygen required for the fuel to burn in the boiler is determined, including:

[0033]

[0034] Wherein, h(t) is the amount of oxygen introduced into the boiler at time t; c(t) is the oxygen concentration at time t; C0 is the oxygen concentration threshold in the boiler; T is the temperature in the boiler; P1 is the current pressure in the boiler; P2 is the standard atmospheric pressure; η is the combustion efficiency of the fuel when it is burned in the boiler; H is the preset amount of oxygen introduced into the boiler;

[0035] Strategies for the amount of oxygen required to burn fuel in the boiler.

[0036] An intelligent control method for a fuel energy-saving regulating device, comprising:

[0037] Magnetizing the fuel based on magnetization technology;

[0038] Detect the combustion efficiency of magnetized fuel when it is burned in a boiler;

[0039] comparing the combustion efficiency to a preset combustion efficiency threshold;

[0040] When the comparison module determines that the combustion efficiency is less than a preset combustion efficiency threshold, a first instruction for detecting the boiler equipment is generated; the first instruction is executed to obtain the detection result of the boiler equipment, and when it is determined that the boiler equipment is normal according to the detection result, a second instruction for adjusting the magnetization parameters of the magnetization processing module is generated.

[0041] The present invention proposes a fuel energy-saving regulating device and an intelligent control method thereof, which effectively changes the molecular structure of the fuel gas, makes the fuel burn fully, and exerts higher performance of the fuel, thereby effectively improving the heating efficiency, reducing the heating time, and achieving the purpose of reducing fuel use. Based on the more complete combustion of the fuel, the exhaust gas emission of the combustion chamber is optimized, and the atmospheric pollution to the environment is reduced. The combustion efficiency of the magnetized fuel is monitored when it is burned in the boiler, and the magnetization parameters of the magnetization processing module are adjusted in time to improve the combustion efficiency of the fuel.

[0042] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0043] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 is a block diagram of a fuel energy-saving adjustment device according to an embodiment of the present invention;

[0046] Figure 2 The figure is a flow chart of an intelligent control method of a fuel energy-saving regulating device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0048] like Figure 1 As shown, the embodiment of the present invention provides a fuel energy-saving adjustment device, including:

[0049] A magnetization processing module, used for performing magnetization processing on the fuel based on magnetization technology;

[0050] A detection module, used to detect the combustion efficiency of the magnetized fuel when it is burned in the boiler;

[0051] A comparison module, for comparing the combustion efficiency with a preset combustion efficiency threshold;

[0052] Generate modules for:

[0053] When the comparison module determines that the combustion efficiency is less than a preset combustion efficiency threshold, a first instruction for detecting the boiler equipment is generated;

[0054] The first instruction is executed to obtain the detection result of the boiler equipment, and when it is determined that the boiler equipment is normal according to the detection result, a second instruction for adjusting the magnetization parameter of the magnetization processing module is generated.

[0055] The working principle of the above technical solution is as follows: magnetization technology magnetizes gas or fuel oil through a strong magnetic field, changes the molecular cluster structure, increases molecular activity, and thus improves combustion efficiency. Detect the combustion efficiency of the magnetized fuel when it is burned in the boiler; compare the combustion efficiency with the preset combustion efficiency threshold, and judge the combustion condition of the fuel. When the comparison module determines that the combustion efficiency is less than the preset combustion efficiency threshold, it means that the combustion effect is not ideal. First, the boiler equipment is tested, and the first instruction is executed to obtain the test result of the boiler equipment. When it is determined that the boiler equipment is normal according to the test result, it means that the unsatisfactory combustion is caused by unreasonable magnetization parameters, and a second instruction is generated to adjust the magnetization parameters of the magnetization processing module.

[0056] The beneficial effects of the above technical solution are: effectively changing the molecular structure of the fuel gas, making the fuel burn fully and exerting higher performance of the fuel, thereby effectively improving the heating efficiency, reducing the heating time, and achieving the purpose of reducing fuel use. Based on the more complete combustion of the fuel, the exhaust gas emissions of the combustion chamber are optimized, reducing atmospheric pollution to the environment. The combustion efficiency of the magnetized fuel during combustion in the boiler is monitored, and the magnetization parameters of the magnetization processing module are adjusted in time to improve the combustion efficiency of the fuel.

[0057] According to some embodiments of the present invention, the magnetization parameters include magnetic field strength and duration.

