Mixed coal combustion characteristic prediction method and device, electronic equipment and storage medium

Abstract

The invention relates to a mixed coal combustion characteristic prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: building a coal quality information database based on element analysis data, industrial analysis data, calorific value data and combustion characteristic parameters of coal types; a training set and a test set are generated, a radial basis function is selected as a kernel function, a sparrow search algorithm is introduced to optimize key parameters of the model, and optimal parameters of the model are determined; on the basis of the optimal parameters, element analysis data, industrial analysis data and calorific value data of the coal quality information database serve as input features, the combustion characteristic parameters serve as output results, a combustion characteristic prediction model is built, and the combustion characteristic parameters of the new coal blending scheme are predicted. Therefore, the problems that the cost is high due to the fact that grid search adopts an exhaustion strategy, and the prediction of the combustion characteristics of the mixed coal is difficult due to the fact that the combustion characteristics of the mixed coal and the coal quality characteristics of the component coal types are not in a simple linear relation in the prior art are solved.

Description

Technical Field

[0001] This application relates to the field of coal combustion technology, and in particular to a method, apparatus, electronic device and storage medium for predicting the combustion characteristics of mixed coal. Background Technology

[0002] Currently, due to limitations in coal source, coal mining quality, and transportation conditions, coal-fired boilers in actual operation are often forced to burn non-designed coal types, leading to reduced equipment safety, decreased combustion efficiency, and increased pollutant emissions. Under the context of deep flexible peak shaving for power plants, this fails to meet the requirements for stable combustion and rapid response at low loads. Power coal blending, as a clean combustion technology, can mix different coal types, reducing power plant coal costs while achieving cleaner and more efficient combustion. By rationally selecting coal blending schemes, the combustion stability of boilers under low loads can be increased, ensuring stable combustion and low emissions, and improving peak shaving limits. This addresses safety, economic, and environmental issues, providing safety, efficiency, and functional guarantees for deep flexible peak shaving.

[0003] In related technologies, power coal blending achieves optimized combustion by mixing raw coal of different qualities. A grid search method is introduced to optimize the scheme, determine the range of key parameters, such as the proportion of each component coal and the amount of additives, and then divide the range into several grid nodes. Each node corresponds to a set of coal blending parameters. The combustion characteristics of the mixed coal at each node (such as stable combustion temperature and burnout rate) are verified through experiments or simulations. The optimal parameter combination suitable for low load conditions is selected to improve the matching degree between the scheme and the boiler requirements.

[0004] However, in related technologies, grid search optimization adopts an exhaustive strategy and lacks intelligent guidance, resulting in an exponential increase in computational cost as the parameter dimension increases. Furthermore, since the combustion characteristics of blended coal and the coal quality characteristics of the component coals are not a simple linear relationship, it is difficult to predict the combustion characteristics of blended coal. The calculation of coal blending ratio is mostly based on linear assumptions or empirical judgments, making it difficult to quantify the synergistic or antagonistic effects that may occur after different coal types are mixed. These issues urgently need to be addressed. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for predicting the combustion characteristics of mixed coal, in order to solve the problems in related technologies, such as the exponential increase in computational cost with the increase of parameter dimension due to the exhaustive strategy of grid search optimization, and the difficulty in predicting the combustion characteristics of mixed coal because the combustion characteristics of mixed coal and the coal quality characteristics of the component coals are not a simple linear relationship.

[0006] The first aspect of this application provides a method for predicting the combustion characteristics of blended coal, comprising the following steps: establishing a coal quality information database based on elemental analysis data, industrial analysis data, calorific value data, and combustion characteristic parameters of the coal type; generating a training set and a test set based on the coal quality information database, selecting a radial basis function as the kernel function, and introducing a sparrow search algorithm to optimize the key parameters of the model to determine the optimal parameters of the model; based on the optimal parameters, using the elemental analysis data, industrial analysis data, and calorific value data of the coal quality information database as input features, and using the combustion characteristic parameters of the coal quality information database as output results, constructing a combustion characteristic prediction model, and substituting the industrial analysis data, elemental analysis data, and calorific value data of a new coal blending scheme into the combustion characteristic prediction model to predict the combustion characteristic parameters of the new coal blending scheme.

[0007] Through the above-mentioned technical means, the embodiments of this application can establish a coal quality information database covering multi-dimensional data of coal types, combine the sparrow search algorithm to optimize the key parameters of the radial basis function kernel model, construct a prediction model with coal quality data as input and combustion characteristics as output, avoid prediction deviations caused by missing basic data through comprehensive coal quality data support, and optimize model parameters by utilizing the global optimization capability of the sparrow search algorithm to improve the prediction accuracy and generalization ability of the model.

[0008] Optionally, in one embodiment of this application, the combustion characteristic parameters include at least one of ignition temperature, burnout temperature, and maximum combustion rate; the elemental analysis data includes the content of at least one of carbon, hydrogen, oxygen, nitrogen, and sulfur; and the industrial analysis data includes the content of at least one of air-dried moisture, ash, volatile matter, and fixed carbon.

