Torch flame stability detection method

Abstract

The invention provides a torch flame stability detection method, which comprises the following steps of: determining a relation function between a hydrogen ammonia doping ratio and flame length, color and temperature according to a flame stability parameter data set, training a flame stability prediction model through a support vector machine algorithm, and judging flame stability states under different ammonia doping ratios; performing kinetic analysis according to an output result of the flame stability prediction model, simulating a combustion process of hydrogen and ammonia gas, obtaining a change curve of the concentration of a key intermediate product along with time, and judging propagation characteristics of a reaction chain under different ammonia doping proportions; the method comprises the steps of simulating flow field distribution under different burner structures according to occurrence conditions of flame stability key points, obtaining a fuel injection velocity field, measuring a temperature field and a species concentration field of a combustion area, and judging the influence of the burner structures on flame stability.

Description

Technical Field

[0001] The invention relates to the field of information technology, and in particular to a method for detecting the stability of a torch flame. Background Art

[0002] In the hydrogen-ammonia combustion torch system, there is a technical contradiction in the effect of the ammonia blending ratio during the tank supply process on the stability of the hydrogen flame. As the ammonia blending ratio increases, the flame length, color and temperature will change, but this change is not a linear relationship. At low ammonia blending ratios, the flame stability increases with the increase in the ratio, and the combustion efficiency also increases accordingly. However, when the ammonia blending ratio exceeds a certain critical value, the flame stability begins to decline, and unstable combustion occurs. This contradiction stems from the complexity of the combustion dynamics of hydrogen-ammonia mixed gas. The presence of ammonia changes the concentration distribution and diffusion rate of the reactants, affecting the progress of the free radical chain reaction. At the same time, the endothermic effect of ammonia decomposition competes with the exothermic effect of hydrogen combustion, resulting in uneven flame temperature distribution. In addition, the presence of ammonia also affects the flame propagation speed and combustion limit, making the flame structure present different characteristics at different blending ratios. Therefore, in practical applications, it is difficult to obtain ideal flame stability by simply adjusting the ammonia blending ratio. It is necessary to comprehensively consider multiple factors such as reaction kinetics, heat and mass transfer processes, and flame structure, and establish a more accurate mathematical model to describe this complex system. This requires the collection and analysis of a large amount of experimental data under different working conditions to find the optimal operating parameter range. Summary of the invention

[0003] The present invention provides a method for detecting the flame stability of a torch, which mainly comprises:

[0004] According to the preset hydrogen-ammonia ratio range, mixed fuel samples with different ratios are obtained from the storage tank, the mixing ratio of hydrogen and ammonia is adjusted by a mass flow controller, and the concentration of hydrogen and ammonia in the mixed fuel is monitored in real time by a gas analyzer to determine whether the components of the mixed fuel meet the preset ratio requirements;

[0005] The flame stability test was carried out on the obtained mixed fuel samples. A high-speed camera system was used to capture the flame morphology, analyze the change of flame length, measure the flame color characteristics, determine the flame temperature distribution, and obtain the flame stability parameter data set under different ammonia mixing ratios;

[0006] According to the flame stability parameter data set, the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature is determined. The flame stability prediction model is trained by the support vector machine algorithm to determine the flame stability state under different ammonia ratios.

[0007] Conduct kinetic analysis on the output results of the flame stability prediction model, simulate the combustion process of hydrogen and ammonia, obtain the time-varying curve of the concentration of key intermediate products, and determine the propagation characteristics of the reaction chain under different ammonia mixing ratios;

[0008] According to the change curve and propagation characteristics, the flame stability key point discrimination criteria are established, the flame stability threshold is set, and by comparing the deviation between the actual flame parameters and the threshold, it is judged whether the flame is in a stable state under the current ammonia mixing ratio, and the conditions for the occurrence of the flame stability key point are determined;

[0009] According to the conditions for the occurrence of key points of flame stability, the flow field distribution under different burner structures is simulated, the fuel injection velocity field is obtained, the temperature field and species concentration field of the combustion area are measured, and the influence of the burner structure on the flame stability is determined;

[0010] According to the analysis results of the influence of burner structure on flame stability, genetic algorithm is used to optimize the geometric parameters of burner. By adjusting the fuel injection angle and the shape of the combustion chamber, the flame morphology evolution process under the optimized burner structure is calculated using numerical simulation method to determine whether the optimized burner can effectively suppress the occurrence of key points of flame stability and obtain the optimal ammonia blending ratio.

[0011] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0012] The present invention discloses a method for detecting the flame stability of a torch. Firstly, the present invention uses a mass flow controller to accurately adjust the mixing ratio of hydrogen and ammonia, and uses a gas analyzer to monitor the component ratio of the mixed fuel in real time. In this way, it is possible to accurately control and obtain mixed fuel samples with different hydrogen-ammonia ratios, thereby solving the problem of accurate regulation of the mixed fuel ratio.

[0013] Next, by conducting flame stability tests on the obtained mixed fuel samples, comprehensive flame stability parameter data is obtained to provide a basis for subsequent model training; secondly, the relationship between the hydrogen-ammonia ratio and flame stability is determined through model analysis, and a relationship model between the hydrogen-ammonia ratio and flame characteristics is established to achieve the prediction of flame stability; finally, by analyzing the impact on flame stability, the discrimination criteria and thresholds of key points of flame stability are determined, which can accurately judge the stable state of the flame, and provide direction for the optimal design of the burner, and obtain the optimal ammonia ratio and burner structure, thereby improving flame stability. In general, the present invention effectively improves the stability of the flame under different hydrogen-ammonia ratios, and provides a practical scientific basis and technical support for fuel mixing and burner design. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1The present invention is a flow chart of a method for detecting the stability of a torch flame.

[0015] Figure 2 It is a schematic diagram of a torch flame stability detection method of the present invention.

[0016] Figure 3 It is another schematic diagram of a torch flame stability detection method of the present invention. DETAILED DESCRIPTION

[0017] The following will describe the technical solutions in the embodiments of the present invention in detail in conjunction with the accompanying drawings in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention.

