System for predicting content of methanol and ethanol in vehicle gasoline

Abstract

The invention provides a system for predicting the content of methanol and ethanol in automotive gasoline, and relates to the technical field of chemical analysis and detection. The method comprises the following steps: firstly, carrying out first chemical treatment on first gasoline to improve the significance of aromatic hydrocarbon, olefin and other components, determining the proportion of an association body according to the components except alcohols in the first gasoline, and further determining a first spectral peak position offset; secondly, carrying out second chemical treatment on the first gasoline, respectively obtaining a characteristic peak combination of each alcohol component so as to remarkably improve the significance, and determining a plurality of first key wavelengths based on each characteristic peak combination; and finally, determining a plurality of corresponding first absorbance values based on the plurality of target key wavelengths so as to finally determine the content of each target component in the first gasoline. According to the method, chemometrics, near infrared spectroscopy and artificial intelligence means are combined, the gasoline component recognition precision is greatly improved, and nonlinear effects such as hydrogen bond association in high-concentration alcohols are effectively corrected.

Description

Technical Field

[0001] The invention belongs to the technical field of chemical analysis and detection, and in particular relates to a system for predicting the content of methanol and ethanol in automotive gasoline. Background Art

[0002] In the field of fuel testing, existing technologies generally use linear models (such as PLS) to model the spectral data of alcohol-gasoline mixtures. However, there are nonlinear interactions such as hydrogen bonding between high-concentration alcohols (such as methanol and ethanol) and gasoline components (such as aromatics and olefins), which leads to complex changes in spectral characteristics. Traditional linear models cannot effectively characterize such nonlinear effects, and the prediction deviation increases significantly with increasing concentration, making it difficult to meet the needs of industrial scenarios for high-precision detection. In addition, experimental data is subject to equipment costs and environmental conditions, and it is difficult to cover dynamic behaviors under extreme working conditions (such as ultra-high temperature and ultra-high concentration), which limits the generalization ability of the model. Summary of the Invention

[0003] The purpose of the present invention is to provide a system for predicting the content of methanol and ethanol in automotive gasoline, so as to solve the technical problem in the prior art of inaccurate detection caused by the difficulty in distinguishing the spectra corresponding to different components in gasoline.

[0004] The present invention proposes a system for predicting the content of methanol and ethanol in gasoline for motor vehicles, comprising:

[0005] a first gasoline characteristic identification module, a first spectrum correction and compensation module, a first key wavelength identification module, and a first gasoline content determination module;

[0006] The first gasoline characteristic identification module is used to identify the content of aromatics, olefins, additives, and alcohols in the first gasoline;

[0007] The first spectrum correction and compensation module is used to obtain a first spectrum peak offset;

[0008] The first key wavelength identification module is used to generate multiple groups of first characteristic peak combinations for the first gasoline, thereby determining multiple first key wavelengths based on the multiple groups of first characteristic peak combinations;

[0009] The first gasoline content determination module is configured to obtain a target component content in the first gasoline based on the first spectrum peak shift and a plurality of the first key wavelengths.

[0010] Preferably, the working steps of the first gasoline characteristic identification module are:

[0011] S11: performing a first chemical treatment operation on the first gasoline to obtain a first gasoline treatment liquid;

[0012] S12: Acquire first near-infrared spectrum information of the first gasoline treatment fluid, and input the first near-infrared spectrum information into a first gasoline component analysis model to obtain first gasoline component information.

[0013] Preferably, the first chemical treatment operation comprises:

[0014] Selective derivatization, selective addition and oxidation reactions.

[0015] Preferably, the working steps of the first spectrum correction and compensation module are:

[0016] S21: constructing a first association equilibrium model, and calculating a first association ratio based on the first gasoline component information;

[0017] S22: Inputting the first aggregate ratio into a first spectrum peak position shift determination model to obtain a first spectrum peak position shift.

[0018] Preferably, the calculation method of the first aggregate ratio includes:

[0019]

[0020] Wherein, CR-OH and CA represent the concentrations of alcohols and other components in gasoline, respectively, and Ka is the first equilibrium constant;

[0021]

[0022] Wherein, the brackets [] represent concentration.

