Fatty acid hydrogenation degree detection method and system based on spectral analysis

Abstract

The invention discloses a fatty acid hydrogenation degree detection method and system based on spectral analysis, and particularly relates to the field of fatty acid hydrogenation detection. Comprising the following steps: S1, acquiring a first pretreatment feature of a to-be-tested sample; S2, performing pretreatment operation on the first pretreatment feature of the to-be-tested sample; S3, acquiring a second pretreatment feature; S4, acquiring a second key feature; according to the fatty acid hydrogenation degree detection method based on spectral analysis, through pretreatment operation, the purity of fatty acid in a to-be-detected sample is extracted to the maximum extent, impurities and interfering substances are removed, and the accuracy and reliability of a detection result are improved; excessive dependence on professional skills of operators is reduced through the constructed learning model and the preset database; by comprehensively applying various spectrum technologies, the advantages of various technologies can be fully exerted, and respective limitations can be made up.

Description

Technical Field

[0001] The present invention relates to the technical field of fatty acid hydrogenation detection, and more specifically, to a method and system for detecting the degree of fatty acid hydrogenation based on spectral analysis. Background Art

[0002] With the rapid development of the food industry and people's increasing attention to food safety and health, accurate detection of the degree of hydrogenation of food ingredients, especially fatty acids, has become particularly important. Partially hydrogenated products such as trans fatty acids are widely present in modern diets. Fatty acid hydrogenation degree detection can also help food processing companies optimize production processes, improve production efficiency, and reduce production costs.

[0003] As a non-destructive and rapid detection method, spectral analysis can quickly and accurately determine the degree of hydrogenation in food by analyzing the absorption characteristics of fatty acid molecules to light of specific wavelengths, greatly improving the quality control efficiency in the food processing process.

[0004] However, there are still some shortcomings in its actual use, such as the sample matrix may be affected by interfering substances, resulting in reduced accuracy of the test results, high requirements for equipment precision, strict requirements on the professional skills of operators, insufficient sensitivity for detecting trace components in certain complex matrices, and different spectral technologies also have their own limitations in application. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for detecting the degree of hydrogenation of fatty acids based on spectral analysis, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis, comprising: S1. Obtaining a first preprocessing characteristic of the sample to be tested: Based on the analysis requirements of the sample, the sample to be tested is recorded as the sample to be tested, and a first preprocessing characteristic of the sample to be tested is obtained; S2, performing a preprocessing operation on the first preprocessing feature of the sample to be tested: performing a preprocessing operation on the first preprocessing feature of the sample to be tested, the preprocessing operation being used to obtain a first key feature corresponding to the first preprocessing feature of the sample to be tested; S3, obtaining a second preprocessing feature: obtaining a second preprocessing feature corresponding to the first key feature, the second preprocessing feature is to collect spectral data of the first key feature using a high-resolution spectrometer, and the collection method uses a multimodal spectroscopy technology; S4, obtaining a second key feature: obtaining a spectrum correction model, and obtaining a second key feature corresponding to the second preprocessing feature through the second preprocessing feature according to the spectrum correction model; S5. Obtaining a third key feature: Obtaining a third key feature corresponding to the second key feature through the second key feature according to the stoichiometric analysis; S6. Obtaining a comprehensive fatty acid hydrogenation evaluation model: Obtaining a comprehensive fatty acid hydrogenation evaluation model, and obtaining an analysis result of the third key feature through the third key feature according to the comprehensive fatty acid hydrogenation evaluation model; S7. Display comprehensive fatty acid hydrogenation assessment report: Based on the comprehensive fatty acid hydrogenation assessment model, through the third key feature, the fatty acid hydrogenation degree corresponding to the third key feature is sent to the user in a preset display method based on the result of comprehensive analysis.

[0007] Preferably, the step of obtaining the first preprocessing characteristic of the sample to be tested in S1 includes: A1: Record the basic information of each sample in the sample set, including the name of the sample, the source of the sample, the batch of the sample, and the storage conditions of the sample; A2: measuring the physical properties of each sample in the sample set, the physical properties including the color of the sample, the transparency of the sample and the texture of the sample; A3: Analyze the chemical properties of each sample in the sample set, the chemical properties including the pH value of the sample, the water content of the sample, and the fatty acid composition of the sample; A4: uniquely mark the original features of each sample to be tested in the sample set, mark each sample to be tested in the sample set with a number, and associate the marking information of each sample to be tested with the original features of each sample to be tested to form a first preprocessing feature.

