Gas dust explosion prevention and control targeted explosion suppressant regulation and control method based on machine learning

Abstract

The invention relates to a gas dust explosion prevention and control targeted explosion suppressant regulation and control method based on machine learning, and belongs to the technical field of explosion prevention and control and material modification. According to the method, the inhibition effect of the explosion suppressant in a composite explosion environment is analyzed through a machine learning model, and targeted optimization is performed on the components, concentration and physical structure of the explosion suppressant based on experimental data and characteristic characterization. The method comprises the following specific steps: screening explosion suppressant components through literature investigation; carrying out modified compounding on the explosion suppressant and collecting explosion characteristic data; carrying out feature importance analysis by utilizing an XGBoost model, and identifying key factors influencing the explosion suppression effect; and optimizing the formula of the explosion suppressant according to a model analysis result, and verifying the effect through experiments. According to the method, the inhibition efficiency and adaptability of the explosion suppressant under the compound explosion condition are greatly improved, data-driven intelligent design is achieved, and the method is suitable for various industrial explosion prevention and control scenes.

Description

Technical Field

[0001] The present invention belongs to the technical field of explosion prevention and control and material modification, and relates to a method for controlling a targeted explosion suppressant for gas and dust explosion prevention and control based on machine learning. Background Art

[0002] In the fields of industry and scientific research, gas-dust compound explosion accidents are common, especially in high-risk environments such as mining, petrochemicals, tunnel construction and dust treatment. The risk of compound explosion of gas and dust poses a great threat to personnel safety and facility stability. Traditional prevention and control measures are difficult to fully cope with these compound explosion situations under complex working conditions, and powder explosion suppressants, as one of the core prevention and control measures, are often limited by the empirical design and the singleness of the modification methods. The commonly used explosion suppressants on the market currently rely mainly on the physical properties of materials and the simple compounding of inhibitory components. However, in the face of complex explosion forms such as gas-dust compound explosions, traditional explosion suppressants are insufficient in key factors such as free radical capture, thermal stability and transient diffusion performance. Existing explosion suppressants often have problems such as thermal instability, uneven dispersion and low free radical capture efficiency at the explosion site, resulting in limited explosion suppression effects. At the same time, the current development of explosion suppressants lacks systematic data analysis and model prediction methods, and the formulation optimization mainly relies on experience, which is difficult to adapt to the changing working conditions and performance requirements under extreme explosion conditions.

[0003] In recent years, with the development of big data and machine learning technology, data-driven material design has gradually emerged in the field of industrial prevention and control. Through machine learning modeling, it is possible to achieve precise control of the composition, concentration and physical structure of explosion suppressants to improve their suppression effect in complex working conditions. However, the application of existing technologies in the targeted design and optimization of explosion suppressants is still shallow, and there is still a lack of a systematic research framework and implementation path. For example, the invention with publication number CN202410912979.3 proposes a method for optimizing the ratio of polymer material additives based on big data, and the Me element and doping amount constituting the binary magnesium hydride alloy are screened out through the optimal prediction model, and the composite hydrogen storage and release material model structure is constructed through the obtained alloy; the invention with publication number CN202111360926.8 proposes a method for designing the ply angle of a composite hydrogen storage container based on machine learning, extracting unit information from the finite element model and using a normalized function to establish a database; taking the output of the neural network as the optimization target, the optimal ply angle of the composite material layer is obtained under the premise that the inner tank size and the number of ply layers remain unchanged. Publication No. CN202410437061.8 discloses a method for intelligent prediction of temperature in tunnel kilns for refractory material firing based on machine learning, which improves the accuracy and reliability of tunnel kiln temperature prediction and completes intelligent prediction of tunnel kiln temperature. Currently, this data-driven artificial intelligence method has not been used in laboratory explosion tests, and the optimization design of explosion suppressants has not received enough attention.

[0004] The current technical difficulty is how to optimize the formula of explosion suppressants through data-driven and intelligent means under complex gas-dust composite explosion conditions. Traditional experimental methods have problems such as high cost, long cycle, and low efficiency, and it is difficult to systematically analyze the explosion suppression effect under multiple components and parameter combinations. In a multi-field coupling scenario, the design of explosion suppressants must take into account multiple factors such as thermal stability, free radical capture efficiency, and physical diffusion characteristics, and these complex influencing factors are difficult to accurately analyze and quantify using traditional methods.