[0023] Preferably, the S22 further includes the following steps:

[0024] S221: obtaining multiple sets of first experimental data under conditions of different gasoline concentrations and temperatures;

[0025] S222: Obtaining a plurality of second complex ratios for each of the plurality of sets of the first experimental data;

[0026] S223: Based on the plurality of ratios of the second aggregate, obtaining a plurality of first correspondences between the ratios of the second aggregate and the second spectral peak position shifts;

[0027] S224: fitting and obtaining a first spectrum peak position shift determination model based on multiple sets of the first corresponding relationships;

[0028] S225: Determine the first spectral peak shift based on the first aggregate ratio and the first spectral peak shift determination model.

[0029] Preferably, the working steps of the first key wavelength identification module are:

[0030] S31: performing a second chemical treatment operation on the first gasoline to obtain a second gasoline treatment liquid;

[0031] S32: performing near infrared spectroscopy analysis on the second gasoline treatment fluid to obtain a plurality of first characteristic peak combinations;

[0032] S33: Determine a plurality of first key wavelengths based on a plurality of groups of the first characteristic peak combinations.

[0033] Preferably, the first characteristic peak combination refers to a characteristic peak combination formed by the near-infrared spectral characteristics of methanol-formaldehyde or ethanol-acetaldehyde.

[0034] Preferably, the working steps of the first gasoline content determination module include:

[0035] S41: Correcting the plurality of first key wavelengths based on the first spectrum peak position shift to obtain a plurality of target key wavelengths;

[0036] S42: determining a plurality of first absorbance values ​​corresponding to a plurality of target key wavelengths in the second near-infrared spectrum information of the second gasoline treatment fluid;

[0037] S43: Determine the target component content of the first gasoline according to the plurality of first absorbance values.

[0038] Preferably, the oxidant used in the second chemical treatment operation is:

[0039] Potassium permanganate or potassium dichromate.

[0040] The methanol and ethanol content prediction system in automotive gasoline proposed in this application relates to the field of chemical analysis and detection technology. First, a first chemical treatment is performed on the first gasoline to improve the significance of components such as aromatics and olefins, and the proportion of the association body is determined based on the components other than alcohols in the first gasoline, and then the first spectral peak offset is determined; secondly, a second chemical treatment is performed on the first gasoline to obtain the characteristic peak combination of each alcohol component to significantly improve its significance, and multiple first key wavelengths are determined based on each characteristic peak combination; finally, based on multiple target key wavelengths, the corresponding multiple first absorbance values ​​are determined to ultimately determine the content of each target component in the first gasoline. This application combines chemometrics, near-infrared spectroscopy and artificial intelligence means, greatly improving the accuracy of gasoline component identification, and effectively correcting nonlinear effects such as hydrogen bond association in high-concentration alcohols. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained from the provided drawings without creative labor.

[0042] Figure 1 is a schematic diagram of the methanol and ethanol content prediction system in the gasoline for vehicle in the present application.

[0043] Figure 2 is an example of a feature peak combination in the methanol and ethanol content prediction system in the gasoline for vehicle in the present application. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0045] The present application will be described in detail below with reference to the drawings and specific embodiments, in which the schematic embodiments and the description are only used to explain the present application, but not to limit the present application.

[0046] The methanol and ethanol content prediction system in the gasoline for vehicle in the present application will be described in detail below, and the system block diagram is specifically shown in Figure 1 .

[0047] The content prediction system mainly comprises a first gasoline characteristic identification module, a first spectrum correction compensation module, a first key wavelength identification module and a first gasoline content determination module.

[0048] The first gasoline characteristic identification module is mainly used for identifying the content of components such as aromatic hydrocarbons, olefins and additives, and the content of alcohol (R-OH), so as to determine the characteristics of the first gasoline. It should be noted that although there is a certain deviation in identifying the content of methanol and ethanol in gasoline by near-infrared spectrum analysis, the identification of alcohol and aromatic hydrocarbons and other components in gasoline can generally meet the requirement of higher accuracy, so the content of alcohol and other components can be analyzed first, so as to obtain the compensation value of the near-infrared spectrum, so as to more accurately determine the content of gasoline.