[0008] Preferably, the preprocessing step of the first preprocessing feature of the sample to be tested in S2 comprises: B1: Solvent optimization: Based on the physical and chemical properties of the sample in the first pretreatment feature of the sample to be tested, a solvent is selected to maximize the purity of the fatty acids extracted from the sample to be tested; B2: Sample purification: The sample to be tested is subjected to solvent purification technology and homogenization technology to remove impurities and interfering substances in the sample to be tested, and obtain a pure fatty acid extract in the sample to be tested; B3: Sample concentration: The pure fatty acid extract in the sample to be tested is concentrated by reducing the volume of solvent through concentration technology to increase the concentration of fatty acids and obtain a concentrated fatty acid sample of the sample to be tested; B4: Obtaining the first key feature: Analyze the fatty acid sample after the sample to be tested is concentrated to obtain the first key feature related to the degree of hydrogenation of the fatty acid. The first key feature includes the double bond position, cis-trans configuration, and carbon chain length information of the fatty acid.

[0009] Preferably, obtaining the spectral correction model in S4 specifically includes: According to the second preprocessing feature, a correction operation is performed on the second preprocessing feature to obtain a second key feature corresponding to the second preprocessing feature, where the second key feature is a target correction spectral feature corresponding to the second preprocessing feature, and the target correction spectral feature includes a chemical bond vibration frequency, a range of change of molecular polarizability, and a change pattern of fluorescence emission intensity; In a preset spectral database, a spectral correction model corresponding to the key feature is obtained. The preset spectral database is used to store the corresponding relationship between the key feature and the spectral correction model.

[0010] Preferably, obtaining the second key feature corresponding to the second preprocessing feature in S4 specifically includes: Obtaining a correction feature correlation value, where the correction feature correlation value is a correlation degree between the second preprocessing feature and the target correction spectrum feature, to determine whether the correlation degree reaches a preset threshold; If the correlation degree reaches a preset threshold, the target correction spectrum feature is confirmed to be the second key feature corresponding to the second preprocessing feature.

[0011] Preferably, in S4, the spectrum correction model is obtained, and before the target correction spectrum feature corresponding to the second key feature is obtained through the second key feature according to the spectrum correction model, the spectrum correction model is constructed, which specifically includes: Obtaining a spectral correction set corresponding to a target correction spectral feature; According to the spectral correction set, characteristic parameters and characteristic patterns corresponding to the target correction spectral characteristics are obtained; A spectral correction model is constructed based on characteristic parameters and characteristic patterns.

[0012] Preferably, obtaining the spectral correction set in S4 includes feature recognition technology, signal separation algorithm, signal enhancement technology, and resolution optimization.

[0013] Preferably, the step of acquiring the third key feature of the sample to be tested in S5 includes: C1: Detection of the second key feature with the help of chemometric tools; C2: Calculate the degree of hydrogenation in the second key feature using a variety of chemometric methods; C3: Applying machine learning algorithms to perform pattern recognition and classification on the second key feature to determine the degree of hydrogenation of fatty acids; C4: Compare the physical properties of the second key feature in the sample to be tested with the chemical properties, which, after verification, constitute the third key feature.

[0014] To achieve the above object, the present invention provides the following technical solution: a fatty acid hydrogenation degree detection system based on spectral analysis, comprising a system operation database, a system center processing module and a user information segment, implementing the above-mentioned fatty acid hydrogenation degree detection method based on spectral analysis, and further comprising: The system operation database includes all data texts of the fatty acid hydrogenation degree detection system, and collects the information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control system. The user information terminal is an information output device for receiving the fatty acid hydrogenation degree detection system; A first preprocessing feature acquisition module: based on the analysis requirements of the sample, the sample to be detected is recorded as a sample to be tested, and a first preprocessing feature of the sample to be tested is acquired; First preprocessing feature preprocessing module: performs a preprocessing operation on the first preprocessing feature of the sample to be tested, and the preprocessing operation is used to obtain a first key feature corresponding to the first preprocessing feature of the sample to be tested; A second preprocessing feature acquisition module: acquiring a second preprocessing feature corresponding to the first key feature, wherein the second preprocessing feature is to collect spectral data of the first key feature using a high-resolution spectrometer, and the collection method uses a multimodal spectroscopy technology; A second key feature acquisition module: acquires a spectrum correction model, and acquires a second key feature corresponding to the second preprocessing feature through the second preprocessing feature according to the spectrum correction model; A third key feature acquisition module: acquires a third key feature corresponding to the second key feature through the second key feature according to stoichiometric analysis; Comprehensive fatty acid hydrogenation evaluation model acquisition module: obtain the comprehensive fatty acid hydrogenation evaluation model, and obtain the analysis result of the third key feature through the third key feature according to the comprehensive fatty acid hydrogenation evaluation model; Comprehensive fatty acid hydrogenation assessment report output module: Based on the comprehensive fatty acid hydrogenation assessment model, through the third key feature, the fatty acid hydrogenation degree corresponding to the third key feature is sent to the user in a preset display method based on the result of comprehensive analysis.

