Detection Method of Aniline Additives in Vehicle Gasoline Based on Near-Infrared Spectroscopy

Abstract

The detection method of aniline additives in vehicle gasoline based on near-infrared spectroscopy proposed in this application relates to the technical field of chemical analysis and detection. First, through big data analysis, a concentration prediction interval is obtained based on aspects such as gasoline source, refining process, and quality standards. Secondly, through derivatization and extraction processes, the aniline additives in gasoline are made more easily detectable. Next, key wavelength information is extracted from the near-infrared spectroscopy analysis results to further highlight the significance of aniline additives in gasoline, and a first aniline predicted concentration is obtained based on big data and a machine learning model. Finally, the first aniline predicted concentration is adjusted based on the first prediction concentration interval to obtain a second aniline predicted concentration. The technical solution of the present invention combines chemical treatment and artificial intelligence technical means to achieve accurate detection of aniline additives in gasoline, and only requires a near-infrared detection device to implement, greatly improving the economy of the detection method.

Description

Technical Field

[0001] The present invention belongs to the technical field of chemical analysis and detection, and particularly relates to a method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy. Background Art

[0002] Due to its fast and non-destructive characteristics, near-infrared spectroscopy technology is widely used in the detection of vehicle gasoline additives. However, characteristic peak overlap easily occurs between aniline compounds and components such as hydrocarbons and alcohols in the gasoline matrix in the near-infrared spectrum, and the accuracy of detecting low-concentration aniline compounds is not high, resulting in insufficient detection stability and low detection accuracy. In the prior art, it is usually necessary to combine near-infrared and mid-infrared spectroscopy for simultaneous detection, but such a detection method requires purchasing multiple sets of equipment, and the economy is poor. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy, so as to solve the technical problems of low detection stability and accuracy of aniline compounds in gasoline existing in the prior art.

[0004] The present invention proposes a method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy, and the method includes:

[0005] S1: Determine a first predicted concentration range according to the first basic information of the first gasoline sample data; wherein, the first basic information is used to characterize the origin, production process, and quality management standard information of the first gasoline sample data;

[0006] S2: Perform a first chemical treatment on the first gasoline sample data to obtain second gasoline sample data;

[0007] S3: Obtain first key wavelength information based on the first near-infrared spectrum information of the second gasoline sample data;

[0008] S4: Input the first key wavelength information into a first aniline concentration prediction model to obtain a first aniline predicted concentration;

[0009] S5: Adjust the first aniline predicted concentration based on the first predicted concentration range to obtain a second aniline predicted concentration.

[0010] Preferably, the S1 further includes:

[0011] S11: Determine first origin information from the first basic information, and determine a first origin label based on the first origin information;

[0012] S12: Determine a first production and processing profile from the first basic information;

[0013] S13: Determine the first quality management standard according to the first place of origin information, and perform semantic analysis on the first quality management standard to obtain the first quality management level;

[0014] S14: Input the first place of origin label, the first production and processing portrait, and the first quality management level into the first predicted concentration range determination model to determine the first predicted concentration range.

[0015] Preferably, the S12 further includes:

[0016] S121: Determine the first production and processing vector based on the first basic information;

[0017] S122: Input the first production and processing vector into the production and processing label determination model to determine the first production and processing portrait.

[0018] Preferably, the S2 further includes the following steps:

[0019] S21: Perform the first chemical pretreatment step on the first gasoline sample data to obtain the third gasoline sample data;

[0020] S22: Perform the first extraction and separation step on the third gasoline sample data to obtain the second gasoline sample data.

[0021] Preferably, the first chemical pretreatment step is a derivatization reaction.

[0022] Preferably, the S3 further includes the following steps:

[0023] S31: Obtain the first near-infrared spectrum information corresponding to the second gasoline sample data;

[0024] S32: Perform the first pretreatment operation on the first near-infrared spectrum information to obtain the second near-infrared spectrum information;

[0025] S33: Perform the first successive projection processing operation on the second near-infrared spectrum information to obtain the first key wavelength information.

