Combustible Substance Inversion Method Based on Combustion Product Markers

Abstract

The present invention belongs to the technical field of combustible type identification and monitoring, and discloses a method for inverting combustibles based on combustion product markers. By constructing an artificial intelligence dynamic inversion algorithm model, the present invention further inverts the type and content of combustibles, realizes the intelligent analysis and processing of multi-dimensional data, can accurately analyze the complex relationship between combustion products and combustibles, and can also accurately invert in a mixed combustion scenario, improving the accuracy of combustible identification. Through gas chromatography-mass spectrometry detection and analysis, and then qualitative and quantitative analysis of characteristic markers based on the original detection data, the present invention is applicable to various organic compounds and some inorganic compounds, greatly expanding the scope of research and application. The present invention can be adapted to the smoldering stage or combustion stage of a fire scene, can identify and analyze combustibles in real time, provide a basis for curbing the spread of fire, and minimize fire losses to the greatest extent.

Description

Technical Field

[0001] The present invention belongs to the technical field of combustible type identification and monitoring, and relates to a method for retrieving combustibles based on combustion product markers. Background Art

[0002] During fire fighting, accurately grasping the combustible conditions in the fire scene is crucial for implementing effective fire extinguishing measures. However, the current means of obtaining combustible information in the fire scene are relatively limited, mainly relying on manual observation and asking insiders, etc., and there are problems such as inaccurate information. Therefore, the research on retrieving combustibles based on combustion product markers is of great significance.

[0003] There are also technical solutions for combustible type identification and monitoring in the prior art. For example, a Chinese invention patent application for a simulation method and a dedicated simulation device for combustion in a special environmental atmosphere with the publication number CN108181422A includes: introducing a mixed gas of a combustion-supporting gas and an environmental atmosphere into a burner for combustion reaction; then performing combustion gas detection: analyzing the gas generated after combustion can determine the gas components generated by combustion in a special environmental atmosphere.

[0004] In addition, a Chinese invention patent application for a method for detecting liquid combustibles in a fire scene with the publication number CN105699236A includes: selecting a metal material at the fire scene, accurately weighing it and then putting it into an experimental container, and determining whether the fire is caused by liquid combustibles by detecting the weight gain of the metal material affected by the fire.

[0005] Although the above two solutions propose some solutions for combustible type identification and monitoring, there are still certain limitations: on the one hand, in the first solution, after obtaining combustion product information through a certain method, the combustible information in the fire scene is retrieved by relying on manual experience judgment. This analysis method has high requirements for the judge and cannot accurately know the current combustible type, quantity, and pyrolysis degree, etc.; on the other hand, in the second solution, by detecting the weight gain of the metal material at the fire scene affected by the fire, and then determining whether the fire is caused by liquid combustibles, this analysis method greatly reduces the timeliness and availability of fire source location in the fire scene. Summary of the Invention

[0006] In view of this, to solve the problems of high manual dependence and low accuracy of combustible identification in the above-mentioned background technology, the present invention collects the gases generated by the smoldering pyrolysis of combustibles in the air, uses a gas chromatograph to detect and analyze their components and concentrations, and further analyzes and processes the complex data of combustion product markers of multiple scenarios and multiple types of fire sources with the help of artificial intelligence algorithms, and explores the changing rules of combustibles hidden behind the component and concentration data of combustion product markers, so as to open up a new inversion path and improve the inversion accuracy. Now, a method for inverting combustibles based on combustion product markers is proposed.

[0007] The object of the present invention can be achieved by the following technical solutions: A method for inverting combustibles based on combustion product markers, including: S1. Using a filter to capture aerosols in fire smoke, and using an extraction liquid to perform oscillating extraction on the captured aerosols to obtain a test solution.

[0008] S2. Perform gas chromatography-mass spectrometry (GC-MS) detection and analysis on the test solution to obtain a chromatographic elution curve, and obtain corresponding original detection data based on the chromatographic elution curve.

[0009] S3. Perform qualitative and quantitative analysis of characteristic markers based on the original detection data to obtain the types of characteristic markers of each effective peak and the effective peak areas of each characteristic marker, and analyze the mass fraction and volume fraction of each characteristic marker.

[0010] S4. Import the mass fraction and volume fraction of each characteristic marker into an artificially intelligent dynamic inversion algorithm model pre-trained to invert the type and content of combustibles.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) By constructing an artificially intelligent dynamic inversion algorithm model, the present invention inverts the type and content of combustibles, realizes the intelligent analysis and processing of multi-dimensional data, can accurately analyze the complex relationship between combustion products and combustibles, and can also accurately invert in a mixed combustion scenario, improving the accuracy of combustible identification.