[0058] According to some embodiments of the present invention, the detection module includes:

[0059] A construction module for building and training a combustion efficiency detection model;

[0060] Output modules for:

[0061] Detecting combustion parameters during combustion in a fuel boiler after magnetization treatment;

[0062] The combustion parameters are input into the combustion efficiency detection model, and the combustion efficiency of the fuel when it is burned in the boiler is output.

[0063] The working principle and beneficial effects of the above technical solution are as follows: construct and train a combustion efficiency detection model; output module to detect the combustion parameters of the fuel after magnetization treatment when it is burned in the boiler; input the combustion parameters into the combustion efficiency detection model, and output the combustion efficiency of the fuel when it is burned in the boiler. It is convenient to accurately determine the combustion efficiency of the fuel when it is burned in the boiler.

[0064] According to some embodiments of the present invention, the combustion parameters include superheater wall temperature, furnace flue gas pressure, main steam pressure, main steam temperature, reheater wall temperature, reheater steam pressure, reheater steam temperature, furnace flue gas temperature, superheater desuperheater inlet flow, main steam flow, total air volume and oxygen supply.

[0065] According to some embodiments of the present invention, the building block comprises:

[0066] An acquisition module, used to acquire sample combustion parameters and corresponding sample combustion efficiency when the fuel is burned in the boiler;

[0067] Establish a module for classifying the working conditions of sample combustion parameters based on a K-nearest neighbor classifier, and obtain several types of working condition data sets based on the classification results and the corresponding sample combustion efficiencies; use the various types of working condition data sets as input to establish initial models for various types of working conditions;

[0068] The optimization module is used to optimize the initial models of various working conditions to obtain the combustion efficiency detection model.

[0069] The working principle and beneficial effects of the above technical solution are as follows: Based on the K-nearest neighbor (K-NN) classifier, the sample combustion parameters are classified into working conditions, and the initial models of various working conditions are established based on the classification results, including: Feature selection: Select the features that have the greatest impact on the working condition classification from the combustion parameters. K-NN classification: Use the K-NN algorithm to classify the sample data into working conditions. Select a suitable K value and optimize the K value through methods such as cross-validation. For each sample, its working condition category is determined according to the categories of its K nearest neighbors. Working condition data set division: According to the K-NN classification results, the sample data is divided into several types of working condition data sets. Initial model establishment: For each type of working condition data set, an initial model is established based on a machine learning algorithm (such as linear regression, decision tree, random forest, etc.). The initial model is trained using this type of working condition data set and its performance is evaluated. The initial models of various working conditions are optimized to improve the accuracy and generalization ability of combustion efficiency detection, including: Hyperparameter tuning: Hyperparameter tuning is performed on each initial model, and the optimal hyperparameter combination is found through methods such as grid search, random search or Bayesian optimization. Ensemble learning: Use ensemble learning methods (such as bagging, boosting) to combine the prediction results of multiple models to improve the overall performance. Feature engineering: Based on the model performance, further feature engineering is performed, such as feature transformation, feature selection, or generating new features. Cross-validation: Use cross-validation to evaluate the stability and generalization ability of the model to ensure that the model performs consistently on different data sets. Model fusion: If there are multiple models in the system (such as models under different working conditions), use model fusion technology (such as stacking, blinding) to further improve the prediction accuracy. Final model determination: Based on the optimization results, select the model with the best performance as the final combustion efficiency detection model.

[0070] According to some embodiments of the present invention, the optimization module includes:

[0071] The first determination module is used to:

[0072] For the initial models of various working conditions, determine the parameters that need to be optimized, including the number of neurons, learning rate and number of training iterations, and determine their respective optimization ranges;

[0073] Initialize PSO parameters, including the initial velocity and position of particles, learning weights, number of training times and scale;

[0074] Determine the fitness function of the particle, use the improved error function of the prediction model as the fitness function of the particle, and find the optimal model parameters;

[0075] The judgment module is used to:

[0076] Compare the fitness values ​​of particles, find the individual optimal position and the global optimal position, and update the optimal fitness value;

[0077] It is determined whether the maximum number of iterations has been reached. If so, the optimal parameters are passed to the initial model for training and prediction to obtain a combustion efficiency detection model.