[0049] The main working steps of the first gasoline characteristic identification module specifically comprise:

[0050] S11: performing a first chemical treatment operation on the first gasoline to obtain a first gasoline treatment liquid.

[0051] In this step, new functional groups are introduced or the molecular structure is changed through chemical reactions, so that aromatic hydrocarbons, olefins and additives produce more significant absorption peaks in the near-infrared spectrum and reduce spectral overlap interference.

[0052] The first chemical treatment operation specifically includes the following three parts:

[0053] 1) Chemical treatment of aromatics:

[0054] Selective derivatization: Use an acetalizing agent (such as ethylene glycol dimethyl ether) to react with aromatic hydrocarbons to generate derivatives with a unique COC absorption peak (about 8200 cm-1), which is significantly different from the C=C peak of olefins (about 7100 cm-1).

[0055] Example reaction:

[0056] Benzene + ethylene glycol dimethyl ether → acid-catalyzed phenylacetal + H2O Benzene + ethylene glycol dimethyl ether acid-catalyzed

[0057] Benzene acetal + H2O

[0058] 2) Chemical treatment of olefins:

[0059] Selective addition reaction: Bromine water (Br2) is used to react with olefins to produce brominated alkanes, whose C-Br absorption peak (about 5600 cm-1) is significantly different from the C=C peak of aromatic hydrocarbons (7100 cm-1).

[0060] Reaction conditions: Carry out at low temperature (0-5°C) to avoid side reactions.

[0061] 3) Chemical treatment of additives

[0062] Oxidation additives: Oxidation of oxygen-containing additives (such as methyl tert-butyl ether MTBE) to generate ketone compounds (C=O peak at about 5750 cm-1), which are separated from the absorption peaks of aromatics / olefins.

[0063] Reagent selection: Potassium permanganate (KMnO4) oxidizes MTBE to methyl ethyl ketone (MEK) under acidic conditions.

[0064] By performing the first chemical treatment operation including the above three steps, significant processing can be completed for aromatics, olefins and additives, so that the content of aromatics, olefins and additives in the first gasoline can be more clearly and conveniently identified through near-infrared spectral data.

[0065] S12: Acquire first near-infrared spectrum information of the first gasoline treatment fluid, and input the first near-infrared spectrum information into a first gasoline component analysis model to obtain first gasoline component information.

[0066] The core of infrared spectroscopy is to capture the "absorption fingerprint" of molecules in response to near-infrared light. When near-infrared light strikes oil, chemical bonds such as CH, OH, and NH within the oil vibrate like musical strings, absorbing light of specific wavelengths. Molecular vibration patterns vary between components, resulting in unique absorption spectra, like fingerprints. By analyzing these "optical fingerprints," the composition and properties of the oil can be inferred.

[0067] In this step, the first near-infrared spectrum information is analyzed based on the first gasoline component analysis model trained in advance, so as to obtain the first gasoline component information.

[0068] The first gasoline component analysis model is specifically trained and obtained by the following method:

[0069] First, sample data is obtained. Gasoline samples from a historical gasoline sample library are selected as training data. For each historical gasoline sample, its near-infrared spectral information is used as input data, and the gasoline sample label is used as output data to train a convolutional neural network model, thereby obtaining the first gasoline component analysis model. The near-infrared spectral analysis information refers to the near-infrared spectrum generated by near-infrared light irradiating the first gasoline.

[0070] After the first near-infrared spectral information is input into the first gasoline component analysis model, the first near-infrared spectral information can be analyzed to find the gasoline sample label with the highest similarity to the first near-infrared spectral information as the first gasoline sample label, and the first gasoline sample label can be output.

[0071] For example, the first gasoline sample label may be model 1, model 2, etc., or the place of origin may be used as the first gasoline sample label.

[0072] Furthermore, based on the obtained first gasoline sample label, the corresponding content of components such as aromatics, olefins, and additives, as well as the content of alcohols (R-OH), can be obtained through a mapping relationship. This mapping relationship is established based on historical analysis results, and the content of each component can be adaptively adjusted based on the similarity.