[0009] Through the above-mentioned technical means, the embodiments of this application can clearly define the specific range of combustion characteristic parameters, elemental analysis data and industrial analysis data, accurately define the dimensions of key parameters, ensure that the coal quality information input into the model can directly correspond to the core characteristics of the combustion process, ensure that the model can accurately capture the influence law of different coal qualities on combustion characteristics, and provide sufficient feature information support for the prediction model.

[0010] Optionally, in one embodiment of this application, the introduction of the sparrow search algorithm to optimize key parameters of the model includes: setting the population size, maximum number of iterations, and discoverer ratio of the sparrow search algorithm; and applying the sparrow search algorithm to optimize the parameters of the support vector regression model, wherein the penalty parameter and the built-in parameters of the RBF kernel function of the support vector regression model are optimized.

[0011] Through the above-mentioned technical means, the embodiments of this application can set parameters such as the population size and number of iterations of the sparrow search algorithm, and specifically optimize the penalty parameters and radial basis function built-in functions of the support vector regression model, thereby achieving directional and efficient optimization of key model parameters. By reasonably setting the algorithm parameters and clearly focusing on the optimization object, the efficiency of parameter optimization is improved, and the generalization ability and stability of the model are guaranteed.

[0012] Optionally, in one embodiment of this application, the step of constructing a combustion characteristic prediction model includes: obtaining the relative error, root mean square error, and coefficient of determination of the support vector regression model; determining an index for evaluating the predictive performance of the model based on the relative error, the root mean square error, and the coefficient of determination, until a preset performance requirement is met, thereby obtaining the combustion characteristic prediction model.

[0013] Through the above-mentioned technical means, the embodiments of this application can obtain the relative error, root mean square error and coefficient of determination of the support vector regression model, construct a quantitative model performance evaluation index and ensure that it meets the preset requirements, thereby realizing the effectiveness verification of the combustion characteristic prediction model. Through comprehensive evaluation of multi-dimensional error indexes, the prediction accuracy of the model is fully reflected, thereby ensuring the reliability of the combustion characteristic parameters output by the model and guaranteeing the safety and economy of the coal blending scheme.

[0014] A second aspect of this application provides a coal blending combustion characteristic prediction device, comprising: a building module for establishing a coal quality information database based on elemental analysis data, industrial analysis data, calorific value data, and combustion characteristic parameters of the coal type; a generating module for generating a training set and a test set based on the coal quality information database, selecting a radial basis function as the kernel function, and introducing a sparrow search algorithm to optimize the key parameters of the model to determine the optimal parameters of the model; and a prediction module for constructing a combustion characteristic prediction model based on the optimal parameters, using the elemental analysis data, industrial analysis data, and calorific value data of the coal quality information database as input features, and using the combustion characteristic parameters of the coal quality information database as output results, so as to substitute the industrial analysis data, elemental analysis data, and calorific value data of a new coal blending scheme into the combustion characteristic prediction model to predict the combustion characteristic parameters of the new coal blending scheme.

[0015] Through the above-mentioned technical means, the embodiments of this application can establish a coal quality information database covering multi-dimensional data of coal types, combine the sparrow search algorithm to optimize the key parameters of the radial basis function kernel model, construct a prediction model with coal quality data as input and combustion characteristics as output, avoid prediction deviations caused by missing basic data through comprehensive coal quality data support, and optimize model parameters by utilizing the global optimization capability of the sparrow search algorithm to improve the prediction accuracy and generalization ability of the model.

[0016] Optionally, in one embodiment of this application, the combustion characteristic parameters include at least one of ignition temperature, burnout temperature, and maximum combustion rate; the elemental analysis data includes the content of at least one of carbon, hydrogen, oxygen, nitrogen, and sulfur; and the industrial analysis data includes the content of at least one of air-dried moisture, ash, volatile matter, and fixed carbon.

[0017] Through the above-mentioned technical means, the embodiments of this application can clearly define the specific range of combustion characteristic parameters, elemental analysis data and industrial analysis data, accurately define the dimensions of key parameters, ensure that the coal quality information input into the model can directly correspond to the core characteristics of the combustion process, ensure that the model can accurately capture the influence law of different coal qualities on combustion characteristics, and provide sufficient feature information support for the prediction model.

[0018] Optionally, in one embodiment of this application, the generation module includes: a setting unit for setting the population size, maximum number of iterations, and discoverer ratio of the sparrow search algorithm; and an optimization unit for applying the sparrow search algorithm to optimize the parameters of the support vector regression model, wherein the penalty parameters and built-in parameters of the support vector regression model are optimized.

[0019] Through the above-mentioned technical means, the embodiments of this application can set parameters such as the population size and number of iterations of the sparrow search algorithm, and specifically optimize the penalty parameters and radial basis function built-in functions of the support vector regression model, thereby achieving directional and efficient optimization of key model parameters. By reasonably setting the algorithm parameters and clearly focusing on the optimization object, the efficiency of parameter optimization is improved, and the generalization ability and stability of the model are guaranteed.