[0012] (2) Through gas chromatography-mass spectrometry (GC-MS) detection and analysis, and then performing qualitative and quantitative analysis of characteristic markers based on the original detection data, this analysis method is applicable to various organic compounds and some inorganic compounds. Whether it is the combustion product of a simple single combustible or the complex smoke generated by the mixed combustion of multiple combustibles, it can be effectively analyzed, greatly expanding the scope of research and application.

[0013] (3) The present invention can be adapted to the smoldering stage or combustion stage of a fire scene, can identify and analyze combustibles in real time, accurately capture the characteristic markers of trace combustion products, determine potential combustibles, provide a basis for curbing the spread of fire, help formulate an efficient fire extinguishing plan, and minimize fire losses to the greatest extent. Description of the Drawings

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for describing the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0015] Figure 1 It is a schematic diagram of the implementation steps of the method of the present invention.

[0016] Figure 2 It is a schematic diagram of the gas sample flow direction for gas chromatography - mass spectrometry detection and analysis corresponding to an embodiment provided by the present invention.

[0017] Figure 3 It is a logic flow chart of effective time series recognition corresponding to an embodiment provided by the present invention. Specific embodiments

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0019] Please refer to Figure 1 As shown, the present invention provides a method for inverting combustibles based on combustion product markers, including: S1. Using a filter to capture aerosols in fire smoke, and using an extraction solution to perform oscillating extraction on the captured aerosols to obtain a test solution.

[0020] It should be noted that the purpose of implementing this step is to obtain a test solution containing combustion product markers in fire smoke and suitable for subsequent detection and analysis. The composition of fire smoke is complex, and the aerosols contain key information related to combustibles, such as specific volatile organic compounds and other combustion product markers. However, it is difficult to directly detect these markers. By capturing aerosols with a filter, the target substances therein can be preliminarily enriched. And by performing oscillating extraction with an extraction solution, according to the principle of similar solubility, the extraction solution can be fully contacted with the aerosols, so that the combustion product markers in the aerosols are dissolved into the extraction solution, thereby obtaining a uniform and easily detectable test solution, providing a suitable sample for subsequent determination of the composition and content of combustibles through gas chromatography - mass spectrometry detection and analysis.

[0021] In a preferred embodiment of the present invention, the specific operation method for oscillating and extracting the captured aerosol is as follows: The filter used in the operation of capturing the aerosol in the fire smoke by the filter is immersed in the pre-prepared extraction liquid, and then an oscillating operation is performed based on the pre-set vibration frequency and vibration duration to obtain a liquid to be tested.

[0022] It should be noted that the present invention is applicable to the smoldering stage or the combustion stage of a fire scene, can identify and analyze combustibles in real time, accurately capture the characteristic markers of trace combustion products, determine potential combustibles, provide a basis for curbing the spread of fire, assist in formulating an efficient fire extinguishing plan, and minimize fire losses to the greatest extent.

[0023] S2. Perform gas chromatography-mass spectrometry (GC-MS) detection and analysis on the liquid to be tested to obtain a chromatographic effluent curve, and obtain the corresponding original detection data based on the chromatographic effluent curve.

[0024] It should be noted that a gas chromatography method is used to invert the combustion product markers. Chromatography, also known as chromatography or chromatography, is a physical and chemical separation method that utilizes the properties of substances such as solubility and adsorption. The separation principle is based on the differences in the interactions between the components in the mixture in the mobile phase and the stationary phase as the separation basis.

[0025] In a preferred embodiment of the present invention, please refer to Figure 2 As shown, the specific analysis method for performing gas chromatography-mass spectrometry (GC-MS) detection and analysis is as follows: The liquid to be tested obtained by oscillating extraction is injected into a gas chromatograph, and then a gasification operation is performed to obtain a gas sample. The gas sample is respectively decompressed through a pressure reducing valve, purified through a drying tube, and then flows into a chromatographic column at a preset pressure and a preset flow rate through a pressure stabilizing valve and a flow meter for separation. Then, the separated components flow into a detector for detection in sequence to obtain a chromatographic effluent curve.

[0026] It should be supplemented that the specific implementation methods and corresponding principles of each step are as follows: 1. Injection into the gas chromatograph and gasification: Injecting the liquid to be tested after oscillating extraction into the gas chromatograph and gasifying it is because the separation principle of gas chromatography is based on the distribution behavior of substances in the gaseous state. Only by converting the liquid to be tested into a gas sample can the various components therein be separated in the chromatographic column under the drive of the carrier gas. After the liquid becomes a gas, the molecular movement is more free, which is conducive to subsequent separation operations.