[0015] Preferably, the acquisition steps in the second key feature acquisition module are as follows: according to the second preprocessing feature, a correction operation is performed on the second preprocessing feature to obtain a second key feature corresponding to the second preprocessing feature, the second key feature is a target correction spectral feature corresponding to the second preprocessing feature, and the target correction spectral feature includes a chemical bond vibration frequency, a range of change in molecular polarizability, and a change pattern of fluorescence emission intensity; obtaining a correction feature association value, the correction feature association value is a degree of association between the second preprocessing feature and the target correction spectral feature, to determine whether the degree of association reaches a preset threshold; if the degree of association reaches the preset threshold, confirm that the target correction spectral feature is the second key feature corresponding to the second preprocessing feature; obtaining a spectral correction set corresponding to the target correction spectral feature, according to the spectral correction set, the spectral correction set includes feature recognition technology, signal separation algorithm, signal enhancement technology, and resolution optimization; obtaining characteristic parameters and characteristic patterns corresponding to the target correction spectral features; constructing a spectral correction model based on the characteristic parameters and characteristic patterns.

[0016] Technical effects and advantages of the present invention: The present invention maximizes the purity of fatty acids extracted from the sample to be tested, removes impurities and interfering substances, and improves the accuracy of subsequent analysis and the reliability of test results through pretreatment operations such as solvent optimization, sample purification, and sample concentration. The present invention automatically executes through the constructed learning model and the preset database, reducing the excessive reliance on the professional skills of the operator; The present invention can give full play to the advantages of various technologies and make up for their respective limitations by comprehensively utilizing multiple spectral technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a diagram of the method steps of the present invention.

[0018] Figure 2 It is a system flow chart of the present invention.

[0019] Figure 3 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0022] In the following, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", and "third" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0023] As attached Figure 1 A method for detecting the degree of fatty acid hydrogenation based on spectral analysis is shown, comprising S1, obtaining a first pretreatment characteristic of a sample to be tested, S2, performing a pretreatment operation on the first pretreatment characteristic of the sample to be tested, S3, obtaining a second pretreatment characteristic, S4, obtaining a second key characteristic, S5, obtaining a third key characteristic, S6, obtaining a comprehensive fatty acid hydrogenation evaluation model, and S7, displaying a comprehensive fatty acid hydrogenation evaluation report.

[0024] S1. Obtaining a first preprocessing characteristic of a sample to be tested: Based on the analysis requirements of the sample, the sample to be tested is recorded as the sample to be tested, and a first preprocessing characteristic of the sample to be tested is obtained.

[0025] Specifically, by performing demand analysis on multiple samples to be tested, the types of samples to be tested include but are not limited to food, oil products, other samples containing fatty acids, etc., and the present embodiment does not limit the types of samples to be tested; after performing demand analysis on multiple samples to be tested, a series of samples to be tested are constructed into a set of samples to be tested. In this embodiment, oil samples will be taken as an example for illustration. The first preprocessing feature is to obtain the original features of each sample to be tested in the set of samples to be tested before preliminary processing. The original features include basic information, physical properties, and chemical properties of the sample.

[0026] In a possible implementation, the step of acquiring the first preprocessing characteristic of the sample to be tested in step S1 includes: A1: Record the basic information of each sample in the sample set, including the name of the sample, the source of the sample, the batch of the sample, and the storage conditions of the sample; A2: measuring the physical properties of each sample in the sample set, the physical properties including the color of the sample, the transparency of the sample and the texture of the sample; A3: Analyze the chemical properties of each sample in the sample set, the chemical properties including the pH value of the sample, the water content of the sample, and the fatty acid composition of the sample; A4: uniquely mark the original features of each sample to be tested in the sample set, mark each sample to be tested in the sample set with a number, and associate the marking information of each sample to be tested with the original features of each sample to be tested to form a first preprocessing feature.