[0020] Optionally, in one embodiment of this application, the prediction module includes: an acquisition unit, used to acquire the relative error, root mean square error, and coefficient of determination of the support vector regression model; and a determination unit, used to determine the indicators for evaluating the predictive performance of the model based on the relative error, the root mean square error, and the coefficient of determination, until a preset performance requirement is met, thereby obtaining the combustion characteristic prediction model.

[0021] Through the above-mentioned technical means, the embodiments of this application can obtain the relative error, root mean square error and coefficient of determination of the support vector regression model, construct a quantitative model performance evaluation index and ensure that it meets the preset requirements, thereby realizing the effectiveness verification of the combustion characteristic prediction model. Through comprehensive evaluation of multi-dimensional error indexes, the prediction accuracy of the model is fully reflected, thereby ensuring the reliability of the combustion characteristic parameters output by the model and guaranteeing the safety and economy of the coal blending scheme.

[0022] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting the combustion characteristics of mixed coal as described in the above embodiments.

[0023] A fourth aspect of this application provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for predicting the combustion characteristics of mixed coal.

[0024] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described method for predicting the combustion characteristics of mixed coal.

[0025] This application's embodiments can establish a coal quality information database covering multi-dimensional data on coal types. By combining the sparrow search algorithm to optimize key parameters of the radial basis function kernel model, a prediction model is constructed with coal quality data as input and combustion characteristics as output. Comprehensive coal quality data support avoids prediction bias caused by missing basic data. The global optimization capability of the sparrow search algorithm optimizes model parameters, improving the model's prediction accuracy and generalization ability. This solves the problems in related technologies, such as the exponential increase in computational cost with increasing parameter dimensions due to the exhaustive strategy of grid search optimization, and the difficulty in predicting the combustion characteristics of blended coal because the relationship between the combustion characteristics of blended coal and the coal quality characteristics of its constituent coal types is not a simple linear one.

[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a method for predicting the combustion characteristics of mixed coal according to an embodiment of this application; Figure 2 This is a flowchart of a method for predicting the combustion characteristics of mixed coal according to an embodiment of this application; Figure 3 This is a schematic diagram of the optimization process of a sparrow search algorithm according to an embodiment of this application; Figure 4 This is a scatter plot comparing the predicted and actual ignition temperature values ​​provided according to one embodiment of this application. Figure 5 This is a scatter plot comparing the predicted and actual burnout temperatures according to one embodiment of this application. Figure 6 This is a scatter plot comparing the predicted and actual maximum combustion rate values ​​provided according to one embodiment of this application. Figure 7 This is a schematic diagram of a coal combustion characteristic prediction device provided according to an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0028] Figure label: 10-Mixed coal combustion characteristic prediction device; 100-Establishment module, 200-Generation module, 300-Prediction module; 801-Memory, 802-Processor, 803-Communication interface. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0030] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for predicting the combustion characteristics of blended coal according to embodiments of this application. Addressing the problems mentioned in the background art, such as the exponential increase in computational cost with increasing parameter dimensions due to the exhaustive strategy employed in grid search optimization, and the difficulty in predicting the combustion characteristics of blended coal due to the non-linear relationship between the combustion characteristics and the coal quality characteristics of its constituent coal types, this application provides a method for predicting the combustion characteristics of blended coal. This method establishes a coal quality information database covering multi-dimensional data of coal types, combines a sparrow search algorithm to optimize key parameters of the radial basis function kernel model, and constructs a prediction model with coal quality data as input and combustion characteristics as output. Comprehensive coal quality data support avoids prediction bias caused by missing basic data. The global optimization capability of the sparrow search algorithm optimizes model parameters, improving the model's prediction accuracy and generalization ability. Therefore, this method solves the problems in the related art, such as the exponential increase in computational cost with increasing parameter dimensions due to the exhaustive strategy employed in grid search optimization, and the difficulty in predicting the combustion characteristics of blended coal due to the non-linear relationship between the combustion characteristics and the coal quality characteristics of its constituent coal types.

[0031] Specifically, Figure 1 This is a flowchart illustrating a method for predicting the combustion characteristics of mixed coal provided in an embodiment of this application.

[0032] like Figure 1 As shown, the method for predicting the combustion characteristics of mixed coal includes the following steps: In step S101, a coal quality information database is established based on the elemental analysis data, industrial analysis data, calorific value data, and combustion characteristic parameters of the coal type.

[0033] It is understood that the elemental analysis data in the embodiments of this application can represent the content of elements that directly participate in the combustion chemical reaction; the industrial analysis data can represent the basic physicochemical properties of coal; and the combustion characteristic parameters can represent the specific performance of coal in the combustion process.

[0034] For example, in the embodiments of this application, coal quality data can be obtained through standardized testing methods or experiments. Elemental analyzers can be used to determine the carbon, hydrogen, oxygen, nitrogen, and sulfur content of coal types. Drying, ashing, and high-temperature decomposition methods can be used to determine moisture, ash, and volatile matter in industrial analysis. Fixed carbon can be calculated using the difference method. Calorific value can be determined using an oxygen bomb calorimeter, and combustion characteristic parameters can be obtained using a thermogravimetric analyzer. These data are then classified by coal type, and associated information such as coal source and mining time is labeled. A structured coal quality information database can be constructed using tools such as SQL or Excel to ensure data traceability and retrieval.