[0027] 2. Pressure reduction: The gas sample is decompressed through a pressure reducing valve to make the gas pressure reach the range required for the normal operation of the gas chromatograph. Excessive pressure may damage the instrument components and also affect the flow state and separation effect of the gas in the instrument. By reducing the pressure, the stable operation of the instrument can be ensured, and the gas sample can enter the subsequent process at an appropriate pressure.

[0028] 3. Purification: The gas sample is purified through a drying tube to remove impurities and moisture. Impurities and moisture may contaminate the chromatographic column, affect the separation effect, and may also damage the detector, reducing the accuracy of detection and the service life of the instrument. The purified gas sample is purer, ensuring the reliability of the detection results.

[0029] 4. Pressure and flow rate stabilization: Through a pressure regulator valve and a flow meter, the gas sample flows into the chromatographic column at a preset pressure and a preset flow rate. This is the key to ensuring stable and reproducible separation effects. Stable pressure and flow rate enable different components to be separated in the chromatographic column according to fixed rules. If the pressure and flow rate are unstable, the residence time of each component in the chromatographic column will change, resulting in a deteriorated separation effect and an inability to accurately obtain information about each component.

[0030] 5. Separation, detection, and obtaining the chromatographic effluent curve: Different components in the chromatographic column have different moving speeds due to different interactions with the stationary phase, thus achieving separation. Each separated component flows into the detector for detection in sequence. The detector converts the concentration or mass change of each component into an electrical signal and records these electrical signals over time, ultimately forming a chromatographic effluent curve. The chromatographic effluent curve contains information such as the retention time, peak area, or peak height of each component. These information are important bases for subsequent qualitative and quantitative analysis. Through the analysis of the curve, it can be determined which components are contained in the test solution (qualitative analysis) and the content of each component (quantitative analysis).

[0031] In a preferred embodiment of the present invention, please refer to Figure 3 As shown, the specific method for obtaining the corresponding original detection data is as follows: Specifically, the original monitoring data includes the number of effective peaks and the retention time corresponding to each effective peak.

[0032] Extract the chromatographic effluent curve, obtain the output electrical signal intensity corresponding to each time series of this chromatographic effluent curve, and then compare it with the pre-set recognizable electrical signal intensity respectively. If the output electrical signal intensity of a certain time series is greater than the recognizable electrical signal intensity, identify this time series as an effective time series.

[0033] It should be further noted that the chromatographic elution curve is a curve showing the change of the signal detected by the detector over time. Its essence is the change of the output electrical signal intensity over time series. A recognizable electrical signal intensity is preset as a threshold, which is determined according to the detection limit of the instrument and experimental experience. Signals below this threshold may be caused by instrument noise or other interference factors and do not represent the true sample component signals. By comparing the output electrical signal intensities of each time series in the chromatographic elution curve with this threshold, when the output electrical signal intensity of a certain time series is greater than the recognizable electrical signal intensity, it is considered that this time series corresponds to the signal generated by a certain component in the sample, and it is identified as a valid time series. This step is to screen out the signals that truly reflect the sample components.

[0034] Based on the continuity of the time series, each valid time series is separated to obtain each set of valid time series, and the output electrical signal intensities corresponding to each valid time series in each set of valid time series are extracted.

[0035] It should be further noted that since there may be multiple components in the sample, the valid time series generated by these components may overlap or appear at intervals. Based on the continuity of the time series, adjacent valid time series are combined into a set, so that each set of valid time series corresponds to a possible sample component peak. For example, if there is a continuous time series greater than the recognizable electrical signal intensity, then this section constitutes a set of valid time series. If there is a signal interval below the threshold in the middle, it is divided into different sets. At the same time, the output electrical signal intensities of each valid time series in each set of valid time series are extracted, and these intensity information can be used for further analysis of the peak characteristics, such as peak height, peak area, etc., to prepare for quantitative analysis.

[0036] Count the number of each set of valid time series, denoted as the number of valid peaks.

[0037] It should be noted that by counting the number of the obtained sets of valid time series, the value obtained is the number of valid peaks. This number directly reflects the number of components with obvious signals detected from the sample under the current detection conditions, that is, the number of possible different characteristic markers, providing preliminary data support for subsequent determination of the types of combustible components in the sample.