[0027] Step S1 records the basic information of the samples to be tested to ensure that the source and storage conditions of each sample are accurately recorded for easy traceability and management; measures the physical properties of the samples to be tested to evaluate the appearance quality and preliminary state of the samples, providing an intuitive reference for subsequent analysis; analyzes the chemical properties of the samples to understand the basic composition of the samples, laying the foundation for subsequent chemometric analysis; and uniquely marks each sample to be tested and associates the marking information with the original features to ensure the uniqueness and traceability of each sample throughout the testing process to avoid confusion and errors.

[0028] S2. Perform a preprocessing operation on the first preprocessing feature of the sample to be tested: Perform a preprocessing operation on the first preprocessing feature of the sample to be tested, where the preprocessing operation is used to obtain a first key feature corresponding to the first preprocessing feature of the sample to be tested.

[0029] Specifically, after obtaining the first pretreatment characteristic of the sample to be tested, the fatty acid hydrogenation degree detection system can obtain multiple key characteristics corresponding to the first pretreatment characteristic of the sample to be tested, that is, the first key characteristic, through a pretreatment operation; in a possible embodiment, the pretreatment step of the first pretreatment characteristic of the sample to be tested in step S2 includes: B1: Solvent optimization: Based on the physical and chemical properties of the sample in the first pretreatment feature of the sample to be tested, a solvent is selected to maximize the purity of the fatty acids extracted from the sample to be tested; Specifically, the physical properties of the sample in the first pretreatment feature of the sample to be tested include the polarity, solubility, and viscosity of the sample to determine the compatibility of the sample with the solvent; the chemical properties of the sample in the first pretreatment feature of the sample to be tested include the composition, saturation content, and stability of fatty acids to improve the extraction efficiency and purity; the ratio of solvent to sample, extraction time, and temperature conditions are adjusted to optimize the extraction process to maximize the extraction purity of fatty acids; In this embodiment, polar solvents are used to extract polar fatty acids, and non-polar solvents are used to extract non-polar fatty acids; B2: Sample purification: The sample to be tested is subjected to solvent purification technology and homogenization technology to remove impurities and interfering substances in the sample to be tested, and obtain a pure fatty acid extract in the sample to be tested; Specifically, purification technologies include liquid-liquid extraction, solid phase extraction, and membrane separation technology; liquid-liquid extraction is to achieve the purpose of separation, extraction and purification by different distribution ratios of different components in the sample in two incompatible solvents; solid phase extraction is to achieve separation and purification by adsorbing and eluting specific components in the sample through solid adsorbents; membrane separation technology is to use the selective permeability of semipermeable membranes to achieve component separation through pressure drive; Specifically, homogenization technology includes the use of a homogenizer and ultrasonic crushing methods to break the fat in the sample into smaller pieces, thereby making the entire product system more stable; Specifically, the pure fatty acid extract of the sample to be tested is a sample containing target fatty acids and low impurity content obtained by solvent borrowing purification technology and homogenization technology; B3: Sample concentration: The pure fatty acid extract in the sample to be tested is concentrated by reducing the volume of solvent through concentration technology to increase the concentration of fatty acids and obtain a concentrated fatty acid sample of the sample to be tested; Specifically, the concentration technologies include: evaporation, freeze drying, and rotary evaporator: evaporation technology is to reduce the volume of the solvent by heating to concentrate the fatty acids, and is carried out under reduced pressure conditions to reduce the boiling point of the solvent and reduce the risk of damage to heat-sensitive substances; freeze drying is a process of directly vaporizing the solvent from the solid state without passing through the liquid state under low temperature and low pressure conditions, which is particularly suitable for the concentration of heat-sensitive substances; rotary evaporator uses a vacuum pump to reduce the boiling point of the solvent, and at the same time increases the liquid surface area by rotation to accelerate the evaporation process; B4: Obtaining the first key feature: Analyze the fatty acid sample after the sample to be tested is concentrated to obtain the first key feature related to the degree of hydrogenation of the fatty acid, the first key feature includes the melting point of the fatty acid sample, the boiling point of the fatty acid sample, the iodine value of the fatty acid sample, and the smell of the fatty acid sample; Specifically, since the increase in the degree of hydrogenation leads to an increase in the melting point of fatty acids, a melting point meter is used to measure according to standard operating procedures; the change in boiling point reflects the degree of hydrogenation of fatty acids, and the boiling point of the sample is measured by a boiling point meter and compared with known data for analysis; the degree of hydrogenation of fatty acids is reflected by iodine value determination, which is determined by the Weiss iodine value method, and the iodine value is determined by titration after the sample is reacted with Weiss reagent; the odor components of the sample are analyzed by gas chromatography-mass spectrometry.