[0018] like Figure 1-3 In this embodiment, a method for detecting the flame stability of a torch may specifically include:

[0019] S101. According to a preset hydrogen-ammonia ratio range, mixed fuel samples with different ratios are obtained from a storage tank, the mixing ratio of hydrogen and ammonia is adjusted by a mass flow controller, and the concentrations of hydrogen and ammonia in the mixed fuel are monitored in real time by a gas analyzer to determine whether the components of the mixed fuel meet the preset ratio requirements.

[0020] A mixed fuel sample within a preset hydrogen-ammonia ratio range is obtained, and the mixed fuel sample is supplied from a storage tank; according to the preset hydrogen-ammonia ratio range, the mixing ratio of hydrogen and ammonia in the mixed fuel sample is adjusted by a mass flow controller; a gas analyzer is used to monitor the mixed fuel sample in real time to obtain concentration data of hydrogen and ammonia; a deviation value between the actual component of the mixed fuel sample and the preset ratio requirement is calculated by a direct comparison method, and if the deviation value exceeds a preset threshold, an automatic correction program of the mass flow controller is triggered; a concentration fluctuation analysis is performed according to the deviation value, and a quantitative evaluation is performed on the concentration stability of the mixed fuel sample; a Kalman filter algorithm is used to smooth the concentration data to obtain smoothed concentration data; and a determination is made as to whether the components of the mixed fuel sample meet the preset ratio requirement by combining the concentration fluctuation analysis result and the smoothed concentration data; if the measurement results for a preset number of consecutive times are all within the allowable deviation range, it is determined that the components of the mixed fuel sample meet the preset ratio requirement.

[0021] Exemplarily, a mixed fuel sample with a preset hydrogen-ammonia ratio range of 30%-70% is obtained from a storage tank, and the mixing ratio of hydrogen and ammonia is accurately adjusted by a mass flow controller. According to the preset fuel sample volume parameter, the adjustment accuracy of the mass flow controller is controlled to 0.1%. A gas analyzer is used to monitor the mixed fuel sample in real time to obtain the concentration data of hydrogen and ammonia. The monitoring data is processed by the standard gas calibration method to obtain the calibrated hydrogen-ammonia mixed fuel concentration data. For the calibrated concentration data, the direct comparison method is used to calculate the deviation value between the actual mixed fuel component and the preset ratio requirement, and the allowable deviation range is set to ±1%. According to the calculated deviation value, a concentration fluctuation analysis is performed to quantitatively evaluate the concentration stability of the mixed fuel sample. If the deviation value exceeds the preset threshold, the automatic correction program of the mass flow controller is triggered to readjust the mixing ratio to meet the predetermined ratio requirement. The Kalman filter algorithm is used to smooth the continuously monitored concentration data to reduce the impact of random fluctuations on the judgment results. Combined with the concentration fluctuation analysis results and the smoothed data, it is judged whether the components of the mixed fuel meet the predetermined ratio requirements. If the measurement results for 10 consecutive times are within the allowable deviation range, it is judged that the components of the mixed fuel meet the predetermined ratio requirements. When obtaining a mixed fuel sample with a preset hydrogen-ammonia ratio range of 30%-70% from the storage tank, the mass flow controller uses the principle of a thermal mass flow meter to accurately adjust the mixing ratio of hydrogen and ammonia. According to the preset fuel sample volume parameter of 500mL, the controller adjustment accuracy is set to 0.1%, that is, the hydrogen flow rate is 150-350mL / min, and the ammonia flow rate is 150-350mL / min. The gas analyzer uses infrared absorption spectroscopy to monitor the mixed fuel sample in real time, with a sampling frequency of 1Hz, to obtain the concentration data of hydrogen and ammonia. Through the standard gas calibration method, 99.999% pure hydrogen and ammonia standard gases are used for calibration to obtain the calibrated hydrogen-ammonia mixed fuel concentration data. The deviation value between the actual mixed fuel component and the preset ratio requirement is calculated by the direct comparison method, and the allowable deviation range is set to ±1%. For example, when the preset hydrogen ratio is 60%, the actual measured value is 62%, and the deviation value is 2%, which exceeds the allowable range. Perform concentration fluctuation analysis, use the standard deviation method to calculate the standard deviation of 100 consecutive measurement data, and evaluate the concentration stability of the mixed fuel sample. If the deviation value exceeds the preset threshold, trigger the PID automatic correction program of the mass flow controller, adjust the P, I, and D parameters, and readjust the mixing ratio to meet the predetermined ratio requirements. Using the Kalman filter algorithm, set the initial state estimate and the error covariance matrix, and smooth the continuously monitored concentration data to reduce the impact of random fluctuations on the judgment results. Combined with the concentration fluctuation analysis results and the smoothed data, judge whether the components of the mixed fuel meet the predetermined ratio requirements. If the measurement results of 10 consecutive times are within the allowable deviation range, it is judged that the components of the mixed fuel meet the predetermined ratio requirements.

[0022] S102. Conduct flame stability test on the obtained mixed fuel samples, use a high-speed camera system to capture the flame morphology, analyze the change of flame length, measure the flame color characteristics, determine the flame temperature distribution, and obtain a flame stability parameter data set under different ammonia blending ratios.

[0023] Obtain the mixed fuel sample, test the mixed fuel with different ammonia blending ratios, capture the flame morphology through a high-speed camera system, and obtain a continuous flame image sequence. Use the Canny edge detection algorithm to extract the flame outline from the flame image sequence, and calculate the characteristic parameters of the flame area and height. According to the flame image sequence, analyze the oscillation frequency and amplitude of the flame length through fast Fourier transform to obtain the flame length oscillation characteristic data. Use a multi-spectral imaging device to collect images of the flame in multiple bands, calculate the color temperature and radiation intensity distribution of the flame through two-color temperature measurement, and obtain the flame color characteristics and temperature distribution data. Calculate the flame stability index. If the ratio of the standard deviation of the flame length to the average flame length is less than a preset threshold, the flame is determined to be stable; construct a flame stability parameter data set based on the flame oscillation frequency, propagation speed, brightness uniformity and stability index.