[0038] Extract each valid time series corresponding to each set of valid time series, and then arrange them in chronological order to obtain the end time series and start time series corresponding to each set of valid time series, and calculate the difference to obtain the duration corresponding to each set of valid time series, denoted as the retention time of each valid peak.

[0039] S3. Qualitatively and quantitatively analyze the characteristic markers based on the original detection data to obtain the types of characteristic markers for each effective peak and the effective peak areas of each characteristic marker, and analyze the mass fraction and volume fraction of each characteristic marker.

[0040] It should be explained that a characteristic marker refers to a chemical substance generated by a specific combustible during the combustion process and capable of characterizing the presence or characteristics of the combustible. Different types of combustibles will produce different types and proportions of combustion products due to differences in their chemical compositions and structures during combustion. The representative components among these products that can be used as judgment bases are the characteristic markers. For example, wood combustion will produce some unique volatile organic compounds and furan substances, which can be used as characteristic markers for wood combustion; while petroleum product combustion will produce specific aromatic hydrocarbon compounds and other characteristic markers.

[0041] In a preferred embodiment of the present invention, the specific analysis process of the qualitative analysis is as follows: Extract the retention time corresponding to each effective peak, and then calculate the absolute value of the difference between each effective peak and the reference retention time of each pre-stored characteristic marker respectively to obtain the retention time deviation amount of each effective peak relative to each characteristic marker. Arrange the retention time deviation amounts of each effective peak relative to each characteristic marker in ascending order, and select the characteristic marker corresponding to the smallest retention time deviation amount as the type of characteristic marker corresponding to the effective peak.

[0042] It should be noted that the explanations for the qualitative analysis are as follows: 1. Basis for retention time comparison: In chromatographic analysis, different substances have unique retention times under the same chromatographic conditions, just like everyone has a unique fingerprint. The reference retention times of each characteristic marker are pre-stored. These reference values are accurate data obtained from multiple measurements under standard conditions and represent the time from sample injection to peak elution of each characteristic marker under ideal conditions. Extract the retention time of each effective peak from the actual detected chromatographic elution curve, which is the time record of the actual components in the sample eluting from the column.

[0043] 2. Calculate the retention time deviation amount: Calculate the difference between the retention time of each effective peak and the reference retention time of all pre-stored characteristic markers one by one, and then take the absolute value. Taking the absolute value is to unify the measurement direction of the deviation and avoid the cancellation of positive and negative differences, so that all deviation amounts can reflect the actual time difference. For example, the retention time of an effective peak is 10 seconds, and the reference retention time of a certain characteristic marker is 8 seconds, and the calculated difference is 2 seconds. If the reference retention time of another characteristic marker is 11 seconds, the difference is 3 seconds. In this way, the retention time deviation amounts of each effective peak relative to each characteristic marker are obtained, and these deviation amounts reflect the degree of difference between the actual detected peak and the standard elution time of the known characteristic marker.

[0044] 3. Determine the type of characteristic marker: Arrange the retention time deviation amounts of each effective peak relative to each characteristic marker in ascending order. The smaller the deviation amount, the closer the retention time of the actually detected peak is to the reference retention time of the characteristic marker, which means that the component corresponding to the effective peak is more likely to be this characteristic marker. Therefore, select the characteristic marker corresponding to the smallest deviation amount as the type of characteristic marker corresponding to the effective peak. For example, if the retention time deviation amounts of an effective peak relative to characteristic markers A, B, and C are 2 seconds, 3 seconds, and 4 seconds respectively, then the characteristic marker A corresponding to the smallest deviation amount of 2 seconds is determined as the type of characteristic marker corresponding to the effective peak, thus completing the preliminary qualitative judgment of the component of the effective peak.

[0045] In a preferred embodiment of the present invention, the specific analysis process of the quantitative analysis is as follows: Use image processing software to obtain the peak areas corresponding to each effective time series set, which are recorded as the effective peak areas of each effective peak, and then serve as the effective peak areas of each characteristic marker.

[0046] Using the formula Analyze to obtain the effective peak area percentage of each characteristic marker , where represents the effective peak area of the th characteristic marker, represents the number of the characteristic marker, , represents the number of characteristic markers.

[0047] It should be explained that the construction logic of the effective peak area percentage of each characteristic marker: represents the effective peak area of the th characteristic marker, which is a quantitative manifestation of the marker in the detection spectrum. The peak area is related to the properties such as the content of the marker and is the key data of a single marker. is the sum of the effective peak areas of all characteristic markers, obtaining the total peak area of all markers, reflecting the overall situation. Divide the effective peak area of a single marker by the total peak area of all markers, and then multiply by , and the obtained is the effective peak area percentage of the th characteristic marker among all markers. In this way, the relative importance or content ratio of each characteristic marker in the mixture can be intuitively compared.