[0030] Step S2 maximizes the purity of fatty acids extracted from the sample to be tested by solvent optimization, thereby improving the accuracy of subsequent analysis; removes impurities and interfering substances in the sample to be tested by sample purification, obtains pure fatty acid extracts, and improves the reliability of the test results; reduces the solvent volume and increases the concentration of fatty acids by sample concentration, thereby providing clearer signals for spectral analysis; and obtains the first key feature by analyzing the concentrated fatty acid sample of the sample to be tested, thereby obtaining characteristic information related to the degree of hydrogenation of fatty acids, thereby providing key data support for the final evaluation.

[0031] S3. Obtain a second preprocessing feature: Obtain a second preprocessing feature corresponding to the first key feature, wherein the second preprocessing feature uses a high-resolution spectrometer to collect spectral data of the first key feature, and the collection method uses multimodal spectroscopy technology.

[0032] Specifically, the fatty acid hydrogenation degree detection system obtains a second preprocessing feature, and the second preprocessing feature is to use a high-resolution spectrometer to collect spectral data of the sample to be tested corresponding to the first key feature, and the collection method uses multimodal spectroscopy technology.

[0033] In this embodiment, the process of obtaining the second pretreatment characteristic of the fatty acid hydrogenation degree detection system is as follows: using a spectrometer with high sensitivity and precise resolution, the spectrometer includes a Fourier transform infrared spectrometer and a UV-visible spectrophotometer, to collect spectral data of the first key characteristic; in the collection process, multimodal spectral technology is used to obtain richer and more comprehensive spectral information; multimodal spectral technology comprehensively uses a variety of different types of spectral technologies, spectral technologies include infrared spectroscopy, Raman spectroscopy, and fluorescence spectroscopy, to comprehensively obtain the second pretreatment characteristics of the sample, the second pretreatment characteristics include the absorption intensity of the sample in different infrared bands, the frequency shift of the scattered light of the sample, and the fluorescence emission intensity under different excitation wavelengths.

[0034] In this embodiment, infrared spectroscopy provides information about the vibration of chemical bonds in fatty acid molecules, Raman spectroscopy reflects changes in the polarizability of molecules, and fluorescence spectroscopy detects the fluorescence characteristics of fatty acid molecules. By comprehensively using multiple spectroscopic techniques, fatty acids are analyzed from multiple angles to improve the accuracy and reliability of the second pretreatment feature.

[0035] Step S3 obtains high-precision spectral data by using a high-resolution spectrometer to improve the accuracy and reliability of the test results; obtains richer and more comprehensive spectral information by adopting multimodal spectral technology, and analyzes the characteristics of fatty acids from multiple angles, thereby improving the comprehensiveness and reliability of the test; comprehensively obtains the second pretreatment characteristics of the sample by using a variety of spectral technologies such as infrared spectroscopy, Raman spectroscopy and fluorescence spectroscopy to ensure the accuracy and reliability of the test results; obtains the absorption intensity of the sample in different infrared bands, the frequency shift of the scattered light of the sample, and the fluorescence emission intensity under different excitation wavelengths, and deeply understands the structure and properties of fatty acids from the molecular level, providing a solid data foundation for subsequent comprehensive analysis.

[0036] S4. Obtain a second key feature: obtain a spectral correction model, and obtain a second key feature corresponding to the second preprocessing feature through the second preprocessing feature according to the spectral correction model.

[0037] Specifically, the spectral correction model is a pre-constructed learning model, and by inputting the second preprocessing feature into the spectral correction model, the spectral correction model obtains the second key feature according to the second preprocessing feature.