[0073] The first spectral correction and compensation module is mainly used to obtain the hydrogen bonding characteristics of the first gasoline based on the content of components such as aromatics, olefins and additives and the content of alcohols (R-OH) determined in the first gasoline characteristic identification module, and to obtain the spectral peak position offset after analyzing the hydrogen bonding characteristics, thereby solving the technical problem of high-concentration nonlinearity.

[0074] Hydrogen bonding has a direct impact on spectral characteristics, mainly in the following two aspects:

[0075] 1. Absorption peak shift and deformation:

[0076] 1. Red shift phenomenon: The free OH stretching vibration peak (such as methanol ~1410nm, ethanol ~1440nm) will shift to the long-wave direction (methanol → 1380-1400nm, ethanol → 1420-1430nm) after forming hydrogen bonds.

[0077] 2. Peak broadening: Dynamic association leads to enhanced asymmetry of the absorption peak and an increase in half-peak width by 20-30%.

[0078] Example: The free OH peak in pure methanol is at 1410 nm, and after adding gasoline it may shift to 1395 nm due to association with aromatic hydrocarbons.

[0079] 2. Nonlinear absorbance response

[0080] At low concentrations (<1%), alcohols are mainly monomeric and the absorbance is linearly related to concentration;

[0081] At high concentrations (>5%), the proportion of the association body increases and the absorbance growth slows down, resulting in a bending of the standard curve (departure from the Lambert-Beer law).

[0082] Based on the above-mentioned adverse effects, in this step, the hydrogen bonding characteristics of the first gasoline are analyzed to obtain the spectral peak shift and correct the near-infrared spectral information of the first gasoline to improve the detection accuracy of the component content in the first gasoline.

[0083] The main working steps of the first spectrum correction and compensation module specifically include:

[0084] S21: constructing a first association equilibrium model, and calculating a first association ratio based on the first gasoline component information.

[0085] Assuming that alcohols (R-OH) form hydrogen bond associations (R-OH…A) with gasoline components (such as aromatics A), the equilibrium reaction is:

[0086]

[0087] Wherein, \cdotp indicates the association of alcohols with gasoline components.

[0088] Calculate the first equilibrium constant K a , the specific calculation formula is as follows:

[0089]

[0090] Wherein, the brackets [] represent the concentration, that is, [R-OH] represents the concentration of the alcohol component in the first gasoline.

[0091] Input temperature T and concentration C R-OH 、C A , calculate the first aggregate ratio f by Ka assoc , the specific calculation formula is as follows:

[0092]

[0093] S22: Inputting the first aggregate ratio into a first spectrum peak position shift determination model to obtain a first spectrum peak position shift.

[0094] In the first spectral peak shift determination model, the relationship between the ratio of the aggregates and the spectral peak shift is obtained based on experimental data fitting, so that the first spectral peak shift can be obtained by the first aggregate ratio determined in S22.

[0095] The S22 includes the following sub-steps:

[0096] S221: Obtain multiple sets of first experimental data under conditions of different gasoline concentrations and temperatures.

[0097] Specifically include:

[0098] Alcohol-gasoline mixtures (such as methanol / ethanol-gasoline) of different concentrations (0-50%) were prepared.

[0099] The near-infrared (NIR) spectra of the samples were measured at different temperatures (20-40°C).

[0100] Each set of the first experimental data includes a near-infrared spectrum at a specified temperature and alcohol concentration.

[0101] S222: Obtain a plurality of second aggregate ratios for each of the plurality of sets of the first experimental data.

[0102] In this step, the second aggregate ratio is obtained by nuclear magnetic resonance (NMR) detection.

[0103] S223: Based on the plurality of second aggregate ratios, obtaining a plurality of first correspondences between the second aggregate ratios and the second spectrum peak position shifts.

[0104] In this step, under the same alcohol concentration conditions, the characteristic absorption peak positions (such as C=O peak and OH peak) of pure alcohol (no association) and alcohol in the associated state are compared.