[0035] The embodiments of this application can integrate multi-dimensional core data of coal types to establish a comprehensive and standardized coal quality information database, providing a comprehensive and reliable data source for subsequent model training, ensuring the representativeness and integrity of the training data, and laying a solid foundation for building a high-precision prediction model.

[0036] Optionally, in one embodiment of this application, the combustion characteristic parameters include at least one of ignition temperature, burnout temperature, and maximum combustion rate; the elemental analysis data includes the content of at least one of carbon, hydrogen, oxygen, nitrogen, and sulfur; and the industrial analysis data includes the content of at least one of air-dried moisture, ash, volatile matter, and fixed carbon.

[0037] It is understood that, in the embodiments of this application, the ignition temperature can be the lowest temperature at which coal begins to burn continuously, which can directly affect the boiler's stable combustion capability under low load; the burnout temperature can be the temperature at which coal is completely burned, which can reflect the degree of coal burnout; the maximum combustion rate can be the fastest rate of heat release during combustion, which can reflect the combustion intensity of coal; the air-dried basis moisture content can be the moisture content of coal in an air-dried state, which can affect the difficulty of coal ignition; the ash content can be the inorganic matter remaining after coal combustion, which can affect thermal efficiency and equipment wear; the volatile matter is the combustible gas decomposed by heating coal, which can determine the ignition rate; and the fixed carbon can be the main combustible component in coal, which can affect the calorific value.

[0038] For example, in this embodiment of the application, combustion characteristic parameters can be determined using a thermogravimetric analyzer: the coal sample is placed in the analyzer, heated at a set rate, and the mass change curve is recorded. The temperature at which the weight loss rate reaches 1% is taken as the ignition temperature, the temperature at which the weight loss rate reaches 98% is taken as the burnout temperature, and the value at which the mass change rate is the maximum combustion rate is taken as the maximum combustion rate. The mass fractions of carbon, hydrogen, oxygen, nitrogen, and sulfur are determined using an elemental analyzer. Industrial analysis data are determined according to GB / T212 standard: the moisture content on an air-dried basis is determined using the 105℃ drying method, the ash content is determined using the 815℃ ashing method, and the volatile matter is determined using the 900℃ air-isolated heating method. Fixed carbon is calculated using the difference method. Parameters are selected and incorporated into the coal quality information database according to actual needs.

[0039] The embodiments of this application can clearly define the specific range of combustion characteristic parameters, elemental analysis data and industrial analysis data, accurately define the dimensions of key parameters, ensure that the coal quality information input into the model can directly correspond to the core characteristics of the combustion process, ensure that the model can accurately capture the influence law of different coal qualities on combustion characteristics, and provide sufficient feature information support for the prediction model.

[0040] In step S102, a training set and a test set are generated based on the coal quality information database, and a radial basis function is selected as the kernel function. A sparrow search algorithm is introduced to optimize the key parameters of the model and determine the optimal parameters of the model.

[0041] It is understood that the radial basis function in the embodiments of this application can be a nonlinear kernel function that can map low-dimensional nonlinear data to a high-dimensional linearly separable space, adapting to the complex relationship between coal quality data and combustion characteristics; the sparrow search algorithm can be an intelligent optimization algorithm that simulates the foraging and warning behavior of sparrows, which can efficiently search for the optimal combination of key parameters of the model and solve the problem of blindness in traditional manual parameter selection.

[0042] In practical implementation, the embodiments of this application can randomly divide the data in the coal quality information database at an 8:2 ratio to generate training and test sets, avoiding the impact of data distribution bias on the model's generalization ability. Support vector regression is employed, using elemental analysis, industrial analysis, and calorific value data as model inputs, and ignition temperature, burnout temperature, and maximum combustion rate as model outputs. The model is built using the training set data. Radial basis functions are selected as the model kernel function due to their strong fitting ability to nonlinear relationships and low computational complexity, making them suitable for processing multi-dimensional coal quality data. When introducing the sparrow search algorithm, parameters such as population size and maximum number of iterations are initialized first. The model prediction error is used as the fitness function, and the algorithm iteratively searches for the key parameters of the support vector regression model until the error is minimized, thus determining the optimal parameters.

[0043] The embodiments of this application can achieve the following by reasonably dividing the dataset, selecting an appropriate kernel function, and introducing intelligent algorithms for optimization: the dataset division ensures that the model can learn general rules, the radial basis function solves the nonlinear mapping problem between coal quality data and combustion characteristics, and the sparrow search algorithm improves the efficiency and accuracy of parameter optimization, thus providing parameter support for building a high-performance prediction model.