[0024] For example, for the obtained mixed fuel samples, the mixed fuels with 30%, 50%, and 70% ammonia blending ratios are tested in turn, the mixed fuels are ignited by a burner, and the flame morphology is captured by a high-speed camera system of 10,000 frames per second, and a continuous 1,000-frame flame image sequence is obtained. The flame contour is extracted from the flame image using the Canny edge detection algorithm, and characteristic parameters such as the flame area and height are calculated. According to the flame image sequence, the flame length change curve is calculated, and the oscillation frequency and amplitude of the flame length are analyzed by fast Fourier transform to obtain the flame length oscillation characteristic data. The flame is imaged in three bands of 340nm, 455nm, and 655nm using a multispectral imaging device, and the color temperature and radiation intensity distribution of the flame are calculated by two-color temperature measurement to obtain the flame color characteristics and temperature distribution data. The flame propagation speed is calculated from the change in the position of the flame front between consecutive frames, and the flame stability parameter data set is constructed by combining the flame morphology, length change, color characteristics, and temperature distribution data. The flame stability index is calculated, which is defined as 1 minus the ratio of the standard deviation of the flame length to the average flame length. For each ammonia blending ratio, the flame oscillation frequency, propagation speed, brightness uniformity and stability index are recorded to form a complete flame stability parameter data set. For the obtained mixed fuel samples, the automated test system sequentially mixes mixed fuels with 30%, 50% and 70% ammonia blending ratios, and accurately controls the flow rate to 10L / min. After the burner is ignited, a 10,000 frame / second high-speed camera system captures the flame morphology and continuously collects 1,000 frames of 1280x1024 resolution flame image sequences. The image processing unit applies the Canny edge detection algorithm, sets the low threshold to 50 and the high threshold to 150, and extracts the flame outline. Calculate the number of flame area pixels and the maximum height pixel number in each frame of the image and convert them into actual size, such as an area of ​​300cm 2, height 40cm. Fast Fourier transform is performed on the flame length data of 1000 frames of images with a sampling frequency of 10kHz to obtain a spectrum diagram, and the main oscillation frequency such as 100Hz and amplitude 0.5cm are identified. The multispectral imaging equipment synchronously collects flame images in three bands of 340nm, 455nm, and 655nm, with 1000 frames in each band. The two-color temperature measurement is applied, and the 455nm and 655nm bands are selected to calculate the flame temperature distribution, and the maximum temperature is 2000K and the average temperature is 1800K. By comparing the changes in the position of the flame front edge of adjacent frames, the flame propagation speed is calculated, such as 0.5m / s. Combine all the data to construct a flame stability parameter data set. Calculate the flame stability index. Assuming the average flame length is 40cm and the standard deviation is 2cm, the stability index is 1-(2 / 40)=0.95. For each ammonia blending ratio, the flame oscillation frequency, such as 100 Hz, propagation speed, such as 0.5 m / s, brightness uniformity standard deviation / average brightness = 0.1, and stability index, such as 0.95, were recorded to form a complete flame stability parameter data set for subsequent analysis and optimization of combustion conditions.

[0025] S103. Determine the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature according to the flame stability parameter data set, train the flame stability prediction model through the support vector machine algorithm, and judge the flame stability state under different ammonia ratios.

[0026] According to the hydrogen-ammonia ratio and flame parameter data sets, the polynomial regression method is used to fit the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature, and three relationship function equations are obtained. The flame stability parameter data set is subjected to feature engineering processing, and the ammonia ratio, flame length, color and temperature are selected as input features, and the flame stability index is used as the label. The flame stability prediction model is trained using the support vector machine algorithm, and the kernel function parameters and regularization parameters are optimized by the grid search method. If the flame parameter data with different ammonia ratios are input, the support vector machine model is used for prediction to obtain the corresponding flame stability prediction value. The stability state of the flame is judged according to the pre-established stability threshold, multiple stability levels are set, and different prediction value ranges are determined.

[0027] Exemplarily, according to the flame stability parameter data set, the polynomial regression method is used to fit the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature, the optimal order is selected by the cross-validation method, and the polynomial coefficients are determined by the least squares method to obtain three relationship function equations. The flame stability parameter data set is subjected to feature engineering, and the ammonia ratio, flame length, color, and temperature are selected as input features, and the flame stability index is used as a label. The optimal feature subset is selected by the recursive feature elimination method, and the relationship function calculation result is added as a new feature to obtain the processed training data set. Using the processed training data set, the flame stability prediction model is trained by the support vector machine algorithm, and the kernel function parameters and regularization parameters are optimized by the grid search method. The L2 regularization term is introduced to deal with the overfitting problem, and the optimal support vector machine model is obtained. The flame parameter data with different ammonia ratios are input, and the trained support vector machine model is used for prediction to obtain the corresponding flame stability prediction value. The stability state of the flame is judged according to the stability threshold determined by the statistical analysis of historical data, and multiple stability levels are set, corresponding to different prediction value ranges, to achieve accurate judgment of the flame stability state under different ammonia ratios. Based on the flame stability parameter data set, which contains 1000 sets of flame parameter records under different ammonia doping ratios of 30%-70%, the polynomial regression method is used to fit the relationship function. Through 5-fold cross validation, the mean square errors of 1-5 order polynomials are compared, and the 3rd order polynomial with the smallest mean square error is selected as the optimal model. The polynomial coefficients are determined by the least squares method, and three relationship function equations between the hydrogen ammonia doping ratio and the flame length, color, and temperature are obtained. Feature engineering is performed on the data set, and the initial features include ammonia doping ratio, flame length, color RGB value, and temperature, a total of 6 features. Recursive feature elimination method is applied, with the step size set to 1 and the number of cross validations set to 5, to select 4 optimal features. The relationship function calculation results are added as new features to form a 7-dimensional feature vector. The prediction model is trained using the support vector machine algorithm, and the RBF kernel function is used to optimize the parameters in the range of C = [0.1, 1, 10, 100] and gamma = [0.01, 0.1, 1, 10] by grid search method. The L2 regularization term is introduced, and the regularization coefficient is set to 0.01 to prevent overfitting. 80% of the data is used as the training set and 20% as the test set. After 1000 iterations of training, the optimal model is obtained, and the accuracy of the test set reaches 95%. Enter the flame parameter data of a new ammonia blending ratio, such as 55%, and the model outputs a stability prediction value of 0.82. According to historical data statistics, the stability threshold is set to [0.7, 0.8, 0.9], corresponding to three levels: unstable, relatively stable, and stable. The judgment results show that the flame is in a relatively stable state under the 55% ammonia blending ratio, which provides a basis for subsequent combustion optimization.