[0005] Based on this, the present invention proposes a method for controlling targeted explosion suppressants for gas-dust explosion prevention and control based on machine learning. This method achieves accurate optimization of the explosion suppressant formula through experimental data collection, characteristic characterization, and training and analysis of machine learning models. Through feature importance analysis, key factors that significantly affect the explosion suppression effect are screened out, so as to target and adjust the composition, concentration, and structural parameters of the explosion suppressant to improve its suppression efficiency and stability in a composite explosion environment. This method uses data-driven prediction and analysis methods, which can significantly shorten the formula optimization cycle and reduce R&D costs, providing an intelligent and systematic design approach for the prevention and control of gas-dust composite explosions, filling the gap in the existing technology in multi-factor collaborative optimization.

[0006] In summary, the present invention realizes intelligent targeted regulation of explosion suppressants by introducing data-driven machine learning technology, breaks through the limitations of traditional empirical design, provides a scientific basis for safety prevention and control under complex compound explosion conditions, and has important application value and innovative significance. Summary of the invention

[0007] In view of this, the purpose of the present invention is to provide a method for controlling targeted explosion suppressants for gas-dust explosion prevention and control based on machine learning. By systematically screening, optimizing and verifying the components and proportions of explosion suppressants, the effect of accurately suppressing compound explosions can be achieved, thereby improving the safety and reliability of gas-dust compound explosion prevention and control.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning includes the following steps:

[0010] S1: Modification and compounding of explosion suppressants: Based on the selected explosion suppressant components, optimize their chemical composition and physical structure, and improve their suppression effect in gas-dust compound explosions through modification and compounding;

[0011] S2: Explosion characteristic experiment and data collection: Under controlled conditions, the modified explosion suppressant is used to conduct a gas-dust composite explosion pre-experiment, and characteristic data of explosion pressure and explosion temperature are collected to provide a basic data set for the model;

[0012] S3: Characterization of modified explosion suppressants and database construction: Characterize the particle size distribution, specific surface area, chemical composition and surface functional groups, thermal stability and other characteristic parameters of the modified explosion suppressants, and establish a gas-dust composite explosion suppression characteristic database based on the explosion characteristic data obtained from the experiment;

[0013] S4: Training and feature analysis of machine learning models: Based on the data set in the database, the machine learning algorithm is used to train the model, build an explosion suppression characteristic prediction model, and analyze the correlation analysis and importance ranking of the output key features;

[0014] S5: Optimization design of targeted explosion suppressants: Based on the feature importance analysis results of the machine learning model, the composition, concentration and structural parameters of the explosion suppressant are adjusted through chemical modification and regulation methods, and an optimized targeted explosion suppressant formula is designed to improve the explosion suppression effect;

[0015] S6: Experimental verification and effect evaluation: Under the same experimental conditions, the optimized targeted explosion suppressant is experimentally verified to evaluate its suppression effect in gas-dust composite explosions. The experimental results are compared with the model prediction results to further optimize the explosion suppressant formula or modify the model.

[0016] Furthermore, the machine learning algorithm is an XGBoost algorithm.

[0017] Furthermore, the explosion suppressant composition includes fly ash and ammonium polyphosphate.

[0018] Furthermore, the modification method includes acid-base activation method, co-condensation and amidation impregnation.

[0019] Furthermore, the characterization method includes dynamic light scattering, specific surface area analysis, energy dispersive spectroscopy, Fourier transform infrared spectroscopy and thermogravimetric analysis.

[0020] Furthermore, the targeted optimization design includes increasing specific surface area, surface modification, adjusting particle size distribution, optimizing inhibitor mass fraction, increasing irregular particle ratio, adding thermal stability enhancer, surface chemical modification and introducing surface modifier.

[0021] Furthermore, the experimental verification includes measuring parameters of pressure and temperature during the explosion process.

[0022] Furthermore, the experimental verification results are compared and analyzed with the model prediction results to further optimize the explosion suppressant formulation or modify the model.

[0023] The beneficial effects of the present invention are:

[0024] (1) Reducing costs and experimental cycles: Through closed-loop optimization that combines model prediction with experimental verification, the present invention reduces the cost of trial and error and the number of experiments, making the design process of explosion suppressants more efficient and reliable, and significantly shortening the research and development cycle.

[0025] (2) Highly efficient suppression of compound explosion reactions: Through chemical modification of the explosion suppressant components and optimized design of the physical structure, the present invention significantly improves the suppression efficiency of the explosion suppressant in gas-dust compound explosions, effectively blocks the explosion reaction chain, reduces the generation of reactants, delays or prevents the spread of explosions, and thus improves industrial safety.