[0105] Calculate the second peak position shift Δλ = λ assoc -λ free , where λ assoc and λ free are the peak positions of the associated state and the free state, respectively.

[0106] S224: Based on the multiple groups of the first corresponding relationships, obtain the first spectrum peak position shift determination model by fitting.

[0107] Since multiple sets of the first correspondences record the correspondence between the ratio of the aggregate and the spectral peak shift under different concentration and temperature conditions, the least squares method can be used to fit the changing relationship between the ratio of the aggregate and the spectral peak shift.

[0108] S225: Determine the first spectral peak shift based on the first aggregate ratio and the first spectral peak shift determination model.

[0109] Preferably, the first spectral peak position shift determination model may be in the form of a curve or a mathematical model, and the corresponding first spectral peak position shift may be obtained by inputting the first aggregate ratio into the first spectral peak position shift determination model.

[0110] The first key wavelength identification module is used to oxidize the first gasoline, thereby oxidizing the methanol and ethanol in the first gasoline into formaldehyde and acetaldehyde, resulting in significantly different near-infrared spectral wavelengths for the methanol and ethanol in the first gasoline. Since unreacted methanol and ethanol remain in the first gasoline after the peroxidation reaction, each of the methanol and ethanol contains both unreacted methanol and reacted formaldehyde, forming a characteristic peak combination. Because the difference between the characteristic peaks of formaldehyde and acetaldehyde is significantly greater than that of methanol and ethanol, the characteristic peak combination of formaldehyde and methanol is even more significantly different from the characteristic peak combination of acetaldehyde and ethanol, thereby facilitating accurate detection of the methanol and ethanol content in the first gasoline and subsequently identifying a number of key wavelengths.

[0111] The main working steps of the first key wavelength identification module specifically include:

[0112] S31: performing a second chemical treatment operation on the first gasoline to obtain a second gasoline treatment liquid.

[0113] The principle of chemical treatment in this step includes: utilizing the chemical structural differences between methanol and ethanol (methanol is CH3OH, ethanol is C2H5OH), designing a selective reaction system, causing methanol or ethanol to undergo specific chemical reactions to generate products with significant spectral differences, thereby expanding the difference in the characteristic absorption peaks of the two in the near-infrared spectrum.

[0114] The specific chemical treatment steps in this step include:

[0115] Reagent selection: Selective oxidants (such as potassium permanganate KMnO4 or potassium dichromate K2Cr2O7) oxidize methanol to formaldehyde (CH2O) under acidic conditions, while ethanol is oxidized to acetaldehyde (CH3CHO).

[0116] Reaction formula:

[0117] Methanol oxidation: CH3OH+[O]→CH2O+H2O

[0118] Ethanol oxidation: C2H5OH+[O]→CH3CHO+H2O

[0119] Reaction conditions:

[0120] Temperature: 50-70℃ (avoid overheating to avoid side reactions).

[0121] pH value: acidic environment (pH = 1-3, adjusted with sulfuric acid).

[0122] Reaction time: 15-30 minutes (the optimal reaction time is determined experimentally to ensure that methanol is completely oxidized while ethanol is only partially oxidized).

[0123] Termination of the reaction: Add a reducing agent (such as sodium bisulfite NaHSO3) to neutralize the residual oxidant and prevent further oxidation.

[0124] The spectral characteristics of the treated product are as follows:

[0125] Methanol oxidation product (formaldehyde): In the near-infrared spectrum, the C=O stretching vibration absorption peak of formaldehyde is located at about 5800 cm-1 (separated from the original -OH peak of methanol).

[0126] Ethanol oxidation product (acetaldehyde): The C=O absorption peak of acetaldehyde is located at about 5750 cm-1, which is significantly different from the original COC absorption peak of ethanol (about 8200 cm-1).

[0127] Unreacted ethanol: retains the original -OH (about 5200 cm-1) and COC (about 8200 cm-1) absorption peaks.

[0128] S32: Performing near infrared spectroscopy analysis on the second gasoline treatment fluid to obtain a plurality of first characteristic peak combinations.