[0028] S104. Perform kinetic analysis on the output results of the flame stability prediction model, simulate the combustion process of hydrogen and ammonia, obtain the time-varying curve of the concentration of key intermediate products, and determine the propagation characteristics of the reaction chain under different ammonia blending ratios.

[0029] The GRI-Mech3.0 mechanism is modified according to the output results of the preset flame stability prediction model to construct the combustion kinetic mechanism of hydrogen and ammonia mixed fuel, which includes elementary reaction equations and reaction rate parameters; the combustion kinetic equation group is solved to obtain the concentration change curve of key intermediate products OH, H and NH2 over time; the contribution of each reaction process to the overall reaction rate under different ammonia doping ratios is calculated using the local sensitivity analysis method to obtain the reaction chain length and branching rate; according to the reaction chain length and branching rate, a correlation model between the ammonia doping ratio and the flame propagation speed and ignition delay time is established, and the flame propagation characteristics under any ammonia doping ratio are predicted by the cubic spline interpolation method; if the reaction chain length is greater than the preset reaction chain length threshold and the branching rate is greater than the preset branching rate threshold, the flame is judged to be in a stable state; if the reaction chain length is less than the preset reaction chain length threshold or the branching rate is less than the preset branching rate threshold, the flame is judged to be in an unstable state.

[0030] For example, according to the output results of the flame stability prediction model, the GRI-Mech3.0 mechanism is modified to construct the combustion kinetics mechanism of hydrogen and ammonia mixed fuel, including the elementary reaction equation and reaction rate parameters, and the reaction mechanism and initial conditions are imported through the CHEMKI N software. The fourth-order Runge-Kutta method is used to solve the combustion kinetics equation group, obtain the concentration change curve of key intermediates such as OH, H, NH2, etc. over time, and calculate the peak concentration and appearance time of each intermediate product. The local sensitivity analysis method is used to calculate the contribution of each reaction step to the overall reaction rate under different ammonia mixing ratios, identify the main reaction path and rate control step, and obtain a quantitative description of the reaction chain propagation characteristics such as reaction chain length and branching rate. Based on the reaction chain propagation characteristic data, a correlation model between the ammonia mixing ratio and the flame propagation speed and ignition delay time is established, and the flame propagation characteristics under any ammonia mixing ratio are predicted by the cubic spline interpolation method. The reaction chain length threshold and branching rate threshold are set, and the flame stability state is comprehensively judged by comparing the relationship between the reaction chain length and branching rate under different ammonia mixing ratios and the preset threshold, combined with the output results of the flame stability prediction model. Based on the stability index of 30%, 50% and 70% ammonia doping ratio output by the flame stability prediction model, the GRI-Mech3.0 mechanism was modified by CHEMKI N software to construct a combustion kinetic mechanism of hydrogen-ammonia mixed fuel containing 253 elementary reactions. The initial conditions were set as temperature 1000K, pressure 1atm, and equivalence ratio 1.0. The fourth-order Runge-Kutta method was used with a time step of 1e-6 seconds to solve the combustion kinetic equations and obtain the concentration-time curves of 10 key intermediates such as OH, H, and NH2. The peak concentration and appearance time of the intermediate products were calculated, such as the peak concentration of OH was 1.5e-3mol / L and the appearance time was 0.5ms. The contribution of each reaction step to the overall reaction rate was calculated using the local sensitivity analysis method, and three main reaction paths and two rate-controlling steps were identified. The reaction chain propagation characteristics were quantitatively described, such as the reaction chain length was 15 and the branching rate was 0.8 when 30% ammonia was doped. The correlation model between ammonia ratio and flame propagation speed and ignition delay time was established, and the flame propagation characteristics at 40% and 60% ammonia ratios were predicted by cubic spline interpolation. The reaction chain length threshold was set to 20, and the branching rate threshold was set to 0.7. The relationship between the reaction chain length and branching rate at different ammonia ratios and the preset thresholds was compared. Combined with the output results of the flame stability prediction model, such as the stability index of 0.85 when 40% ammonia was added, it was comprehensively judged that the flame was in a stable state when 40% ammonia was added, and the flame stability was reduced when 60% ammonia was added.

[0031] S105. According to the change curve and propagation characteristics, a flame stability key point discrimination criterion is established, and a flame stability threshold is set. By comparing the deviation between the actual flame parameters and the threshold, it is determined whether the flame is in a stable state under the current ammonia mixing ratio, and the conditions for the occurrence of the flame stability key point are determined.

[0032] Obtain flame characteristic data, extract key features of flame stability using principal component analysis, classify the key features using K-means clustering algorithm, and obtain feature vectors including flame length, temperature and oscillation frequency. According to the feature vector, establish a flame stability discrimination model using support vector machine algorithm, the discrimination model uses key features as input variables and flame stability state as output variables. For the discrimination model, set the flame stability threshold, construct a multidimensional threshold space, and the boundary of the multidimensional threshold space is determined by the output result of the support vector machine model. Receive the actual flame parameters under the current ammonia blending ratio, calculate the Mahalanobis distance between the actual flame parameters and the multidimensional threshold space, and the Mahalanobis distance is obtained by inverting the covariance matrix and calculating the sum of squares of the multidimensional feature vector differences. If the Mahalanobis distance is less than the preset threshold, it is determined that the flame is in a stable state; when 10 consecutive data points are all located in the stable area, it is determined to be a key point of flame stability, and the occurrence conditions of the key point of flame stability are recorded.