[0026] (3) Strong adaptability: The present invention adopts multi-level optimization of explosion suppressant properties, including particle size, morphology, surface functional groups and thermal stability, to ensure that the explosion suppressant has stronger stability and diffusion performance under extreme conditions such as high temperature and high pressure, and is suitable for a variety of complex explosion scenarios with wide adaptability.

[0027] (4) Data-driven targeted optimization: Based on the feature analysis and optimization process of machine learning, the present invention can identify the key factors that have a significant impact on the explosion suppression effect in a data-driven manner, thereby performing targeted design and dynamic optimization of the explosion suppressant to achieve precise adaptation to different explosion conditions.

[0028] (5) Improving the safety and reliability of industrial applications: The targeted explosion suppressant formulation optimization method of the present invention has higher explosion suppression efficiency and stability in complex industrial environments, significantly improving the safety and control effects in gas-dust composite explosion environments, and providing reliable technical support for high-risk scenarios such as mines, chemicals, and tunnels.

[0029] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0031] Figure 1 It is the overall flow chart of the present invention;

[0032] Figure 2 To characterize the physical and chemical properties of the modified explosion suppressant;

[0033] Figure 3This is the result diagram of explosion characteristic experiment data collection;

[0034] Figure 4 This is the prediction data analysis chart of the XGBoost model;

[0035] Figure 5 It is a feature correlation analysis diagram of the machine learning model;

[0036] Figure 6 Feature importance analysis diagram for machine learning models;

[0037] Figure 7 Prediction data analysis chart of the XGBoost model after updating the database. DETAILED DESCRIPTION

[0038] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0039] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0040] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0041] Figure 1 This is the overall flow chart of the present invention, showing the steps of the method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning. Figure 2To characterize the physical and chemical properties of modified explosion suppressants, including important characteristic data such as particle size distribution, specific surface area, thermogravimetric, and adsorption tests. Figure 3 This is a graph of explosion characteristics experimental data collection results, showing the dynamic changes in pressure, temperature, etc. of explosion suppressants with different components in a composite explosion. Figure 4 This is the prediction data analysis chart of the XGBoost model, showing the prediction effect of the model on the explosion feature; Figure 5 This is a feature correlation analysis diagram of the machine learning model. The Pearson correlation analysis shows the positive and negative effects of different explosion suppressant characteristics on the explosion suppression effect. Figure 6 This is a feature importance analysis diagram of the machine learning model. The ranking shows the influence of different explosion suppressant characteristics on the explosion suppression effect. Figure 7 The prediction data analysis chart of the XGBoost model after updating the database shows the match between the actual suppression effect of the designed targeted explosion suppressant and the model prediction results.

[0042] The present invention provides a method for controlling a targeted explosion suppressant for gas and dust explosion prevention and control based on machine learning. The method is a method for controlling a targeted explosion suppressant for gas and dust explosion prevention and control based on machine learning. Specifically, the molecular simulation method comprises the following specific steps:

[0043] The specific steps of the embodiment are as follows:

[0044] S1 Literature research and theoretical analysis: Based on the material science and explosion dynamics theory of explosion inhibitors, literature research is conducted to preliminarily screen the modified explosion inhibitor components and modification and regulation methods for potential composite explosions, providing a theoretical basis for modification and compounding

[0045] First, we conducted literature research and theoretical analysis, and screened out the chemical composition and physical properties of gas-coal dust composite explosion inhibitors based on the existing explosion suppression material science and composite explosion dynamics theory. Combined with relevant theoretical knowledge, we analyzed the characteristics of different materials in terms of chain reaction inhibition, free radical capture, thermal stability and surface functional groups, and determined candidate explosion suppressant components with high explosion suppression potential. The screened components will be used in subsequent experiments and model analysis to provide a scientific basis for modification and compounding.

[0046] Modification and compounding of S2 explosion suppressant: Based on the selected explosion suppressant components, optimize its chemical composition and physical structure, and improve its suppression effect in gas-dust composite explosion through modification and compounding.

[0047] According to the explosion suppressant components screened in S1, the chemical composition and physical structure are optimized through modification and compounding to improve the suppression effect in the gas-dust compound explosion environment. The specific operations include:

[0048] Modified fly ash (FAC) was used as the inner shell carrier. After residual carbon treatment, the fly ash activity was activated by acid-base activation method to obtain nitrogen-containing modified MFAC1 and MFAC2. On this basis, ammonium polyphosphate was impregnated by co-condensation and amidation to obtain phosphorus-containing modified PMFAC1 and PMFAC2.

[0049] S3 Explosion characteristic experiment and data collection: Under controlled conditions, the modified explosion suppressant is used to conduct a gas-dust composite explosion pre-experiment, and the explosion pressure is collected as characteristic data to provide a basic data set for the model.