[0078] The working principle and beneficial effects of the above technical solution: The first determination module prepares the necessary parameters and conditions for the PSO algorithm to optimize the parameters of the initial models of various working conditions, including: Determine the parameters and ranges to be optimized: For the initial model of each type of working condition, identify the key parameters that need to be optimized, such as the number of neurons in the neural network, the learning rate, the number of training iterations, etc. Set a reasonable search range for each parameter to be optimized, which should be determined based on prior knowledge or preliminary experiments. Initialize PSO parameters: Particle initial speed and position: Randomly generate the initial speed and position of each particle, and these values ​​correspond to the potential solutions of the parameters to be optimized. Learning weight (or inertia weight): Set the inertia weight of the particle, which affects the tendency of the particle to maintain the current speed, usually a number between 0 and 1. Number of training: Set the total number of iterations for the PSO algorithm, that is, the total number of rounds of the algorithm. Particle swarm size: Determine the number of particles participating in the optimization, which will affect the search ability and computational complexity of the algorithm. Determine the fitness function: Use the improved error function of the prediction model (such as mean square error MSE, mean absolute error MAE, etc.) as the fitness function of the particle. This function will evaluate the quality of the particle (i.e. a set of model parameters) and will be used to guide the search process of the particle. During the execution of the PSO algorithm, the judgment module compares the fitness values ​​of the particles, updates the optimal solution, and determines whether the algorithm has ended. Steps: Compare fitness values: In each round of iteration, calculate the fitness value of each particle (i.e. the error of the model under the current parameters). Compare the fitness values ​​of the particles and update the individual optimal position of each particle (i.e. the optimal solution encountered by the particle during the search process) and the global optimal position (i.e. the optimal solution encountered by the entire particle group during the search process). Update particle position and speed: Update the particle's speed and position based on the particle's current position, speed, individual optimal position and global optimal position, as well as parameters such as learning weights. This step is the core of the PSO algorithm, which enables particles to move towards a better solution. Determine whether the maximum number of iterations has been reached: Check whether the algorithm has reached the preset maximum number of iterations. If the maximum number of iterations has been reached, the algorithm ends and the global optimal position (i.e. the optimal model parameters) is passed back to the initial model. Training and prediction: Use the optimal model parameters to train the initial model until the model converges or reaches the predetermined training standard. Use the trained model to make predictions to obtain the combustion efficiency detection model.

[0079] According to some embodiments of the present invention, a boiler device includes a superheater, a furnace, a reheater, and a superheater desuperheater.

[0080] According to some embodiments of the present invention, the second determining module is further included, which is used to:

[0081] When the magnetized fuel is burned in the boiler, the current oxygen concentration is detected; according to the current oxygen concentration and the combustion efficiency of the fuel when burning in the boiler, the introduction strategy of the amount of oxygen required for the fuel to burn in the boiler is determined, including:

[0082]

[0083] Wherein, h(t) is the amount of oxygen introduced into the boiler at time t; c(t) is the oxygen concentration at time t; C0 is the oxygen concentration threshold in the boiler; T is the temperature in the boiler; P1 is the current pressure in the boiler; P2 is the standard atmospheric pressure; η is the combustion efficiency of the fuel when it is burned in the boiler; H is the preset amount of oxygen introduced into the boiler;

[0084] Strategies for the amount of oxygen required to burn fuel in the boiler.

[0085] The working principle and beneficial effects of the above technical solution are as follows: when the magnetized fuel is burned in the boiler, the current oxygen concentration is detected; based on the current oxygen concentration and the combustion efficiency of the fuel when burning in the boiler, the strategy for introducing the amount of oxygen required for the fuel to burn in the boiler is determined to ensure the combustion conditions, and the oxygen concentration in the boiler is adaptively adjusted so that the fuel can be fully burned while avoiding the waste of oxygen, and the combustion process is accurately and intelligently adjusted and controlled to achieve efficient combustion.

[0086] like Figure 2 As shown, an intelligent control method for a fuel energy-saving regulating device includes steps S1-S4:

[0087] S1. Magnetizing the fuel based on magnetization technology;

[0088] S2, detecting the combustion efficiency of the magnetized fuel when it is burned in the boiler;

[0089] S3, comparing the combustion efficiency with a preset combustion efficiency threshold;

[0090] S4. When the comparison module determines that the combustion efficiency is less than a preset combustion efficiency threshold, a first instruction for detecting the boiler equipment is generated; the first instruction is executed to obtain the detection result of the boiler equipment, and when it is determined that the boiler equipment is normal according to the detection result, a second instruction for adjusting the magnetization parameters of the magnetization processing module is generated.

[0091] The beneficial effects of the above technical solution are: effectively changing the molecular structure of the fuel gas, making the fuel burn fully and exerting higher performance of the fuel, thereby effectively improving the heating efficiency, reducing the heating time, and achieving the purpose of reducing fuel use. Based on the more complete combustion of the fuel, the exhaust gas emissions of the combustion chamber are optimized, reducing atmospheric pollution to the environment. The combustion efficiency of the magnetized fuel during combustion in the boiler is monitored, and the magnetization parameters of the magnetization processing module are adjusted in time to improve the combustion efficiency of the fuel.