[0026] Preferably, the first pretreatment operation includes a standard normal variate transformation step and a second derivative composite processing step.

[0027] Preferably, the S33 further includes the following steps:

[0028] S331: Randomly select the first initial wavelength point from the second near-infrared spectrum information, and obtain the first initial wavelength corresponding to the first initial wavelength point;

[0029] S332: Calculate the first projection vector of each first candidate wavelength and the first initial wavelength, determine the first candidate wavelength with the largest first projection vector as the first target wavelength, and add it to the first wavelength set;

[0030] S333: If the number of the first target wavelengths in the first wavelength set is equal to the first value, output the first wavelength set as the first key wavelength information; otherwise, continue to execute S332.

[0031] Preferably, the S5 further includes the following steps:

[0032] S51: If the first aniline predicted concentration coincides with the first predicted concentration range, use the first aniline predicted concentration as the second aniline predicted concentration and enter S54; otherwise, calculate the first deviation value and enter S52;

[0033] S52: If the first deviation value is less than or equal to the first preset value, enter S53; otherwise, output a detection error message;

[0034] S53: Normalize the first aniline predicted concentration within the first predicted concentration range according to the first deviation value, obtain the second aniline predicted concentration, and enter S54;

[0035] S54: Output the second aniline predicted concentration.

[0036] Preferably, the first value is 15.

[0037] The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy proposed in this application relates to the technical field of chemical analysis and detection. First, through big data analysis, obtain the concentration prediction range based on aspects such as gasoline source, refining process, and quality standards. Secondly, through derivatization and extraction processes, make the aniline additives in gasoline more easily detectable. Next, extract the key wavelength information from the near-infrared spectroscopy analysis results to further highlight the significance of aniline additives in gasoline, and obtain the first aniline predicted concentration based on big data and machine learning models. Finally, adjust the first aniline predicted concentration based on the first predicted concentration range to obtain the second aniline predicted concentration. The technical solution of the present invention combines chemical treatment and artificial intelligence technical means to achieve accurate detection of aniline additives in gasoline, and only requires a near-infrared detection device to implement, greatly improving the economy of the detection method. Description of the Drawings

[0038] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, without creative efforts, other implementation drawings can be obtained according to the provided drawings.

[0039] Figure 1 It is the execution flowchart of the detection method for aniline additives in vehicle gasoline based on near-infrared spectroscopy in the present invention.

[0040] Figure 2 It is the flowchart for determining the first key wavelength information in the detection method for aniline additives in vehicle gasoline based on near-infrared spectroscopy in the present invention.

[0041] Figure 3 It is the schematic diagram for determining the predicted concentration of the second aniline in vehicle gasoline based on near-infrared spectroscopy in the present invention. Specific Embodiments

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0043] The following will detail the present invention in combination with the drawings and specific embodiments, where the illustrative embodiments and explanations are only used to explain the present invention, but not to limit the present invention.

[0044] The following will detail the detection method for aniline additives in vehicle gasoline based on near-infrared spectroscopy of the present invention, specifically as Figure 1 shown.

[0045] S1: Determine the first predicted concentration range according to the first basic information of the first gasoline sample data.

[0046] Aniline substances are usually not intentionally added to gasoline, and their content is mainly affected by the source and origin of gasoline, the production process and raw materials. In addition, it may also be affected by quality management standards. For example, the composition of crude oil varies from place to place. Some crude oils may contain trace amounts of aromatic amine precursors, which may be partially converted into aniline compounds during the refining process. For example, the nitrogen content of crude oil from certain specific oil regions may be relatively high, and it may contain some nitrogen-containing heterocyclic compounds, which may undergo complex chemical reactions during the refining process to produce trace amounts of aniline substances. For example, if the quality management standard is high, the removal of aniline additives during the production and processing process is usually more thorough.