[0044] Optionally, in one embodiment of this application, the introduction of the sparrow search algorithm to optimize key parameters of the model includes: setting the population size, maximum number of iterations, and discoverer ratio of the sparrow search algorithm; and applying the sparrow search algorithm to optimize the parameters of the support vector regression model, wherein the penalty parameter and the built-in parameters of the RBF kernel function of the support vector regression model are optimized.

[0045] It is understood that in the sparrow search algorithm of this application embodiment, the population number can be the number of individuals participating in the parameter search, which can affect the search breadth; the maximum number of iterations can be the maximum number of loops to terminate the algorithm, balancing search efficiency and accuracy; the discoverer ratio can be the proportion of individuals in the algorithm responsible for exploring new search areas, affecting the globality of the search; the penalty parameter of the support vector regression model can be used to control the model's tolerance to error, avoiding overfitting or underfitting.

[0046] In actual implementation, the sparrow search algorithm parameters can be set according to the data scale in this embodiment: for example, the population size is set to 20, the maximum number of iterations is set to 50, and the discoverer ratio is set to 0.3, which can ensure that the search is both extensive and efficient; when applying the algorithm, the search range of the penalty parameter C is limited to 0.1-10, the search range of the parameter g of the RBF (Radial Basis Function) kernel function is limited to 0.1-10, and the root mean square error of the support vector regression model on the training set is used as the fitness function; the algorithm explores the optimal parameter region through discoverers, followers follow the discoverers to search, and vigilants identify dangerous areas and adjust their positions, iterating until the maximum number of iterations or error convergence, and outputting the optimal penalty parameter and the parameter of the RBF kernel function.

[0047] This application embodiment can set parameters such as population size and iteration count of the sparrow search algorithm, and specifically optimize the penalty parameter and radial basis function of the support vector regression model, thereby achieving targeted and efficient optimization of key model parameters. By reasonably setting algorithm parameters and clearly focusing on the optimization object, the efficiency of parameter optimization is improved, and the generalization ability and stability of the model are guaranteed.

[0048] In step S103, based on the optimal parameters, the elemental analysis data, industrial analysis data, and calorific value data of the coal quality information database are used as input features, and the combustion characteristic parameters of the coal quality information database are used as output results to construct a combustion characteristic prediction model. The industrial analysis data, elemental analysis data, and calorific value data of the new coal blending scheme are then substituted into the combustion characteristic prediction model to predict the combustion characteristic parameters of the new coal blending scheme.

[0049] It is understood that in the embodiments of this application, the input features can be the independent variables used by the model for prediction, and the output results are the dependent variables that the model needs to predict, which can reflect the actual combustion performance of the mixed coal; the combustion characteristic prediction model can be a model based on the support vector regression algorithm that realizes the mapping relationship between input and output, and its core is to establish accurate prediction logic through optimal parameters.

[0050] In practical implementation, the embodiments of this application can substitute the optimal parameters into the support vector regression model, using elemental analysis, industrial analysis, and calorific value data from the training set as inputs and combustion characteristic parameters as outputs, to train the model to learn the relationship between the two. After the model training is completed, for a new coal blending scheme, its industrial analysis, elemental analysis, and calorific value data are first obtained through standardized testing. These data are then substituted into the model as inputs. The model, through the learned relationship, outputs the combustion characteristic parameters of the coal blending scheme, such as ignition temperature and burnout temperature. The industrial analysis, elemental analysis, and calorific value data of the blended coal are calculated by weighted average. The predicted combustion characteristic parameters can be used to guide the coal blending and combustion of coal-fired boilers.

[0051] The embodiments of this application can construct a prediction model of input and output based on optimal parameters and apply it to new coal blending schemes. It can quickly transform the basic coal quality data of new coal blending schemes into combustion characteristic parameters, realize accurate and rapid prediction of the combustion characteristics of mixed coal, provide a scientific basis for the design and optimization of coal blending schemes, and significantly improve the efficiency and reliability of coal blending work.

[0052] Optionally, in one embodiment of this application, the step of constructing a combustion characteristic prediction model includes: obtaining the relative error, root mean square error, and coefficient of determination of the support vector regression model; determining an index for evaluating the predictive performance of the model based on the relative error, the root mean square error, and the coefficient of determination, until a preset performance requirement is met, thereby obtaining the combustion characteristic prediction model.

[0053] It is understood that in the embodiments of this application, the relative error can be the proportion of the difference between the model's predicted value and the true value to the true value, reflecting the prediction deviation of a single sample; the root mean square error can be the square root of the mean square error, reflecting the overall error level of the model; the coefficient of determination can be used to measure the model's ability to explain data variation, and the closer the value is to 1, the better the model fit; the preset performance requirements can be the model's performance indicators set according to the actual application scenario, such as a coefficient of determination ≥ 0.95 and a relative error ≤ 5%. The preset performance requirements can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0054] In practical implementation, this embodiment of the application can input test set data into a trained support vector regression model to obtain predicted combustion characteristic parameters. The model performance is evaluated using multi-dimensional indicators, compared with the actual combustion characteristic parameters in the test set, and the relative error of each sample is calculated. Then, the overall root mean square error and coefficient of determination are calculated using formulas. The calculated indicators are compared with performance requirements; if the requirements are not met, the process returns to adjusting the sparrow search algorithm parameters or supplementing the coal quality information database, retraining the model until the indicators meet the requirements, and finally determining the final combustion characteristic prediction model.