[0033] Exemplarily, according to the change curve and propagation characteristic data, the principal component analysis method is used to extract the key features of flame stability, and the features are classified by the K-means clustering algorithm to obtain the characteristic vector of the key point of flame stability, including parameters such as flame length, temperature and oscillation frequency. The flame stability discrimination model is established by using the support vector machine algorithm, with the key features as input variables and the flame stability state as output variables. The optimal model parameters are determined by 5-fold cross validation to obtain the flame stability key point discrimination criterion. Based on historical data and expert knowledge, the Delphi method is used to integrate expert opinions, set the flame stability threshold, construct a multidimensional threshold space, and use the output results of the support vector machine model to assist in determining the boundary of the multidimensional threshold space. The actual flame parameters under the current ammonia mixing ratio are input, and the Mahalanobis distance with the threshold space is calculated, which is obtained by inverting the covariance matrix and calculating the sum of squares of the multidimensional characteristic vector differences. If the distance is less than the preset threshold, it is determined by the statistical distribution of historical data, and the flame is determined to be in a stable state. When 10 consecutive data points are all located in the stable area, it is determined to be a flame stability key point, and the current conditions are recorded as the conditions for the occurrence of the flame stability key point. Based on 1000 sets of flame stability experimental data, the principal component analysis method was used to extract key features, retaining the principal components with a cumulative contribution rate of 95%, and obtaining five main features, flame length, temperature, oscillation frequency, propagation speed and OH radical concentration. Using the K-means clustering algorithm, the number of clusters k=3 was set. After 50 iterations, the feature space was divided into three categories: stable, metastable and unstable. The support vector machine algorithm was used to construct a discriminant model, with a 5-dimensional feature vector as input and a stability state as output, 0-unstable, 1-metastable, 2-stable. The RBF kernel function was used, and the parameters C=10 and gamma=0.1 were optimized through 5-fold cross validation. The model accuracy reached 92%. The Delphi method was applied, and 7 experts were invited to conduct 3 rounds of evaluation. Combined with historical data statistics, the multidimensional threshold space was determined, with flame length of 30-50cm, temperature of 1800-2200K, oscillation frequency of 100-150Hz, propagation speed of 0.5-1.5m / s, and OH concentration of (1-5)×10^-3mol / L. The Mahalanobis distance between the actual parameters and the threshold space was calculated, and the inverse matrix of the covariance matrix was used to set the distance threshold to 2.5 based on the 95% confidence interval of historical data. Under the 30% ammonia doping ratio, the measured parameters were input, flame length of 40cm, temperature of 2000K, oscillation frequency of 120Hz, propagation speed of 1.0m / s, and OH concentration of 3×10^-3mol / L. The Mahalanobis distance was calculated to be 1.8, which was less than the threshold of 2.5, and it was determined to be a stable state. 100 data points are monitored continuously. When 10 consecutive points are within the stable region, the condition is mixed with 30% ammonia and the current parameter combination is recorded as the key point of flame stability.

[0034] S106. Based on the conditions for the occurrence of key points of flame stability, simulate the flow field distribution under different burner structures, obtain the fuel injection velocity field, measure the temperature field and species concentration field in the combustion area, and determine the impact of the burner structure on flame stability.

[0035] According to the fuel mixture ratio, combustion temperature and pressure parameters, a three-dimensional model of the burner structure is established, including the nozzle diameter, combustion chamber length and cross-sectional area; ANSYS Fluent software is used to perform meshing and boundary condition setting of the burner structure model; the Navier-Stokes equations and k-ε turbulence model of fluid motion are solved to obtain the fuel injection velocity field of the burner structure model; according to the fuel injection velocity field, the velocity vector distribution and turbulence intensity distribution of the combustion area in the burner structure model are obtained; the temperature field and species concentration field of the combustion area are calculated using a simulated combustion model and a chemical reaction kinetic equation; the temperature distribution cloud map of the temperature field and the concentration distribution of key species in the species concentration field are obtained; the flame oscillation frequency and amplitude are calculated according to the temperature distribution cloud map and the concentration distribution of the key species; the random forest regression model is used to analyze the relationship between the burner structure parameters and the flame oscillation frequency and amplitude; if the flame oscillation frequency is lower than a preset threshold and the flame oscillation amplitude is lower than a preset threshold, it is judged that the burner structure corresponding to the burner structure parameters has good flame stability.

[0036] For example, according to the occurrence conditions of the key points of flame stability, the parameters such as fuel mixture ratio, combustion temperature and pressure are converted into burner structural parameters, and three-dimensional models of different burner structures are established, including nozzle diameter, combustion chamber length and cross-sectional area. ANSYS Fluent software is used for meshing and boundary condition setting to simulate the flow field distribution under different structures. By solving the basic equations of fluid motion such as the Navier-Stokes equation and the k-ε turbulence model equation, the fuel injection velocity field is calculated, the velocity vector distribution and turbulence intensity distribution in the combustion area are obtained, and the flow field characteristics under different structures are judged. Using the simulated combustion model Eddy Dissipation Concept combustion model and the chemical reaction kinetic equation, the temperature field and species concentration field of the combustion area are calculated, and the temperature distribution cloud map and the concentration distribution of key species such as OH, NO, etc. are obtained. Based on the simulation results, the flame oscillation frequency and amplitude are calculated to evaluate the flame stability. Using the random forest regression model, the relationship between the burner structural parameters and the flame stability index is analyzed to determine the degree of influence of different structures on flame stability. The differences in flame stability under different burner structures were compared by variance analysis ANOVA, and the influence of structural changes on stability was quantitatively evaluated. Based on the key conditions of flame stability, fuel mixture ratio of 40%, combustion temperature of 2000K, and pressure of 2atm, three burner structures were designed, with A-type nozzle diameter of 5mm, combustion chamber length of 200mm, and cross-sectional area of ​​100cm 2 , B-type nozzle diameter 8mm, combustion chamber length 250mm, cross-sectional area 150cm 2 , C-type nozzle diameter 6mm, combustion chamber length 180mm, cross-sectional area 80cm 2. A three-dimensional model was established using ANSYS Fluent software, and the mesh was divided using tetrahedral units with a mesh size of about 500,000. The boundary conditions were set as follows: inlet velocity 20 m / s, outlet pressure 1 atm, and wall adiabatic. The Navier-Stokes equations and k-ε turbulence model equations were solved with 1000 iterations and a residual less than 1e-6. The calculation results show that the maximum turbulence intensity is 15% for type A, 12% for type B, and 18% for type C. The EDC combustion model was applied, and the reaction mechanism included 30 species and 200 elementary reactions. The temperature field calculation results show that the maximum temperature of type A is 2150K, type B is 2080K, and type C is 2210K. The peak OH concentration is 2.5e-3 mol / L for type A, 2.1e-3 mol / L for type B, and 2.8e-3 mol / L for type C. The temperature fluctuation was analyzed by fast Fourier transform, and the flame oscillation frequency was obtained, which was 120Hz for type A, 95Hz for type B, and 135Hz for type C; the amplitude was 50K for type A, 40K for type B, and 65K for type C. The relationship between structural parameters and stability indicators was analyzed using the random forest regression model with 100 trees and a maximum depth of 10. The feature importance was ranked as nozzle diameter 0.4, combustion chamber length 0.3, and cross-sectional area 0.3. The results of ANOVA analysis showed that the flame stability of the three structures was significantly different with a p value of <0.01, among which type B had the highest stability and type C had the lowest. Comprehensive evaluation showed that the type B burner structure had the most positive effect on flame stability.