[0047] Therefore, in this step, first, based on the first basic information of the first gasoline sample data, the maximum possible concentration range of its aniline additives is determined.

[0048] Among them, the first basic information is used to characterize information such as the source, origin, production process, and quality management standard of the first gasoline sample data.

[0049] The S1 specifically may include the following sub-steps:

[0050] S11: Determine the first origin information from the first basic information, and determine the first origin label based on the first origin information.

[0051] To ensure gasoline safety, information on the extraction and production and processing processes of gasoline is usually recorded and traceability information is provided. The first basic information can be obtained by sorting out based on the traceability information.

[0052] Since gasoline extracted from different regions has certain characteristics in its composition, in this step, preferably, different regions can be classified and labeled in advance according to the characteristics of gasoline composition in different regions worldwide. Furthermore, the first origin label can be determined through the first origin information.

[0053] Among them, the first origin label may include information on the component characteristics of gasoline. For example, whether it contains aromatic amine precursors or nitrogen-containing heterocyclic compounds, and information such as the concentration range of the above substances.

[0054] S12: Determine the first production and processing profile from the first basic information.

[0055] During the production and processing process of gasoline, the impact of aspects such as refining process, refining section, and blending process on the concentration of aniline substances in gasoline is mainly considered.

[0056] First, different refineries adopt different process routes and equipment. Some advanced refining processes can more effectively remove impurities, including possible aniline substances. For example, refineries using deep hydrocracking and refining processes can better control the impurity content in gasoline and reduce the residue of aniline substances. However, some small refineries or refineries with relatively backward processes may have slightly worse effects in removing impurities, resulting in relatively high aniline substance content in gasoline.

[0057] Secondly, the refining process is crucial for removing impurities. If the refining process is not perfect, it may lead to the residue of aniline substances. For example, if the refining steps such as desulfurization and denitrification are not thorough enough, a small amount of aniline substances may enter the final product.

[0058] Finally, during the blending process of oil, if components containing aniline substances are used, or the mixing ratio of components is inappropriate, it may also lead to an increase in the aniline substance content.

[0059] Therefore, S12 may include the following sub-steps:

[0060] S121: Determine a first production and processing vector based on the first basic information.

[0061] In this step, it is necessary to determine the refining process information, refining equipment information, refining process information, and blend information corresponding to the first gasoline sample.

[0062] According to the above four types of information in the specified data format, they are organized into the first production and processing vector. Among them, the first production and processing vector is preferably a 1×4-dimensional vector.

[0063] S122: Input the first production and processing vector into the production and processing label determination model to determine the first production and processing portrait.

[0064] The production and processing label determination model is obtained by training a convolutional neural network model. Among them, gasoline sample data from different regions are used as training data. For each sample data, for its production and processing vector, its production and processing label is manually marked. For the labeled sample data, using the production and processing vector as the input data and the manually labeled production and processing label as the output data, the production and processing label determination model is trained.

[0065] Among them, the first production and processing portrait records the relevant information used to characterize the first gasoline sample in the production and processing stage. For example, it can be "deep hydrocracking, un-desulfurized, blend component content".

[0066] S13: Determine the first quality management standard according to the first origin information, and perform semantic analysis on the first quality management standard to obtain the first quality management level.

[0067] Generally speaking, the quality management standards for gasoline vary by origin. Therefore, based on the first origin information determined in step S11, the corresponding first quality relationship standard can be queried. Next, the first quality management standard can be analyzed through the semantic analysis model in the prior art to obtain the first quality management level corresponding to the first gasoline sample.

[0068] Preferably, the quality management level corresponding to the specified origin can also be found through a pre-established mapping table.

[0069] Preferably, the first quality relationship level can be divided into 3 levels or 4 levels.

[0070] S14: Input the first origin label, the first production and processing portrait, and the first quality management level into the first predicted concentration interval determination model to determine the first predicted concentration interval.