[0055] The embodiments of this application can obtain the relative error, root mean square error, and coefficient of determination of the support vector regression model, construct a quantitative model performance evaluation index and ensure that it meets the preset requirements, thereby realizing the effectiveness verification of the combustion characteristic prediction model. Through comprehensive evaluation of multi-dimensional error indexes, the prediction accuracy of the model is fully reflected, thereby ensuring the reliability of the combustion characteristic parameters output by the model and guaranteeing the safety and economy of the coal blending scheme.

[0056] Specifically, it can be combined with Figures 2 to 6 As shown, the working principle of the coal combustion characteristic prediction method in this application is explained in detail with a specific embodiment.

[0057] Figure 2 This is a flowchart of a method for predicting the combustion characteristics of mixed coal according to an embodiment of this application.

[0058] like Figure 2 As shown, the process of predicting the combustion characteristics of blended coal unfolds in two aspects, ultimately forming a complete prediction closed loop. On the one hand, a coal quality database covering various coal types is first established, which includes elemental analysis (content of elements such as carbon and hydrogen), industrial analysis (indicators such as moisture and ash content), and calorific value data. After determining the specific proportion of blended coal types, targeted analysis is carried out on these coal types based on the database. Then, the data is integrated through linear fitting to obtain coal blending analysis data that can be directly used as input to the model.

[0059] On the other hand, a coal blending combustion characteristic prediction model is constructed based on SVR (Support Vector Regression). At the same time, the Sparrow Search algorithm is introduced to optimize the key parameters of the model (such as penalty parameters and RBF kernel function parameters) to improve the prediction accuracy of the model. Finally, the coal blending analysis data obtained above is input into the optimized model to output the combustion characteristic prediction results of the coal blending scheme (such as ignition temperature, burnout temperature, etc.), providing a basis for the rationality evaluation of the coal blending scheme.

[0060] Figure 3 This is a schematic diagram of the optimization process of the sparrow search algorithm according to an embodiment of this application.

[0061] like Figure 3 As shown, the optimization range of the parameters to be optimized is first set according to actual needs. For example, the range of values ​​for the penalty parameter in the support vector regression model and the range of the RBF kernel function parameter g [0.1, 10] are defined to delineate the effective boundary for the algorithm search. Next, a certain number of individuals are initialized as the starting point for optimization. Then, the population is divided into discoverers and followers. The former is responsible for exploring new parameter regions to expand the search range, while the latter performs a local fine-tuning search based on the discoverers' work. Both work together to improve optimization efficiency. During the process, a danger warning behavior is randomly triggered. If some individuals detect that the current region may be trapped in a local optimum, they will actively move to a better region to avoid search stagnation. Finally, the algorithm terminates the search by judging whether the population fitness (based on model prediction error) meets the standard: if it does not meet the standard, the population is re-divided and iteration continues; if it does meet the standard, the optimal parameter combination is output, providing key support for improving the model's prediction accuracy.

[0062] Specifically, this embodiment of the application can take 35 coal quality data points obtained from experiments as an example to carry out the following work: A combustion characteristic model is constructed based on basic coal quality analysis and calorific value. First, coal quality data is collected and processed. A total of 35 coal quality data points are obtained through experiments. Elemental analysis, industrial analysis, and calorific value data are used as inputs to the model, while ignition temperature, burnout temperature, and maximum combustion rate are used as outputs. The input features are normalized so that the values ​​fall within the range [0,1]. The data are randomly divided into a training set and a test set in an 8:2 ratio. The training set is used to build and train the model, and the test set is used to test the performance of the established model.

[0063] Further, predictive modeling was performed using support vector regression. Elemental analysis, industrial analysis, and calorific value data were used as inputs, while ignition temperature, burnout temperature, and maximum combustion rate were used as outputs. The model was built using training data. Radial basis functions were selected as the model kernel function, and the model parameters were determined using a sparrow search algorithm to complete the prediction model. The parameters for the sparrow search algorithm, including population size, maximum number of iterations, discoverer ratio, and optimization range of each parameter, are shown in Table 1. Table 1

[0064] Furthermore, the model accuracy is verified. The modeling effect is evaluated using test set data. Figure 4 , Figure 5 and Figure 6 The scatter plots of the actual and predicted values ​​for ignition temperature, burnout temperature, and maximum combustion rate are compared. The prediction results for these three parameters are shown in Table 2. The prediction results indicate that ignition temperature, burnout temperature, and maximum combustion rate have good prediction accuracy.

[0065] Table 2

[0066] A comparison of model accuracy was conducted, comparing the prediction results with those obtained using the traditional grid search method to determine model parameters, as shown in Table 3. The comparison results demonstrate that the model's prediction accuracy and generalization ability were significantly improved after optimization using the sparrow search algorithm.