[0037] S107. Based on the analysis results of the influence of the burner structure on the flame stability, a genetic algorithm is used to optimize the geometric parameters of the burner. By adjusting the fuel injection angle and the shape of the combustion chamber, a numerical simulation method is used to calculate the evolution of the flame morphology under the optimized burner structure, and it is determined whether the optimized burner can effectively suppress the occurrence of key points of flame stability and obtain the optimal ammonia blending ratio.

[0038] The geometric parameters of the burner, the fuel injection angle and the shape of the combustion chamber are obtained to construct the genetic algorithm optimization model; wherein the genetic algorithm optimization model sets the population size, the crossover rate and the mutation rate. According to the structural parameters obtained by the optimization model, a three-dimensional computational fluid dynamics model is established; the three-dimensional computational fluid dynamics model adopts a turbulence model and a GRI-Mech3.0 reaction mechanism. The spatiotemporal distribution data of the flame morphology evolution are obtained through the three-dimensional computational fluid dynamics model; the flame oscillation frequency, the flame propagation speed and the flame temperature distribution are calculated according to the spatiotemporal distribution data; if the flame oscillation frequency is less than the preset frequency threshold and the amplitude is less than the preset amplitude threshold, the ammonia blending ratio range for stable combustion is determined. The NSGA-II algorithm is used for multi-objective optimization, and flame stability, combustion efficiency and NOx emission level are set as optimization targets; the Pareto optimal solution set is obtained based on the multi-objective optimization. The performance data of the optimized burner is obtained through a small test bench; the performance data is compared with the numerical simulation prediction results; and the optimization parameters are adjusted according to the comparison results.

[0039] For example, according to the analysis results of the influence of the burner structure on the flame stability, a genetic algorithm optimization model is constructed, and the population size is set to 100, the crossover rate is 0.8, and the mutation rate is 0.1. The burner geometric parameters nozzle diameter, combustion chamber length, cross-sectional area, fuel injection angle and combustion chamber shape are set as optimization variables, and the weighted sum of the flame oscillation frequency and amplitude is used as the fitness function to optimize the burner structural parameters. Using the optimized burner structural parameters, a three-dimensional computational fluid dynamics model is established, and the k-ε turbulence model and GRI-Mech3.0 reaction mechanism are used to simulate the combustion process under different ammonia mixing ratios, and the spatiotemporal distribution data of the flame morphology evolution are obtained. By analyzing the flame morphology evolution data, characteristic parameters such as flame oscillation frequency, flame propagation speed and flame temperature distribution are calculated. When the flame oscillation frequency is less than 100Hz and the amplitude is less than 50K, it is determined to be stable, and the ammonia mixing ratio range for stable combustion is determined. Based on the ammonia blending ratio range for stable combustion, combined with combustion efficiency and emission characteristics data, the NSGA-II algorithm was used for multi-objective optimization. Flame stability, combustion efficiency and NOx emission level were set as optimization targets, and the Pareto optimal solution set was calculated to select the optimal ammonia blending ratio. The performance of the optimized burner was verified by a small test bench, and the experimental results were compared with the numerical simulation predictions. The optimization parameters were further adjusted to ensure the accuracy and reliability of the optimization results. Based on the previous analysis results, a genetic algorithm optimization model was constructed, with a population size of 100, a crossover rate of 0.8, a mutation rate of 0.1, and 500 iterations. The optimization variables include nozzle diameter 5-10mm, combustion chamber length 150-300mm, and cross-sectional area 50-200cm 2, fuel injection angle 15-45°. The fitness function is 0.7×(1 / flame oscillation frequency)+0.3×(1 / flame amplitude). After 500 generations of evolution, the optimal structure is obtained, with a nozzle diameter of 7.5mm, a combustion chamber length of 220mm, and a cross-sectional area of ​​120cm 2 , injection angle 30°. The optimized burner model was established using ANSYS Fluent software, and the k-ε turbulence model and GRI-Mech3.0 reaction mechanism with 53 species and 325 reactions were used to simulate the combustion process at 30%, 40%, 50%, and 60% ammonia doping ratios. The time step was 0.1ms and the total simulation time was 100ms. The flame morphology evolution data was analyzed, and it was calculated that the flame oscillation frequency was 85Hz and the amplitude was 45K when 40% ammonia was doped, which was determined to be stable; the frequency was 120Hz and the amplitude was 70K when 60% ammonia was doped, which was determined to be unstable. The ammonia doping ratio range for stable combustion was determined to be 35%-55%. Within this range, the NSGA-II algorithm was used for multi-objective optimization, with a population size of 50 and 200 iterations. The optimization goal is to maximize the flame stability index 1-oscillation frequency / 100Hz-amplitude

[0040] / 100K, maximize combustion efficiency, minimize NOx emissions. Obtain the Pareto optimal solution set, select the flame stability index of 0.85, combustion efficiency of 98%, NOx emissions of 30ppm, corresponding to the best ammonia ratio of 45%. Verified on a small test bench, the measured flame stability index is 0.82, the combustion efficiency is 97.5%, and the NOx emissions are 32ppm, with an error of less than 5% from the simulation results, verifying the reliability of the optimization results.