[0050] Under the standard experimental conditions of a 20-L explosion ball, a gas-dust composite explosion pre-experiment was carried out using the modified fly ash explosion suppressant to collect key characteristic data during the explosion process, including explosion pressure, explosion temperature (such as Figure 3 The experimental data is used as the basic data set of the machine learning model to ensure that the model can accurately capture the influence of the explosion suppressant composition and modification conditions on the composite explosion suppression effect, which is convenient for subsequent model training and feature analysis.

[0051] S4 Characterization and database construction of modified explosion suppressants: Characterize the particle size distribution, specific surface area, chemical composition, surface functional groups, and thermal stability of the modified explosion suppressants, and establish a gas-dust composite explosion suppression characteristics database based on the explosion characteristics data obtained from the experiment

[0052] The physicochemical properties of the modified explosion suppressant were systematically characterized using dynamic light scattering, surface area analysis, energy dispersive spectroscopy and thermogravimetric analysis, including key properties such as particle size distribution, surface area, chemical composition, surface functional groups and thermal stability (see Figure 2). The experimental data and characterization results were integrated to establish the database of composite explosion suppressant properties, including: x1: specific surface area, x2: particle size D50 (μm), x3: particle size D90 (μm), x4: surface area average particle size (μm), x5: volume average particle size (μm), x6: aspect ratio S50, x7: convexity S50, x8: elongation S50, x9: roundness, x10: sphericity S50, x11: peak of 3410 in FTIR, x12: peak of 3430 in FTIR, x13: peak of 3220 in FTIR, x14: peak of 2920 in FTIR, x15: peak of 2130 in FTIR, x16: peak of 1630 in FTIR, x17: peak of 1690 in FTIR, x18: peak of 1690 in FTIR The peak values ​​of 1430, x19: the peak value of 1250 in FTIR, x20: the peak value of 1090 in FTIR, x21: the peak value of 1020 in FTIR, x22: the peak value of 788 in FTIR, x23: the peak value of 100℃ in thermogravimetric curve, x24: the peak value of 300 in TG curve, x25: the peak value of 550 in TG curve, x26: the peak value of 700 in thermogravimetric curve, x27: time, x28: the mass fraction of inhibitor, provide systematic input features for the machine learning model, ensuring that the model can effectively identify and extract the key factors that have a significant impact on the explosion suppression effect.

[0053] S5 Machine learning model training and feature analysis: Based on the data set in the database, use the machine learning algorithm to train the model, build an explosion suppression characteristic prediction model, and analyze the correlation analysis and importance ranking of the output key features

[0054] Based on the database built by S4, the XGBoost machine learning algorithm is used to train the data set and build an explosion suppression characteristic prediction model. The prediction results are as follows: Figure 4 As shown. Through feature correlation analysis (such as Figure 5 As shown in the figure, the correlation between the physical and chemical properties of the explosion suppressant can be observed, among which some properties have significant positive or negative correlations, such as specific surface area (x1), particle size D50 (x2), particle size D90 (x3) and other properties have a strong correlation with the performance of the explosion suppressant. The results of feature importance analysis are shown in the figure. Figure 6 As shown in the figure, the key factors that significantly affect the explosion suppression effect are determined, including time (x27), mass fraction of inhibitor (x28), specific surface area (x1), particle size D50 (x2), particle size D90 (x3) and other characteristics. These key characteristics play a leading role in the explosion suppression effect predicted by the model, providing a scientific basis for the optimization of the explosion suppression agent formulation. The model training process combines cross-validation and accuracy evaluation to ensure the adaptability and prediction accuracy of the model under different experimental conditions. This step provides a scientific basis for the optimization of the explosion suppression agent formulation through the feature analysis results of machine learning.

[0055] S6 Optimization design of targeted explosion suppressants: Based on the feature importance analysis results of the machine learning model, the composition, concentration and structural parameters of the explosion suppressant are adjusted through chemical modification and regulation methods to design an optimized targeted explosion suppressant formula to improve the explosion suppression effect