[0067] Table 3

[0068] To predict the combustion characteristics of blended coal, for a given blending scheme, the elemental analysis, industrial analysis, and calorific value data of the blended coal are calculated using a weighted average method. This step is explained using an example. Assume a scheme is obtained by blending three types of coal in proportions H1, H2, and H3, with elemental analysis C percentages of C1, C2, and C3 respectively. Then, the elemental analysis C percentage of the blended coal in this scheme is calculated as follows: , Following this method, the weighted average values ​​of other basic coal quality analysis data and calorific value for the current coal blending scheme are calculated.

[0069] Predicting combustion characteristics: For a new coal blending scheme, the basic analysis data and calorific value data of the coal blending scheme are calculated and used as model input. The model's prediction function is used to obtain the ignition temperature, burnout temperature, and maximum combustion rate combustion characteristic parameters of the current coal blending scheme.

[0070] Taking a certain coal blending scheme A as an example, the basic analysis data and calorific value data of the coal blending scheme are shown in Table 4 below:

[0071] Using the above parameters as input, the predicted ignition temperature, burnout temperature, and maximum combustion rate of mixed coal A are 361.5 ℃, 542.8 ℃, and 10.42 % / min, respectively. Compared with the actual ignition temperature (357.9 ℃), burnout temperature (533.8 ℃), and maximum combustion rate (9.97 % / min) of A, the relative errors of this prediction method are as follows: , , .

[0072] The method for predicting the combustion characteristics of blended coal proposed in this application establishes a coal quality information database covering multi-dimensional data of coal types. By combining the sparrow search algorithm to optimize key parameters of the radial basis function kernel model, a prediction model is constructed with coal quality data as input and combustion characteristics as output. Comprehensive coal quality data support avoids prediction bias caused by missing basic data. The global optimization capability of the sparrow search algorithm optimizes model parameters, improving the model's prediction accuracy and generalization ability. This solves the problems in related technologies where grid search optimization uses an exhaustive strategy, leading to an exponential increase in computational cost with increasing parameter dimensions, and where the relationship between the combustion characteristics of blended coal and the coal quality characteristics of its constituent coal types is not a simple linear one, making the prediction of blended coal combustion characteristics difficult.

[0073] Next, the coal combustion characteristic prediction device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0074] Figure 7 This is a schematic diagram of the structure of the coal combustion characteristic prediction device according to an embodiment of this application.

[0075] like Figure 7 As shown, the mixed coal combustion characteristic prediction device 10 includes: a setup module 100, a generation module 200, and a prediction module 300.

[0076] Module 100 is used to establish a coal quality information database based on elemental analysis data, industrial analysis data, calorific value data, and combustion characteristic parameters of coal types.

[0077] The generation module 200 is used to generate training and testing sets based on the coal quality information database, and selects the radial basis function as the kernel function, introduces the sparrow search algorithm to optimize the key parameters of the model, and determines the optimal parameters of the model.

[0078] The prediction module 300 is used to construct a combustion characteristic prediction model based on the optimal parameters, using elemental analysis data, industrial analysis data, and calorific value data from the coal quality information database as input features, and combustion characteristic parameters from the coal quality information database as output results. The model is used to substitute the industrial analysis data, elemental analysis data, and calorific value data of the new coal blending scheme into the combustion characteristic prediction model to predict the combustion characteristic parameters of the new coal blending scheme.

[0079] Optionally, in one embodiment of this application, the combustion characteristic parameters include at least one of ignition temperature, burnout temperature, and maximum combustion rate; the elemental analysis data includes the content of at least one of carbon, hydrogen, oxygen, nitrogen, and sulfur; and the industrial analysis data includes the content of at least one of air-dried moisture, ash, volatile matter, and fixed carbon.

[0080] Optionally, in one embodiment of this application, the generation module 200 includes a setting unit and an optimization unit.

[0081] The setting unit is used to set the population size, maximum number of iterations, and discoverer ratio of the sparrow search algorithm.

[0082] The optimization unit is used to optimize the parameters of the support vector regression model by applying the sparrow search algorithm, specifically optimizing the penalty parameters and the built-in parameters of the RBF kernel function.

[0083] Optionally, in one embodiment of this application, the prediction module 300 includes: an acquisition unit and a determination unit.

[0084] The acquisition unit is used to acquire the relative error, root mean square error, and coefficient of determination of the support vector regression model.

[0085] The determining unit is used to determine the indicators for evaluating the predictive performance of the model based on the relative error, the root mean square error, and the coefficient of determination, until the preset performance requirements are met, thereby obtaining the combustion characteristic prediction model.

[0086] It should be noted that the foregoing explanation of the embodiment of the method for predicting the combustion characteristics of mixed coal also applies to the mixed coal combustion characteristic prediction device of this embodiment, and will not be repeated here.