[0041] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for detecting the stability of a torch flame, characterized in that: The method comprises: According to the preset hydrogen-ammonia ratio range, mixed fuel samples with different ratios are obtained from the storage tank, the mixing ratio of hydrogen and ammonia is adjusted by a mass flow controller, and the concentration of hydrogen and ammonia in the mixed fuel is monitored in real time by a gas analyzer to determine whether the components of the mixed fuel meet the preset ratio requirements; The flame stability test was carried out on the obtained mixed fuel samples. A high-speed camera system was used to capture the flame morphology, analyze the change of flame length, measure the flame color characteristics, determine the flame temperature distribution, and obtain the flame stability parameter data set under different ammonia mixing ratios; According to the flame stability parameter data set, the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature is determined. The flame stability prediction model is trained by the support vector machine algorithm to determine the flame stability state under different ammonia ratios. Conduct kinetic analysis on the output results of the flame stability prediction model, simulate the combustion process of hydrogen and ammonia, obtain the time-varying curve of the concentration of key intermediate products, and determine the propagation characteristics of the reaction chain under different ammonia mixing ratios; According to the change curve and propagation characteristics, the flame stability key point discrimination criteria are established, the flame stability threshold is set, and by comparing the deviation between the actual flame parameters and the threshold, it is judged whether the flame is in a stable state under the current ammonia mixing ratio, and the conditions for the occurrence of the flame stability key point are determined; According to the conditions for the occurrence of key points of flame stability, the flow field distribution under different burner structures is simulated, the fuel injection velocity field is obtained, the temperature field and species concentration field of the combustion area are measured, and the influence of the burner structure on the flame stability is determined; According to the analysis results of the influence of burner structure on flame stability, genetic algorithm is used to optimize the geometric parameters of burner. By adjusting the fuel injection angle and the shape of the combustion chamber, the flame morphology evolution process under the optimized burner structure is calculated using numerical simulation method to determine whether the optimized burner can effectively suppress the occurrence of key points of flame stability and obtain the optimal ammonia blending ratio.

2. The method according to claim 1, wherein: The method comprises obtaining mixed fuel samples with different proportions from a storage tank according to a preset hydrogen-ammonia ratio range, adjusting the mixing ratio of hydrogen and ammonia by a mass flow controller, monitoring the concentration of hydrogen and ammonia in the mixed fuel in real time by a gas analyzer, and judging whether the components of the mixed fuel meet the preset ratio requirements, including: Obtaining a mixed fuel sample within a preset hydrogen-ammonia ratio range, wherein the mixed fuel sample is supplied from a storage tank; According to the preset hydrogen-ammonia ratio range, adjusting the mixing ratio of hydrogen and ammonia in the mixed fuel sample by a mass flow controller; Using a gas analyzer to monitor the mixed fuel sample in real time to obtain concentration data of hydrogen and ammonia; Calculating the deviation between the actual components of the mixed fuel sample and the preset ratio requirement by using a direct comparison method, and triggering the automatic correction procedure of the mass flow controller if the deviation exceeds a preset threshold; Performing concentration fluctuation analysis according to the deviation value to quantitatively evaluate the concentration stability of the mixed fuel sample; Using a Kalman filter algorithm to smooth the concentration data to obtain smoothed concentration data; Combining the concentration fluctuation analysis result and the smoothed concentration data, determining whether the components of the mixed fuel sample meet the predetermined ratio requirements; If the measurement results for a preset number of consecutive times are all within the allowable deviation range, it is determined that the components of the mixed fuel sample meet the predetermined ratio requirements.

3. The method according to claim 1, wherein: The flame stability test is performed on the obtained mixed fuel sample, and a high-speed camera system is used to capture the flame morphology, analyze the change of flame length, measure the flame color characteristics, and determine the flame temperature distribution to obtain a flame stability parameter data set under different ammonia mixing ratios, including: Obtaining the mixed fuel sample, testing the mixed fuel with different ammonia blending ratios, capturing the flame morphology through a high-speed camera system, and obtaining a continuous flame image sequence; The Canny edge detection algorithm is used to extract the flame contour from the flame image sequence, and the characteristic parameters of the flame area and height are calculated; According to the flame image sequence, analyzing the oscillation frequency and amplitude of the flame length by fast Fourier transform to obtain flame length oscillation characteristic data; A multi-spectral imaging device is used to collect images of the flame in multiple bands, and the color temperature and radiation intensity distribution of the flame are calculated by two-color temperature measurement to obtain flame color characteristics and temperature distribution data; Calculating the flame stability index, and if the ratio of the flame length standard deviation to the average flame length is less than a preset threshold, determining that the flame is stable; A flame stability parameter data set is constructed based on the flame oscillation frequency, propagation speed, brightness uniformity and stability index.

4. The method according to claim 1, wherein: The method comprises: determining the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature according to the flame stability parameter data set, training the flame stability prediction model by the support vector machine algorithm, and judging the flame stability state under different ammonia ratios, including: According to the hydrogen-ammonia ratio and flame parameter data set, a polynomial regression method is used to fit the relationship function between the hydrogen-ammonia ratio and the flame length, color and temperature to obtain three relationship function equations; Performing feature engineering processing on the flame stability parameter data set, selecting the ammonia mixing ratio, flame length, color and temperature as input features, and taking the flame stability index as a label; The flame stability prediction model was trained using support vector machine algorithm, and the kernel function parameters and regularization parameters were optimized using grid search method. If flame parameter data with different ammonia blending ratios are input, the support vector machine model is used to perform predictions to obtain corresponding flame stability prediction values; The stability state of the flame is judged according to a pre-established stability threshold, a plurality of stability levels are set, and different prediction value ranges are determined.