[0071] Among them, the first predicted concentration interval determination model is obtained by training a machine learning model. Historical gasoline-related data from different regions is selected as sample data. For each piece of sample data, its origin label, production and processing portrait, and quality management level are used as input data, and the predicted concentration interval that meets the confidence requirement is used as output data to train the first predicted concentration interval determination model.

[0072] Among them, the predicted concentration interval that meets the confidence requirement is determined as follows: First, obtain the measured concentration value of aniline additives corresponding to each piece of sample data, and expand the measured concentration value of aniline additives according to a confidence level of 80% to obtain the predicted concentration interval corresponding to this piece of sample data.

[0073] S2: Perform a first chemical treatment on the first gasoline sample data to obtain second gasoline sample data.

[0074] In near-infrared spectroscopy analysis, the concentration detection of aniline additives in gasoline is often interfered by overlapping characteristic peaks, resulting in a decrease in detection sensitivity and accuracy. To solve the above problems, before analyzing the near-infrared spectrum in this step, the characteristic absorption or fluorescence signal of aniline compounds is significantly enhanced through derivatization reaction and extraction separation technology, and at the same time, interfering components are effectively separated, so as to prepare for the subsequent near-infrared spectroscopy analysis.

[0075] Among them, the first chemical treatment includes two steps, namely the first chemical pretreatment step and the first extraction and separation step.

[0076] S2 includes the following sub-steps:

[0077] S21: Perform the first chemical pretreatment step on the first gasoline sample data to obtain the third gasoline sample data.

[0078] The first chemical pretreatment step uses a derivatization reaction. Specifically, aniline compounds are converted into derivatives with stronger characteristic absorption or fluorescence signals to enhance the detection signal.

[0079] The specific implementation steps are as follows:

[0080] Reagent selection: Select one or more derivatization reagents, such as aldehydes, ketones, acid anhydrides, or acylating reagents, to react with aniline compounds to form derivatives with specific spectral characteristics. The selection of reagents should be based on their reactivity with aniline, the stability of the derivatives, and their suitability for near-infrared spectroscopy detection.

[0081] Reaction condition optimization: By controlling the reaction temperature (e.g., 40 - 60 °C), reaction time (e.g., 10 - 30 minutes), and pH value (e.g., neutral or weakly acidic), ensure the efficient progress of the derivatization reaction while avoiding the occurrence of side reactions.

[0082] Derivative verification: Verify the formation of derivatives through high-performance liquid chromatography (HPLC) or mass spectrometry (MS) techniques, and optimize the reaction conditions to ensure the purity and stability of the derivatives.

[0083] S22: Perform the first extraction and separation step on the third gasoline sample data to obtain the second gasoline sample data.

[0084] The first extraction and separation step uses solid-phase extraction (SPE) or liquid-liquid extraction (LLE) techniques to separate aniline derivatives from other components to reduce interference and improve detection accuracy.

[0085] The specific implementation steps of solid-phase extraction (SPE) are as follows:

[0086] Extraction material selection: Use a solid-phase extraction column with specific adsorption characteristics (such as C18, C8, or polar adsorbents) to selectively adsorb aniline derivatives.

[0087] Operation process: Pass the sample through the extraction column and elute it with an appropriate eluent (such as methanol, acetonitrile, or water) to separate the target derivative from other interfering components.

[0088] Parameter optimization: Optimize the extraction efficiency by adjusting the flow rate (e.g., 1 - 5 mL / min), eluent concentration, and volume.

[0089] The specific implementation steps of liquid - liquid extraction (LLE) are as follows:

[0090] Solvent selection: Select an organic solvent immiscible with the sample matrix (such as hexane, ethyl acetate, or toluene) to achieve selective extraction of aniline derivatives.

[0091] Operation process: Mix the sample with the extraction solvent in a certain ratio (e.g., 1:1 to 1:5), promote extraction by shaking or stirring, and then separate the organic phase and the aqueous phase.

[0092] Parameter optimization: Optimize the extraction efficiency by adjusting the type, ratio, and extraction time of the extraction solvent (e.g., 5 - 15 minutes).