[0087] The coal combustion characteristic prediction device proposed in this application can establish a coal quality information database covering multi-dimensional data of coal types. By combining the sparrow search algorithm to optimize key parameters of the radial basis function kernel model, a prediction model is constructed with coal quality data as input and combustion characteristics as output. Comprehensive coal quality data support avoids prediction bias caused by missing basic data. The global optimization capability of the sparrow search algorithm optimizes model parameters, improving the model's prediction accuracy and generalization ability. This solves the problems in related technologies where grid search optimization uses an exhaustive strategy, leading to an exponential increase in computational cost with increasing parameter dimensions, and where the relationship between the combustion characteristics of mixed coal and the coal quality characteristics of its constituent coal types is not a simple linear one, making the prediction of mixed coal combustion characteristics difficult.

[0088] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 801, the processor 802, and the computer program stored on the memory 801 and capable of running on the processor 802.

[0089] When the processor 802 executes the program, it implements the method for predicting the combustion characteristics of mixed coal provided in the above embodiments.

[0090] Furthermore, electronic devices also include: Communication interface 803 is used for communication between memory 801 and processor 802.

[0091] The memory 801 is used to store computer programs that can run on the processor 802.

[0092] The memory 801 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0093] If the memory 801, processor 802, and communication interface 803 are implemented independently, then the communication interface 803, memory 801, and processor 802 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 8The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0094] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.

[0095] The processor 802 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0096] This application also provides a non-volatile computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for predicting the combustion characteristics of mixed coal.

[0097] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described method for predicting the combustion characteristics of mixed coal.

[0098] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0099] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0100] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0102] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0103] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0104] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0105] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for predicting the combustion characteristics of mixed coal, characterized in that, Includes the following steps: A coal quality information database is established based on elemental analysis data, industrial analysis data, calorific value data, and combustion characteristic parameters of coal types. Training and testing sets are generated based on the coal quality information database. Radial basis functions are selected as kernel functions, and sparrow search algorithm is introduced to optimize the key parameters of the model and determine the optimal parameters of the model. Based on the optimal parameters, using the elemental analysis data, industrial analysis data, and calorific value data from the coal quality information database as input features, and the combustion characteristic parameters from the coal quality information database as output results, a combustion characteristic prediction model is constructed. The industrial analysis data, elemental analysis data, and calorific value data of the new coal blending scheme are then substituted into the combustion characteristic prediction model to predict the combustion characteristic parameters of the new coal blending scheme.

2. The method according to claim 1, characterized in that, The combustion characteristic parameters include at least one of ignition temperature, burnout temperature, and maximum combustion rate; the elemental analysis data includes the content of at least one of carbon, hydrogen, oxygen, nitrogen, and sulfur; and the industrial analysis data includes the content of at least one of air-dried moisture, ash, volatile matter, and fixed carbon.

3. The method according to claim 1, characterized in that, The introduction of the sparrow search algorithm to optimize key parameters of the model includes: Set the population size, maximum number of iterations, and discoverer ratio for the sparrow search algorithm; The sparrow search algorithm is applied to optimize the parameters of the support vector regression model, specifically optimizing the penalty parameter and the built-in parameters of the RBF kernel function.

4. The method according to claim 3, characterized in that, The construction of the combustion characteristic prediction model includes: Obtain the relative error, root mean square error, and coefficient of determination of the support vector regression model; The indicators for evaluating the predictive performance of the model are determined based on the relative error, the root mean square error, and the coefficient of determination until the preset performance requirements are met, thus obtaining the combustion characteristic prediction model.

5. A device for predicting the combustion characteristics of mixed coal, characterized in that, include: A module is established to create a coal quality information database based on elemental analysis data, industrial analysis data, calorific value data, and combustion characteristic parameters of coal types. The generation module is used to generate training and testing sets based on the coal quality information database, and selects the radial basis function as the kernel function, introduces the sparrow search algorithm to optimize the key parameters of the model, and determines the optimal parameters of the model. The prediction module is used to construct a combustion characteristic prediction model based on the optimal parameters, using elemental analysis data, industrial analysis data, and calorific value data from the coal quality information database as input features, and combustion characteristic parameters from the coal quality information database as output results. The model is then used to input the industrial analysis data, elemental analysis data, and calorific value data of the new coal blending scheme into the combustion characteristic prediction model to predict the combustion characteristic parameters of the new coal blending scheme.

6. The apparatus according to claim 5, characterized in that, The combustion characteristic parameters include at least one of ignition temperature, burnout temperature, and maximum combustion rate; the elemental analysis data includes the content of at least one of carbon, hydrogen, oxygen, nitrogen, and sulfur; and the industrial analysis data includes the content of at least one of air-dried moisture, ash, volatile matter, and fixed carbon.

7. The apparatus according to claim 5, characterized in that, The generation module includes: The setting unit is used to set the population size, maximum number of iterations, and discoverer ratio of the sparrow search algorithm; The optimization unit is used to optimize the parameters of the support vector regression model by applying the sparrow search algorithm, specifically optimizing the penalty parameters and the built-in parameters of the RBF kernel function.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method for predicting the combustion characteristics of mixed coal as described in any one of claims 1-4.

9. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for predicting the combustion characteristics of mixed coal as described in any one of claims 1-4.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the method for predicting the combustion characteristics of mixed coal as described in any one of claims 1-4.

Images