[0048] In a preferred embodiment of the present invention, the specific analysis methods of the mass fraction and volume fraction are as follows: Extract the effective peak area percentage of each characteristic marker .

[0049] Using the formula The mass fractions corresponding to each characteristic marker are obtained through analysis , where represents the relative response factor of the th characteristic marker

[0050] It should be explained that the relative response factor is an important parameter used in chromatographic analysis to correct the response differences of different substances on the detector, ensuring that the quantitative analysis results more accurately reflect the true content of each substance in the sample. In chromatographic analysis, the response sensitivities of different substances on the same detector are different. Even if the actual contents of two substances are the same, the peak areas or peak heights they produce may be different. For example, the contents of substance A and substance B in the sample are both 1%, but due to the different responses of the detector to them, the peak area of substance A may be twice that of substance B. The relative response factor is a parameter introduced to correct this difference

[0051] It should be further explained that the construction idea of the formula: 1. In is the percentage of the effective peak area of the th characteristic marker calculated previously, which reflects the relative proportion of this marker in the peak areas of all markers; is the relative response factor of the th characteristic marker. The response degrees of different substances on the detection instrument are different, and the relative response factor is used to correct this difference, making the peak area more accurately correlated with the actual amount of the substance. The multiplication of the two comprehensively considers the peak area proportion and response characteristics of this marker

[0052] 2. is the sum of "percentage of effective peak area × relative response factor" for all characteristic markers, representing the total amount after comprehensive consideration of all markers, and is used to provide a reference standard for the total amount

[0053] 3. Divide the numerator by the denominator and then multiply by , and the obtained is the mass fraction corresponding to the th characteristic marker. In this way, the actual mass proportion of each characteristic marker in the mixture can be more accurately reflected, eliminating the influence caused by the response differences of different substances

[0054] In a feasible simulation process, assume that there are 3 characteristic markers ( ), and based on the above formula, data simulation is carried out to obtain the corresponding simulation calculation results. Some simulation results can be referred to in Table 1

[0055] Table 1. Partial simulation data and simulation calculation results

[0056]

[0057] In the above simulation results, the mass fraction of characteristic marker 1 is approximately 32.4%, which means that after considering the peak area ratio and relative response factor, its proportion in the mixture mass is approximately 32.4%. Although the percentage of its effective peak area is 0.3 (smaller compared to characteristic marker 2), the relative response factor of 0.8 makes it not lag too far behind in terms of mass proportion.

[0058] The mass fraction of characteristic marker 2 is approximately 40.5%, which is the highest among the three markers in terms of mass proportion. Its percentage of effective peak area is 0.5 and the relative response factor is 0.6, and the combination of the two makes its proportion in the mixture relatively large.

[0059] The mass fraction of characteristic marker 3 is approximately 27.0%, and the percentage of effective peak area and relative response factor are 0.2 and 1.0 respectively. Compared with the other two markers, its mass proportion in the mixture is the lowest.

[0060] Using the formula the volume fractions corresponding to each characteristic marker are analyzed , where represents the density of the th characteristic marker pre - stored.

[0061] In a preferred embodiment of the present invention, the specific analysis method of the relative response factor: Standard samples of each characteristic marker with different concentrations are prepared in advance, and then a gas chromatograph is used to detect the standard samples of each characteristic marker with different concentrations to obtain the standard effective peak areas of each characteristic marker at each concentration.

[0062] Impurity samples of each characteristic marker with a specific concentration are prepared in advance, and then a gas chromatograph is used to detect the impurity samples of each characteristic marker with a specific concentration to obtain the control effective peak areas of each characteristic marker at the specific concentration.

[0063] Using the formula the relative response factors of each characteristic marker are analyzed , where represents the control effective peak area of each characteristic marker at a specific concentration, represents the th standard effective peak area corresponding to the th concentration standard sample of the th characteristic marker, represents the specific concentration of the impurity sample of the th characteristic marker, represents the th concentration corresponding to the th concentration standard sample of the , represents the quantity of concentration.

[0064] It should be noted that the construction idea of the above formula is as follows: 1. What is calculated is the ratio of the control effective peak area of the th characteristic marker at a specific concentration to this concentration. This ratio reflects the peak area corresponding to the unit concentration of this marker under specific conditions, and it is the quantification of the response of this marker under this specific reference.