[0093] Through step S2, the identifiability of aniline compounds in the second gasoline sample data can be significantly enhanced, thus preparing for the subsequent spectral analysis step.

[0094] S3: Obtain the first key wavelength information based on the first near - infrared spectral information of the second gasoline sample data.

[0095] Through step S2, certain enhancement processing has been carried out on the aniline additives in the gasoline sample. In order to further improve the detection accuracy, in this step, the first key wavelength information is extracted from the first near - infrared spectral information corresponding to the second gasoline sample. By removing the irrelevant wavelength information in the first near - infrared spectral information and retaining the first key wavelength information with a higher correlation degree to the recognition accuracy.

[0096] S3 includes the following sub - steps, as Figure 2 shown:

[0097] S31: Obtain the first near - infrared spectral information corresponding to the second gasoline sample data.

[0098] The first near - infrared spectral information is obtained by a near - infrared spectral analyzer.

[0099] S32: Perform a first pre - processing operation on the first near - infrared spectral information to obtain the second near - infrared spectral information.

[0100] Among them, the first pre - processing operation includes a standard normal variate transformation (SNV) step and a second - derivative composite processing step.

[0101] The standard normal variate transformation (SNV) step specifically includes:

[0102] The original near-infrared spectral matrix Xm×n (m is the number of samples, n is the number of wavelength points) is processed by SNV to eliminate the interference of light scattering. The value at each position in the processed matrix is calculated by the following formula:

[0103] ;

[0104] In the formula, is the transformed value of the i-th sample at the j-th wavelength point, μ i is the mean value of the spectrum of the i-th sample, σ i is the standard deviation, x i,j is the original absorbance value. Among them, 0 < i ≤ m, 0 < j ≤ n.

[0105] The specific steps of the second derivative composite processing include:

[0106] The second derivative of the spectrum after SNV processing is calculated using the Savitzky-Golay filter, and the parameter settings are:

[0107] Window width: 11 wavelength points (dynamically adjusted according to the spectral resolution, ranging from 7 to 15 points);

[0108] Polynomial order: 3;

[0109] Derivative order: 2;

[0110] The baseline drift is eliminated and the characteristic peaks are sharpened by the second derivative, and the preprocessed spectral matrix X preprocessed .

[0111] S33: Perform the first successive projection processing operation on the second near-infrared spectral information to obtain the first key wavelength information.

[0112] By performing successive projection processing on the second near-infrared spectral information obtained after preprocessing, the first key wavelength information can be obtained.

[0113] To avoid overfitting and information loss, the wavelength screening target interval can be set to a specified number. Preferably, the number of wavelength points to be obtained is 15.

[0114] The S33 includes the following sub-steps:

[0115] S331: Randomly select the first initial wavelength point from the second near-infrared spectral information, and obtain the first initial wavelength corresponding to the first initial wavelength point.

[0116] The first initial wavelength point is randomly obtained from the second near-infrared spectral information.

[0117] S332: Calculate the first projection vector of each first candidate wavelength and the first initial wavelength, determine the first candidate wavelength with the largest first projection vector as the first target wavelength, and add it to the first wavelength set.

[0118] In this step, multiple first candidate wavelengths can be randomly determined from the second near-infrared spectral information, and the first projection vector of each first candidate wavelength and the first initial wavelength is calculated one by one, and the first candidate wavelength with the largest first projection vector is added to the first wavelength set. By repeating this step, the first wavelength set composed of a specified number of first target wavelengths can be obtained.

[0119] S333: If the number of the first target wavelengths in the first wavelength set is equal to the first value, output the first wavelength set as the first key wavelength information; otherwise, continue to execute S332.

[0120] The goal of this step is to output the first wavelength set that meets the first value requirement and use the first wavelength information as the first key wavelength information. Therefore, when the value requirement is not met, step S332 needs to be executed cyclically.