[0129] The first characteristic peak combination refers to a characteristic peak combination formed by the near-infrared spectral characteristics of methanol-formaldehyde or ethanol-acetaldehyde, and each of the first characteristic peak combinations includes multiple characteristic peaks.

[0130] An example of new characteristic peaks introduced by chemical treatments include:

[0131] Methanol: After oxidation, formaldehyde is generated, and its C=O peak (5800 cm-1) combines with the -OH peak (5200 cm-1) of the original methanol to form a characteristic spectral combination of methanol.

[0132] Ethanol: After oxidation, acetaldehyde is generated, and its C=O peak (5750 cm-1) combines with the COC peak (8200 cm-1) of the original ethanol to form a characteristic spectral combination of ethanol.

[0133] The distinction between different components in gasoline can be achieved by combining characteristic peaks. The reasons are as follows. Figure 2 As shown:

[0134] The characteristic peak combination of methanol: 5200 cm-1 (-OH) + 5800 cm-1 (C=O).

[0135] The characteristic peak combination of ethanol: 5750 cm-1 (C=O) + 8200 cm-1 (COC).

[0136] By comparing the intensity and position of these two combinations, methanol and ethanol can be distinguished.

[0137] S33: Determine a plurality of first key wavelengths based on a plurality of groups of the first characteristic peak combinations.

[0138] There is a certain corresponding conversion relationship between characteristic peaks and wavelengths. In this step, one or more first key wavelengths corresponding to each first characteristic peak combination can be obtained through reverse calculation. Thus, multiple first characteristic peak combinations can be used to obtain multiple first key wavelengths.

[0139] The first gasoline content determination module uses the spectral peak offset output by the first spectral correction and compensation module to correct the key wavelength output by the first key wavelength identification module, thereby obtaining a corrected target key wavelength. Ultimately, the content of each component in the first gasoline can be determined based on the target key wavelength.

[0140] The main working steps of the first gasoline content determination module specifically include:

[0141] S41: Correcting the plurality of first key wavelengths based on the first spectrum peak position shift to obtain a plurality of target key wavelengths.

[0142] In this step, the correction process can be completed based on an artificial or machine learning model to correct the near-infrared spectrum peak shift caused by the nonlinear concentration in gasoline.

[0143] S42: Determine a plurality of first absorbance values ​​corresponding to a plurality of target key wavelengths in the second near-infrared spectrum information of the second gasoline treatment fluid.

[0144] In the second gasoline treatment fluid, different components correspond to different target key wavelengths. Therefore, by determining multiple first absorbance values ​​corresponding to different target key wavelengths in the second near-infrared spectrum information, the content of the corresponding target component in the first gasoline can be subsequently determined.

[0145] The absorbance value can be calculated using a common method in the art, which will not be described in detail here.

[0146] S43: Determine the target component content of the first gasoline according to the plurality of first absorbance values.

[0147] In this step, the content of each target component in the first gasoline can be determined by the changing relationship between different first absorbance values ​​and the content of different target components in gasoline.

[0148] The methanol and ethanol content prediction system in automotive gasoline proposed in this application relates to the field of chemical analysis and detection technology. First, a first chemical treatment is performed on the first gasoline to improve the significance of components such as aromatics and olefins, and the proportion of the association body is determined based on the components other than alcohols in the first gasoline, and then the first spectral peak offset is determined; secondly, a second chemical treatment is performed on the first gasoline to obtain the characteristic peak combination of each alcohol component respectively to significantly improve its significance, and multiple first key wavelengths are determined based on each characteristic peak combination; finally, multiple first key wavelengths are corrected based on the first spectral peak offset to obtain multiple target key wavelengths, and the corresponding multiple first absorbance values ​​are determined to finally determine the content of each target component in the first gasoline. This application combines chemometrics, near-infrared spectroscopy and artificial intelligence means, greatly improving the accuracy of gasoline component identification and effectively correcting nonlinear effects such as hydrogen bond association in high-concentration alcohols.