[0065] 2. is for the th characteristic marker, for the

[0066] standard samples of different concentrations, calculate the ratio of their standard effective peak areas to the corresponding concentrations respectively, and then find the average value of these ratios. It represents the average response of this marker at multiple different concentrations. 3. What is obtained by dividing the numerator by the denominator is the

[0067] relative response factor, which is used to measure the relative relationship between the response of the th characteristic marker at a specific concentration and the average response at multiple concentrations. Through this factor, the response differences of different characteristic markers due to their own property differences during detection can be corrected, so as to more accurately analyze information such as the content of each marker in the subsequent process. ), and based on the above formula for data simulation, the corresponding simulation calculation results are obtained. Some simulation results can be referred to Table 2.

[0068] Table 2. Some simulation data and simulation calculation results

[0069]

[0070] For the above simulation results, for characteristic marker 1, the ratio of the peak area per unit concentration at a specific concentration to the ratio of the average peak area per unit concentration at multiple concentrations, the relative response factor is approximately 0.54. This indicates that in this detection system, compared with its average response at multiple concentrations, the response at a specific concentration is relatively weak.

[0071] The situation of biomarker 2 is similar. When the peak area ratio per unit concentration at a specific concentration is compared with the average peak area per unit concentration, the relative response factor is also approximately 0.54. This indicates that the response degree of biomarker 2 at a specific concentration is relatively weak compared to its average response degree at multiple concentrations, and is similar to the relative response situation of biomarker 1. The relative response factor can be used for subsequent calibration calculations of information such as the content of biomarkers, making the analysis results more accurate.

[0072] It should be noted that in the present invention, gas chromatography-mass spectrometry is used for detection and analysis, and then qualitative and quantitative analysis of biomarkers is carried out based on the original detection data. This analysis method is applicable to various organic compounds and some inorganic compounds. Whether it is the combustion products of simple single combustibles or the complex flue gas generated by the mixed combustion of multiple combustibles, effective analysis can be carried out, greatly expanding the research and application scope.

[0073] S4. Import the mass fraction and volume fraction of each biomarker into the pre-trained artificial intelligence dynamic inversion algorithm model to invert the type and content of combustibles.

[0074] In a preferred embodiment of the present invention, the specific training method of the artificial intelligence dynamic inversion algorithm model is as follows: Extract a large number of historically saved combustible combustion data, specifically including the type and content of combustibles, as well as the corresponding types of biomarkers after combustion, the mass fraction and volume fraction of each biomarker.

[0075] The artificial intelligence dynamic inversion algorithm model is obtained through continuous training of the above data by an artificial intelligence algorithm.

[0076] It needs to be explained that the purpose of the training method of the artificial intelligence dynamic inversion algorithm model is to enable the model to learn the internal relationship between the type and content of combustibles and the biomarkers of combustion products, so as to achieve the goal of accurately inverting combustibles based on combustion products. For example, collect combustion product data generated by different combustibles such as various woods, plastics, and fabrics under different combustion conditions to form a rich data set.

[0077] In a preferred embodiment of the present invention, the specific method for inverting the type and content of combustibles is as follows: Extract the mass fraction and volume fraction of each biomarker and input them into the artificial intelligence dynamic inversion algorithm model respectively.

[0078] Obtain the pre-saved combustion records of each combustible, specifically including the type and content of combustibles, reference biomarkers, and the reference mass fraction and reference volume fraction of each reference biomarker.

[0079] Compare the reference characteristic markers corresponding to each combustible combustion record with the input characteristic markers. If the type of the reference characteristic marker corresponding to a certain combustible combustion record is the same as the type of the input characteristic marker, use this combustible combustion record as the reference combustible combustion record.

[0080] Extract the reference mass fraction and reference volume fraction of each reference characteristic marker corresponding to each reference combustible combustion record, and then compare them with the mass fraction and volume fraction of each input characteristic marker respectively to obtain the mass fraction similarity and volume fraction similarity of each characteristic marker.

[0081] In a feasible embodiment, the specific analysis method of the mass fraction similarity of each characteristic marker: Calculate the absolute value after taking the difference between the reference mass fraction of each reference characteristic marker corresponding to each reference combustible combustion record and the mass fraction of each input characteristic marker, and then calculate the ratio with the mass fraction of each input characteristic marker to obtain the mass fraction similarity of each characteristic marker.

[0082] In a feasible embodiment, the specific analysis method of the mass fraction similarity of each characteristic marker can refer to the specific analysis method of the volume fraction similarity of each characteristic marker.