[0092] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A fuel energy-saving regulating device, characterized in that: include: A magnetization processing module, used for performing magnetization processing on the fuel based on magnetization technology; A detection module, used to detect the combustion efficiency of the magnetized fuel when it is burned in the boiler; A comparison module, for comparing the combustion efficiency with a preset combustion efficiency threshold; Generate modules for: When the comparison module determines that the combustion efficiency is less than a preset combustion efficiency threshold, a first instruction for detecting the boiler equipment is generated; Execute the first instruction to obtain the detection result of the boiler equipment, and generate a second instruction for adjusting the magnetization parameter of the magnetization processing module when it is determined that the boiler equipment is normal according to the detection result; The detection module comprises: A construction module for building and training a combustion efficiency detection model; Output modules for: Detecting combustion parameters during combustion in a fuel boiler after magnetization treatment; The combustion parameters are input into the combustion efficiency detection model, and the combustion efficiency of the fuel when it is burned in the boiler is output; The building blocks include: An acquisition module, used to acquire sample combustion parameters and corresponding sample combustion efficiency when the fuel is burned in the boiler; Establish a module for classifying the working conditions of sample combustion parameters based on a K-nearest neighbor classifier, and obtain several types of working condition data sets based on the classification results and the corresponding sample combustion efficiencies; use the various types of working condition data sets as input to establish initial models for various types of working conditions; The optimization module is used to optimize the initial models of various working conditions to obtain the combustion efficiency detection model; The optimization module comprises: The first determination module is used to: For the initial models of various working conditions, determine the parameters that need to be optimized, including the number of neurons, learning rate and number of training iterations, and determine their respective optimization ranges; Initialize PSO parameters, including the initial velocity and position of particles, learning weights, number of training times and scale; Determine the fitness function of the particle, use the improved error function of the prediction model as the fitness function of the particle, and find the optimal model parameters; The judgment module is used to: Compare the fitness values ​​of particles, find the individual optimal position and the global optimal position, and update the optimal fitness value; It is determined whether the maximum number of iterations has been reached. If so, the optimal parameters are passed to the initial model for training and prediction to obtain a combustion efficiency detection model.

2. The fuel energy saving regulating device according to claim 1, characterized in that: The magnetization parameters include magnetic field strength and duration.

3. The fuel energy saving regulating device according to claim 1, characterized in that: The combustion parameters include superheater wall temperature, furnace flue gas pressure, main steam pressure, main steam temperature, reheater wall temperature, reheater steam pressure, reheater steam temperature, furnace flue gas temperature, superheater desuperheater inlet flow, main steam flow, total air volume and oxygen supply.

4. The fuel energy saving regulating device according to claim 1, characterized in that: Boiler equipment includes superheater, furnace, reheater and superheater desuperheater.

5. The fuel energy-saving regulating device according to claim 1, characterized in that: Also included is a second determining module, configured to: When the magnetized fuel is burned in the boiler, the current oxygen concentration is detected; according to the current oxygen concentration and the combustion efficiency of the fuel when burning in the boiler, the introduction strategy of the amount of oxygen required for the fuel to burn in the boiler is determined, including: Wherein, h(t) is the amount of oxygen introduced into the boiler at time t; c(t) is the oxygen concentration at time t; C0 is the oxygen concentration threshold in the boiler; T is the temperature in the boiler; P1 is the current pressure in the boiler; P2 is the standard atmospheric pressure; η is the combustion efficiency of the fuel when it is burned in the boiler; H is the preset amount of oxygen introduced into the boiler; Strategies for the amount of oxygen required to burn fuel in the boiler.

6. The intelligent control method of the fuel energy-saving regulating device according to claim 1, characterized in that: include: Magnetizing the fuel based on magnetization technology; Detect the combustion efficiency of magnetized fuel when it is burned in a boiler; comparing the combustion efficiency to a preset combustion efficiency threshold; When the comparison module determines that the combustion efficiency is less than a preset combustion efficiency threshold, a first instruction for detecting the boiler equipment is generated; the first instruction is executed to obtain the detection result of the boiler equipment, and when it is determined that the boiler equipment is normal according to the detection result, a second instruction for adjusting the magnetization parameters of the magnetization processing module is generated.

Images