[0121] Preferably, the first value is taken as 15.

[0122] S4: Input the first key wavelength information into the first aniline concentration prediction model to obtain the first aniline predicted concentration.

[0123] In S2 and S3, the first key wavelength information for characterizing the content of aniline additives in the first gasoline sample has been determined through chemical treatment means and key wavelength extraction means, and different wavelength information is related to the concentration of aniline additives in gasoline.

[0124] Therefore, in this step, the first key wavelength information obtained in S3 is input into the first aniline concentration prediction model to obtain the first aniline predicted concentration.

[0125] The first aniline concentration prediction model can be trained using known machine learning models in the prior art, such as a convolutional neural network model. During training, historical gasoline data is used as sample data, that is, for each piece of sample data, its key wavelength information is used as input data, and the measured aniline concentration information is used as output data to train the first aniline concentration prediction model.

[0126] S5: Adjust the first aniline predicted concentration based on the first predicted concentration interval to obtain the second aniline predicted concentration.

[0127] In this step, based on the numerical relationship between the first predicted concentration range and the first predicted aniline concentration, determine the second predicted aniline concentration corresponding to the first gasoline sample for the final output.

[0128] S5 includes the following sub-steps:

[0129] S51: If the first predicted aniline concentration coincides with the first predicted concentration range, then take the first predicted aniline concentration as the second predicted aniline concentration and proceed to S54; otherwise, calculate the first deviation value and proceed to S52.

[0130] If the first predicted aniline concentration coincides with the first predicted concentration range, it proves that there is a certain consistency in the prediction results of S1 and S4, and the first predicted aniline concentration can be directly determined as the second predicted aniline concentration and output.

[0131] If the first predicted aniline concentration does not coincide with the first predicted concentration range, it proves that there is a certain deviation in the prediction results of S1 and S4. Therefore, the final result needs to be adjusted according to the specific situation.

[0132] Wherein the first deviation value refers to the numerical deviation value between the first predicted aniline concentration and the nearest endpoint of the first predicted concentration range. For example, if the first predicted concentration range is 20 - 40 and the first predicted aniline concentration is 42, then the first deviation value is (42 - 40) = 2.

[0133] S52: If the first deviation value is less than or equal to the first preset value, proceed to S53; otherwise, output a detection error message.

[0134] In this step, if the first deviation value is less than or equal to the preset value, the first predicted aniline concentration needs to be adjusted according to the first predicted concentration range. If the first deviation value is too large, it indicates that the detection error is too large, and a detection error message is output.

[0135] S53: Normalize the first predicted aniline concentration within the first predicted concentration range according to the first deviation value, and obtain the second predicted aniline concentration, and proceed to S54.

[0136] In this step, it is necessary to integrate the first predicted aniline concentration and the first predicted concentration range to obtain the second predicted aniline concentration.

[0137] For example, Figure 3As shown, if the first predicted concentration range is 20 - 40, the first aniline predicted concentration is 42, and the first preset value is 10, then the midpoint value of the first predicted concentration range is 30. Since the first aniline predicted concentration 42 is greater than the upper endpoint value 40 of the first predicted concentration range, the first aniline predicted concentration can be normalized to the numerical range (30, 40) from the midpoint to the upper endpoint of the first predicted concentration range according to the first deviation value (42 - 40) = 2, and then the second aniline predicted concentration can be determined to be 38.

[0138] S54: Output the second aniline predicted concentration.

[0139] The second aniline predicted concentration is the concentration value of the aniline additive corresponding to the first gasoline sample.

[0140] The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy proposed in this application relates to the technical field of chemical analysis and detection. First, through big data analysis, concentration prediction intervals are obtained based on aspects such as gasoline sources, refining processes, and quality standards. Secondly, through derivatization and extraction processes, the aniline additives in gasoline are made more easily detectable. Next, key wavelength information is extracted from the near-infrared spectroscopy analysis results to further highlight the significance of aniline additives in gasoline, and the first aniline predicted concentration is obtained based on big data and machine learning models. Finally, the first aniline predicted concentration is adjusted based on the first predicted concentration range to obtain the second aniline predicted concentration. The technical solution of the present invention combines chemical treatment and artificial intelligence technical means to achieve accurate detection of aniline additives in gasoline, and can be implemented only with a near-infrared detection device, greatly improving the economy of the detection method.