[0083] Sum up the mass fraction similarity and volume fraction similarity of each characteristic marker according to the weights to obtain the similarity of each characteristic marker, and then perform an average calculation to obtain the reference evaluation index of each reference combustible combustion record.

[0084] It should be noted that different characteristic markers may have different importance in judging the type and content of combustibles, so corresponding weights are assigned to the mass fraction similarity and volume fraction similarity respectively. The determination of the weights is usually based on professional knowledge, experience, and the analysis of a large amount of experimental data. For example, some characteristic markers have a stronger indication effect on a specific combustible type, and their corresponding weights will be larger. Exemplarily, the weight corresponding to the mass fraction similarity is 0.6, and the weight corresponding to the volume fraction similarity is 0.4.

[0085] Compare the reference evaluation indexes of each reference combustible combustion record, select the reference combustible combustion record corresponding to the maximum reference evaluation index as the target combustible combustion record, and output the combustible type and content corresponding to the target combustible combustion record as the combustible type and content.

[0086] It should be noted that the reference evaluation index comprehensively reflects the similarity between the currently detected characteristic markers of combustion products and the combustion records of each reference combustible. In actual fire scenarios, the characteristic markers of combustion products contain key information about the combustibles. Different combustibles produce characteristic markers with unique proportions and types when burning. By calculating the reference evaluation indices of the combustion records of each reference combustible in the previous steps and comparing these indices, the reference record that is closest to the characteristics of the current combustion products can be found. For example, there are three reference combustible combustion records A, B, and C, with corresponding reference evaluation indices of 0.8, 0.6, and 0.7 respectively. The higher the index, the more similar it is to the characteristics of the current combustion products. Therefore, the record of A has the highest matching degree with the current situation.

[0087] It should be noted that the present invention constructs an artificial intelligence dynamic inversion algorithm model to invert the type and content of combustibles, thereby realizing the intelligent analysis and processing of multi-dimensional data, being able to accurately analyze the complex relationship between combustion products and combustibles, and being able to accurately invert even in mixed combustion scenarios, improving the accuracy of combustible identification.

[0088] The above content is only an example and explanation of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for retrieving combustibles based on combustion product markers, characterized in that, Including: S1. Use a filter to capture aerosols in fire smoke, and use an extraction liquid to perform oscillating extraction on the captured aerosols to obtain a test solution; S2. Perform gas chromatography-mass spectrometry (GC-MS) detection and analysis on the test solution to obtain a chromatographic effluent curve, and obtain corresponding original detection data based on the chromatographic effluent curve; The specific method for obtaining the corresponding original detection data is as follows: The original detection data includes the number of effective peaks and the retention time corresponding to each effective peak; Extract the chromatographic effluent curve, obtain the output signal intensity of the chromatographic effluent curve corresponding to each time series, and then compare it with the pre-set recognizable signal intensity respectively. If the output signal intensity of a certain time series is greater than the recognizable signal intensity, identify this time series as an effective time series; Separate each effective time series based on the continuity of the time series to obtain each set of effective time series, and extract the output signal intensity of each effective time series corresponding to each set of effective time series; Count the number of each set of effective time series, which is recorded as the number of effective peaks; Extract each effective time series corresponding to each set of effective time series, and then arrange them in chronological order to obtain the end time series and start time series corresponding to each set of effective time series, and perform difference calculation to obtain the duration corresponding to each set of effective time series, which is recorded as the retention time of each effective peak; S3. Perform qualitative and quantitative analysis of characteristic markers based on the original detection data to obtain the type of characteristic markers of each effective peak and the effective peak area of each characteristic marker, and analyze the mass fraction and volume fraction of each characteristic marker; S4. Import the mass fraction and volume fraction of each characteristic marker into the pre-trained artificial intelligence dynamic inversion algorithm model to invert the type and content of combustibles; The specific training method of the artificial intelligence dynamic inversion algorithm model is as follows: Extract a large number of historical combustible combustion data, specifically including the type and content of combustibles, as well as the type of characteristic markers after combustion, the mass fraction and volume fraction of each characteristic marker; Continuously train through an artificial intelligence algorithm based on the combustible combustion data to obtain the artificial intelligence dynamic inversion algorithm model.

2. The combustible substance inversion method based on combustion product markers according to claim 1, characterized in that: The specific operation method for performing oscillating extraction on the captured aerosols is as follows: Immerse the filter used in the operation of capturing aerosols in fire smoke with the filter into the pre-prepared extraction liquid, and then perform oscillating operation based on the pre-set vibration frequency and vibration duration to obtain a test solution.