5. The method according to claim 1, wherein: The output results of the flame stability prediction model are subjected to dynamic analysis, the combustion process of hydrogen and ammonia is simulated, the concentration curve of key intermediate products is obtained over time, and the propagation characteristics of the reaction chain under different ammonia mixing ratios are determined, including: Modify the GRI-Mech3.0 mechanism according to the output results of the preset flame stability prediction model to construct the combustion kinetics mechanism of the hydrogen and ammonia mixed fuel, wherein the combustion kinetics mechanism includes elementary reaction equations and reaction rate parameters; Solve the combustion kinetic equations to obtain the concentration curves of the key intermediate products OH, H and NH2 over time; The contribution of each reaction process to the overall reaction rate under different ammonia doping ratios was calculated using the local sensitivity analysis method, and the reaction chain length and branching rate were obtained. A correlation model between the ammonia ratio, the flame propagation speed and the ignition delay time is established according to the reaction chain length and the branching rate, and the flame propagation characteristics under any ammonia ratio are predicted by the cubic spline interpolation method; If the reaction chain length is greater than a preset reaction chain length threshold and the branching rate is greater than a preset branching rate threshold, it is determined that the flame is in a stable state; If the reaction chain length is less than a preset reaction chain length threshold or the branching rate is less than a preset branching rate threshold, it is determined that the flame is in an unstable state.

6. The method according to claim 1, wherein: According to the change curve and propagation characteristics, a flame stability key point discrimination criterion is established, a flame stability threshold is set, and by comparing the deviation between the actual flame parameters and the threshold, it is judged whether the flame is in a stable state under the current ammonia mixing ratio, and the occurrence conditions of the flame stability key point are determined, including: Obtaining flame characteristic data, extracting key features of flame stability using principal component analysis, classifying the key features using a K-means clustering algorithm, and obtaining feature vectors including flame length, temperature, and oscillation frequency; According to the feature vector, a flame stability discrimination model is established using a support vector machine algorithm, wherein the discrimination model uses key features as input variables and flame stability status as output variables; For the discrimination model, a flame stability threshold is set to construct a multidimensional threshold space, wherein the boundary of the multidimensional threshold space is determined by the output result of the support vector machine model; receiving an actual flame parameter under a current ammonia blending ratio, and calculating a Mahalanobis distance between the actual flame parameter and a multidimensional threshold space, wherein the Mahalanobis distance is obtained by inverting a covariance matrix and calculating a sum of squares of multidimensional eigenvector differences; If the Mahalanobis distance is less than a preset threshold, it is determined that the flame is in a stable state; When 10 consecutive data points are all located in the stable region, they are determined to be key points of flame stability, and the conditions for the occurrence of the key points of flame stability are recorded.

7. The method according to claim 1, wherein: The method aims at the occurrence conditions of the key points of flame stability, simulates the flow field distribution under different burner structures, obtains the fuel injection velocity field, measures the temperature field and species concentration field of the combustion area, and determines the influence of the burner structure on the flame stability, including: According to the fuel mixture ratio, combustion temperature and pressure parameters, a three-dimensional model of the burner structure is established, including the nozzle diameter, combustion chamber length and cross-sectional area; ANSYS Fluent software is used to perform meshing and boundary condition setting of the burner structure model; Solving the Navier-Stokes equations of fluid motion and the k-ε turbulence model to obtain the fuel injection velocity field of the burner structure model; According to the fuel injection velocity field, obtaining the velocity vector distribution and turbulence intensity distribution of the combustion area in the burner structure model; Calculating the temperature field and species concentration field of the combustion area by using a simulated combustion model and a chemical reaction kinetic equation; Obtaining a temperature distribution cloud map of the temperature field and a concentration distribution of key species in the species concentration field; Calculating the flame oscillation frequency and amplitude according to the temperature distribution cloud map and the concentration distribution of the key species; Analyzing the relationship between the burner structural parameters and the flame oscillation frequency and amplitude using a random forest regression model; If the flame oscillation frequency is lower than a preset threshold and the flame oscillation amplitude is lower than a preset threshold, it is determined that the burner structure corresponding to the burner structural parameters has good flame stability.

8. The method according to claim 1, wherein: The method uses a genetic algorithm to optimize the geometric parameters of the burner based on the analysis results of the influence of the burner structure on the flame stability, adjusts the fuel injection angle and the shape of the combustion chamber, and uses a numerical simulation method to calculate the evolution of the flame morphology under the optimized burner structure, and determines whether the optimized burner can effectively suppress the occurrence of key points of flame stability, and obtains the optimal ammonia blending ratio, including: Obtaining burner geometric parameters, fuel injection angle and combustion chamber shape, and constructing the genetic algorithm optimization model; Wherein, the genetic algorithm optimization model sets the population size, crossover rate and mutation rate; A three-dimensional computational fluid dynamics model is established based on the structural parameters obtained from the optimization model; The three-dimensional computational fluid dynamics model adopts a turbulence model and a GRI-Mech3.0 reaction mechanism; Acquiring the spatiotemporal distribution data of flame morphology evolution through the three-dimensional computational fluid dynamics model; Calculating flame oscillation frequency, flame propagation speed and flame temperature distribution according to the spatiotemporal distribution data; If the flame oscillation frequency is less than a preset frequency threshold and the amplitude is less than a preset amplitude threshold, then the ammonia blending ratio range for stable combustion is determined; The NSGA-II algorithm is used for multi-objective optimization, and flame stability, combustion efficiency and NOx emission level are set as optimization targets; Obtaining a Pareto optimal solution set based on the multi-objective optimization; Obtain performance data for optimized afterburners through small test benches; comparing the performance data with numerical simulation prediction results; The optimization parameters are adjusted according to the comparison results.

Images