[0141] The above are only the preferred embodiments of the present invention. Therefore, all equivalent changes or modifications made according to the structures, features, and principles described in the scope of the present invention patent application are included in the scope of the present invention patent application.

Claims

1. A detection method for aniline additives in vehicle gasoline based on near-infrared spectroscopy, characterized in that, The method includes: S1: Determine a first predicted concentration range according to the first basic information of the first gasoline sample data; wherein, the first basic information is used to characterize the origin, production process, and quality management standard information of the first gasoline sample data; S1 further includes: S11: Determine first origin information from the first basic information, and determine a first origin label based on the first origin information; S12: Determine a first production and processing profile from the first basic information; S13: Determine a first quality management standard according to the first origin information, and perform semantic analysis on the first quality management standard to obtain a first quality management level; S14: Input the first origin label, the first production and processing profile, and the first quality management level into a first predicted concentration range determination model to determine the first predicted concentration range; S2: Perform a first chemical treatment on the first gasoline sample data to obtain second gasoline sample data; S3: Obtain first key wavelength information based on the first near-infrared spectrum information of the second gasoline sample data; S3 further includes the following steps: S31: Obtain the first near-infrared spectrum information corresponding to the second gasoline sample data; S32: Perform a first preprocessing operation on the first near-infrared spectrum information to obtain second near-infrared spectrum information; S33: Perform a first successive projection processing operation on the second near-infrared spectrum information to obtain the first key wavelength information; S4: Input the first key wavelength information into a first aniline concentration prediction model to obtain a first predicted aniline concentration; S5: Adjust the first predicted aniline concentration based on the first predicted concentration range to obtain a second predicted aniline concentration.

2. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 1, characterized in that S12 further includes: S121: Determine a first production and processing vector based on the first basic information; S122: Input the first production and processing vector into a production and processing label determination model to determine the first production and processing profile.

3. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 2, wherein S2 further includes the following steps: S21: Perform a first chemical pretreatment step on the first gasoline sample data to obtain third gasoline sample data; S22: Perform a first extraction and separation step on the third gasoline sample data to obtain second gasoline sample data.

4. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 3, wherein The first chemical pretreatment step is a derivatization reaction.

5. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 4, wherein The first preprocessing operation includes a standard normal variate transformation step and a second derivative composite processing step.

6. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 5, wherein S33 further includes the following steps: S331: Randomly select a first initial wavelength point from the second near-infrared spectrum information, and obtain a first initial wavelength corresponding to the first initial wavelength point; S332: Calculate a first projection vector of each first candidate wavelength and the first initial wavelength, determine the first candidate wavelength with the largest first projection vector as the first target wavelength, and add it to the first wavelength set; S333: If the number of the first target wavelengths in the first wavelength set is equal to the first value, output the first wavelength set as the first key wavelength information; otherwise, continue to execute S332.

7. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 6, characterized in that, The S5 further includes the following steps: S51: If the first aniline predicted concentration coincides with the first predicted concentration range, use the first aniline predicted concentration as the second aniline predicted concentration and proceed to S54; otherwise, calculate the first deviation value and proceed to S52; S52: If the first deviation value is less than or equal to the first preset value, proceed to S53; otherwise, output a detection error message; S53: Normalize the first aniline predicted concentration within the first predicted concentration range according to the first deviation value, obtain the second aniline predicted concentration, and proceed to S54; S54: Output the second aniline predicted concentration.

8. The method for detecting aniline additives in vehicle gasoline based on near-infrared spectroscopy according to claim 7, wherein The first value is 15.

Images