3. The combustible inversion method based on combustion product markers according to claim 2, characterized in that: The specific analysis method for performing gas chromatography-mass spectrometry detection and analysis is as follows: Inject the test solution obtained by oscillating extraction into a gas chromatograph, and then perform vaporization operation to obtain a gas sample. The gas sample is respectively decompressed through a pressure reducing valve, purified through a drying tube, and then flows into a chromatographic column at a preset pressure and preset flow rate through a pressure stabilizing valve and a flow meter for separation. Then, the separated components flow into a detector for detection in sequence to obtain a chromatographic effluent curve.

4. The combustible inversion method based on combustion product markers according to claim 1, characterized in that: The specific analysis process of the qualitative analysis is as follows: Extract the retention times corresponding to each effective peak, and then calculate the absolute values of the differences between the retention times of each effective peak and the reference retention times of each pre-stored characteristic marker to obtain the retention time deviation of each effective peak relative to each characteristic marker. Arrange the retention time deviations of each effective peak relative to each characteristic marker in ascending order, and select the characteristic marker corresponding to the smallest retention time deviation as the characteristic marker type corresponding to the effective peak.

5. The combustible inversion method based on combustion product markers according to claim 4, characterized in that: The specific analysis process of the quantitative analysis is as follows: Use image processing software to obtain the effective peak areas of each effective peak, and then use them as the effective peak areas of each characteristic marker; Using the formula Analyze to obtain the effective peak area percentage of each characteristic marker , where represents the effective peak area of the th characteristic marker, represents the number of the characteristic marker, , represents the number of characteristic markers.

6. The combustible inversion method based on combustion product markers as claimed in claim 5, wherein: The specific analysis methods of the mass fraction and volume fraction are as follows: Extract the effective peak area percentage of each characteristic marker ; Using the formula the mass fractions corresponding to each characteristic marker are obtained through analysis , where represents the relative response factor of the th characteristic marker; Using the formula the volume fraction corresponding to each characteristic marker is obtained by analysis , where represents the density of the th characteristic marker pre - saved 7. The combustible inversion method based on combustion product markers according to claim 6, characterized in that: The specific analysis method of the relative response factor: Prepare standard samples of each characteristic marker with different concentrations in advance, and then use a gas chromatograph to detect the standard samples of each characteristic marker with different concentrations to obtain the standard effective peak areas of each characteristic marker at each concentration; Prepare impurity samples of each characteristic marker with a specific concentration in advance, and then use a gas chromatograph to detect the impurity samples of each characteristic marker with a specific concentration to obtain the control effective peak areas of each characteristic marker at the specific concentration; Using the formula Analyze to obtain the relative response factors of each characteristic marker , where represents the control effective peak area of each characteristic marker at a specific concentration, represents the th characteristic marker, and the standard effective peak area corresponding to the th concentration standard sample, represents the specific concentration of the impurity sample of the th characteristic marker, represents the th characteristic marker, and the concentration corresponding to the th concentration standard sample, represents the number of the concentration, , represents the number of concentrations.

8. The combustible inversion method based on combustion product markers according to claim 1, characterized in that: The specific method for inverting the combustible type and content is as follows: Extract the mass fraction and volume fraction of each characteristic marker and input them into the artificial intelligence dynamic inversion algorithm model respectively; Obtain the combustion records of each combustible pre-stored, specifically including the combustible type and content, reference characteristic markers, and the reference mass fraction and reference volume fraction of each reference characteristic marker; Compare the reference characteristic markers corresponding to each combustible combustion record with the input characteristic markers. If the type of the reference characteristic marker corresponding to a combustible combustion record is the same as the type of the input characteristic marker, regard this combustible combustion record as the reference combustible combustion record; Extract the reference mass fraction and reference volume fraction of each reference characteristic marker corresponding to each reference combustible combustion record, and then compare them with the mass fraction and volume fraction of each input characteristic marker respectively to obtain the mass fraction similarity and volume fraction similarity of each characteristic marker; Sum the mass fraction similarity and volume fraction similarity of each characteristic marker according to the weight to obtain the similarity of each characteristic marker, and then calculate the mean value to obtain the reference evaluation index of each reference combustible combustion record; Compare the reference evaluation indexes of each reference combustible combustion record, select the reference combustible combustion record corresponding to the maximum reference evaluation index as the target combustible combustion record, and output the combustible type and content corresponding to the target combustible combustion record as the combustible type and content.

Images