[0056] According to the feature importance analysis results output by the machine learning model, targeted optimization design is achieved by adjusting the composition, concentration and structural parameters of the explosion suppressant. The details are as follows: 1. Select nano-scale materials or further refine the explosion suppressant particles by grinding to increase the specific surface area; 2. Modify the surface of the material, such as adding functional groups to further improve the reactivity of the explosion suppressant surface; 3. Appropriately increase the small particle size component (such as D50 reduced to below 750μm) to improve the rapid diffusion ability of the explosion suppressant at the beginning of the explosion, thereby accelerating the suppression of the explosion reaction chain; 4. According to the dust concentration and scale of the explosion environment, optimize the mass fraction of the inhibitor to ensure that it can reach an effective inhibition concentration at the beginning of the explosion; 5. Increase the proportion of irregularly shaped explosion suppressant particles (appropriately reduce the roundness) so that they can be more effectively suspended in the explosion environment and improve the spatial coverage; 6. Add thermal stability enhancers (such as metal oxide nanoparticles) to improve the tolerance of the material at high temperatures, thereby improving its resistance to high temperature explosion environments. 7. Carry out surface chemical modification on explosion suppressants, use plasma surface treatment or surface coating of functional polymers to increase the number of functional groups such as hydroxyl and carbonyl to improve its free radical capture ability; 8. Introduce surface modifiers to enhance the stability and activity of functional groups to ensure that a strong inhibitory effect can be maintained in a high-temperature and high-pressure explosion environment, or use wet chemical oxidation treatment. The optimized formula will have a higher composite explosion suppression efficiency and effectively improve the prevention and control effect.

[0057] S7 Experimental verification and effect evaluation: Under the same experimental conditions, the optimized targeted explosion suppressant is experimentally verified to evaluate its suppression effect in gas-dust composite explosions, and the experimental results are compared with the model prediction results to further optimize the explosion suppressant formula or modify the model

[0058] Under the same experimental conditions as S3, the targeted explosion suppressant designed in S6 was experimentally verified, and the key data of pressure explosion characteristics during the explosion process were measured. The experimental results were compared and analyzed with the prediction results of the machine learning model, such as Figure 7 As shown, the accuracy of the model prediction is verified. If there is a deviation between the experimental results and the prediction, the explosion suppressant formula can be further optimized or the model database can be updated to ensure the stability and reliability of the explosion suppressant in practical applications and realize the targeted explosion suppressant optimization for gas-coal dust composite explosions.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A targeted explosion suppressant control method for gas and dust explosion prevention and control based on machine learning, characterized in that: The following steps are involved: S1: Modification and compounding of explosion suppressants: Based on the selected explosion suppressant components, optimize their chemical composition and physical structure, and improve their suppression effect in gas-dust compound explosions through modification and compounding; S2: Explosion characteristic experiment and data collection: Under controlled conditions, the modified explosion suppressant is used to conduct a gas-dust composite explosion pre-experiment, and characteristic data of explosion pressure and explosion temperature are collected to provide a basic data set for the model; S3: Characterization of modified explosion suppressants and database construction: Characterize the particle size distribution, specific surface area, chemical composition and surface functional groups, thermal stability and other characteristic parameters of the modified explosion suppressants, and establish a gas-dust composite explosion suppression characteristic database based on the explosion characteristic data obtained from the experiment; S4: Training and feature analysis of machine learning models: Based on the data set in the database, the machine learning algorithm is used to train the model, build an explosion suppression characteristic prediction model, and analyze the correlation analysis and importance ranking of the output key features; S5: Optimization design of targeted explosion suppressants: Based on the feature importance analysis results of the machine learning model, the composition, concentration and structural parameters of the explosion suppressant are adjusted through chemical modification and regulation methods, and an optimized targeted explosion suppressant formula is designed to improve the explosion suppression effect; S6: Experimental verification and effect evaluation: Under the same experimental conditions, the optimized targeted explosion suppressant is experimentally verified to evaluate its suppression effect in gas-dust composite explosions. The experimental results are compared with the model prediction results to further optimize the explosion suppressant formula or modify the model.

2. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The machine learning algorithm is the XGBoost algorithm.

3. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The explosion suppressant comprises fly ash and ammonium polyphosphate.

4. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The modification methods include acid-base activation, co-condensation and amidation impregnation.

5. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The characterization methods include dynamic light scattering, specific surface area analysis, energy dispersive spectroscopy, Fourier transform infrared spectroscopy and thermogravimetric analysis.

6. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The targeted optimization design includes increasing specific surface area, surface modification, adjusting particle size distribution, optimizing inhibitor mass fraction, increasing irregular particle ratio, adding thermal stability enhancer, surface chemical modification and introducing surface modifier.

7. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The experimental verification includes measuring the parameters of pressure and temperature during the explosion.

8. The method for controlling targeted explosion suppressants for gas and dust explosion prevention and control based on machine learning according to claim 1 is characterized in that: The experimental verification results are compared and analyzed with the model prediction results to further optimize the explosion suppressant formulation or modify the model.

Images