[0149] The above description is only a preferred embodiment of the present invention. Therefore, any equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A system for predicting the content of methanol and ethanol in gasoline, characterized in that: include: a first gasoline characteristic identification module, a first spectrum correction and compensation module, a first key wavelength identification module, and a first gasoline content determination module; The first gasoline characteristic identification module is used to identify the content of aromatics, olefins, additives, and alcohols in the first gasoline; The first spectrum correction and compensation module is used to obtain a first spectrum peak offset; The first key wavelength identification module is used to generate multiple groups of first characteristic peak combinations for the first gasoline, thereby determining multiple first key wavelengths based on the multiple groups of first characteristic peak combinations; The first gasoline content determination module is configured to obtain a target component content in the first gasoline based on the first spectral peak shift and a plurality of the first key wavelengths.

2. The system for predicting methanol and ethanol content in motor gasoline according to claim 1, characterized in that: The working steps of the first gasoline characteristic identification module are as follows: S11: performing a first chemical treatment operation on the first gasoline to obtain a first gasoline treatment liquid; S12: Acquire first near-infrared spectrum information of the first gasoline treatment fluid, and input the first near-infrared spectrum information into a first gasoline component analysis model to obtain first gasoline component information.

3. The system for predicting methanol and ethanol content in motor gasoline according to claim 2, characterized in that: The first chemical treatment operation comprises: Selective derivatization, selective addition and oxidation reactions.

4. The system for predicting methanol and ethanol content in motor gasoline according to claim 3, characterized in that: The working steps of the first spectrum correction and compensation module are: S21: constructing a first association equilibrium model, and calculating a first association ratio based on the first gasoline component information; S22: Inputting the first aggregate ratio into a first spectrum peak position shift determination model to obtain a first spectrum peak position shift.

5. The system for predicting methanol and ethanol content in motor gasoline according to claim 4, characterized in that: The calculation method of the first aggregate ratio includes: Among them, the C R-OH 、C A Respectively represent the concentrations of alcohols and other components in gasoline, the K a is the first equilibrium constant; Wherein, the brackets [] represent concentration.

6. The system for predicting methanol and ethanol content in motor gasoline according to claim 5, characterized in that: The S22 further includes the following steps: S221: obtaining multiple sets of first experimental data under conditions of different gasoline concentrations and temperatures; S222: Obtaining a plurality of second complex ratios for each of the plurality of sets of the first experimental data; S223: Based on the plurality of ratios of the second aggregate, obtaining a plurality of first correspondences between the ratios of the second aggregate and the second spectral peak position shifts; S224: fitting and obtaining a first spectrum peak position shift determination model based on multiple sets of the first corresponding relationships; S225: Determine the first spectral peak shift based on the first aggregate ratio and the first spectral peak shift determination model.

7. The system for predicting methanol and ethanol content in motor gasoline according to claim 6, characterized in that: The working steps of the first key wavelength identification module are: S31: performing a second chemical treatment operation on the first gasoline to obtain a second gasoline treatment liquid; S32: performing near infrared spectroscopy analysis on the second gasoline treatment fluid to obtain a plurality of first characteristic peak combinations; S33: Determine a plurality of first key wavelengths based on a plurality of groups of the first characteristic peak combinations.

8. The system for predicting methanol and ethanol content in motor gasoline according to claim 7, characterized in that: The first characteristic peak combination refers to a characteristic peak combination formed by the near-infrared spectrum characteristics of methanol-formaldehyde or ethanol-acetaldehyde.

9. The system for predicting methanol and ethanol content in motor gasoline according to claim 8, characterized in that: The working steps of the first gasoline content determination module include: S41: Correcting the plurality of first key wavelengths based on the first spectrum peak position shift to obtain a plurality of target key wavelengths; S42: determining a plurality of first absorbance values ​​corresponding to a plurality of target key wavelengths in the second near-infrared spectrum information of the second gasoline treatment fluid; S43: Determine the target component content of the first gasoline according to the plurality of first absorbance values.

10. The system for predicting methanol and ethanol content in motor gasoline according to claim 9, characterized in that: The oxidant used in the second chemical treatment operation is: Potassium permanganate or potassium dichromate.

Images