[0038] In one possible embodiment, step S4 includes: performing a correction operation on the second preprocessing feature according to the second preprocessing feature to obtain a second key feature corresponding to the second preprocessing feature, the second key feature being a target correction spectral feature corresponding to the second preprocessing feature, the target correction spectral feature including a chemical bond vibration frequency, a range of change of molecular polarizability, and a change pattern of fluorescence emission intensity; obtaining a spectral correction model corresponding to the key feature in a preset spectral database, the preset spectral database being used to save the correspondence between the key feature and the spectral correction model.

[0039] In this embodiment, when performing the correction operation, the second preprocessing feature is analyzed in detail; specifically, the chemical bond vibration frequency reflects the change in vibration frequency of different chemical bonds in the fatty acid molecule at different degrees of hydrogenation; the range of change in molecular polarizability reflects the change in the degree of polarization of the fatty acid molecule under the action of the electric field; the change pattern of the fluorescence emission intensity reflects the information on the molecular structure and electronic transition of the fatty acid; when the second preprocessing feature is obtained, the key feature matching it will be searched in the database, and the corresponding spectral correction model will be obtained.

[0040] In a possible implementation, step S4 also includes: obtaining a correction feature association value, the correction feature association value being the degree of association between the second preprocessing feature and the target correction spectral feature, to determine whether the degree of association reaches a preset threshold; if the degree of association reaches the preset threshold, confirming that the target correction spectral feature is the second key feature corresponding to the second preprocessing feature.

[0041] In this embodiment, the correction feature association value is calculated by a statistical method to reflect the correlation between the second preprocessing feature and the target correction spectral feature; the preset threshold is determined based on historical data. If the degree of correlation reaches or exceeds the threshold, it is considered that the target correction spectral feature is highly correlated with the second preprocessing feature and is confirmed as the second key feature.

[0042] In a possible implementation, step S4 also includes: obtaining a spectral correction set corresponding to the target correction spectral feature, based on the spectral correction set, the spectral correction set includes feature recognition technology, signal separation algorithm, signal enhancement technology, and resolution optimization; obtaining characteristic parameters and characteristic patterns corresponding to the target correction spectral feature; and constructing a spectral correction model based on the characteristic parameters and characteristic patterns.

[0043] Specifically, feature recognition technology is used to identify characteristic information related to the degree of hydrogenation of fatty acids; signal separation algorithms remove noise and interfering signals; signal enhancement technology improves signal strength and clarity; and resolution optimization improves the resolution of spectral data.

[0044] Step S4 obtains the second key feature according to the second preprocessing feature by acquiring the spectral correction model, thereby improving the accuracy and reliability of the detection result; obtains the target correction spectral feature by performing a correction operation on the second preprocessing feature, thereby more accurately reflecting the characteristics of the fatty acid molecules and improving the detection accuracy; determines the degree of correlation between the second preprocessing feature and the target correction spectral feature by obtaining the correction feature correlation value, and ensures that the obtained second key feature is consistent with the actual condition of the sample; and performs feature recognition, signal separation, signal enhancement and resolution optimization on the spectral data by constructing a spectral correction model, thereby improving the analysis quality of the spectral data and the reliability of the detection results.

[0045] S5. Obtain the third key feature: Obtain the third key feature corresponding to the second key feature through the second key feature according to the stoichiometric analysis.

[0046] In a possible implementation, the step of acquiring the third key feature of the sample to be tested in S5 includes: C1: Detection of the second key feature with the help of chemometric tools; C2: Calculate the degree of hydrogenation in the second key feature using a variety of chemometric methods; C3: Applying machine learning algorithms to perform pattern recognition and classification on the second key feature to determine the degree of hydrogenation of fatty acids; C4: Compare the physical properties of the second key feature in the sample to be tested with the chemical properties, which, after verification, constitute the third key feature.

[0047] Specifically, the chemometric tools used in the detection of the degree of hydrogenation of fatty acids include spectrometers, chromatographs, and mass spectrometers; various chemometric methods used in the detection of the degree of hydrogenation of fatty acids include partial least squares, principal component analysis, and cluster analysis to extract useful information and establish models to detect the degree of hydrogenation of fatty acids. Machine learning algorithms used in the detection of the degree of hydrogenation of fatty acids include support vector machines, artificial neural networks, and decision trees to determine the degree of hydrogenation of fatty acids; Specifically, the physical properties of the second key feature in the sample to be tested are compared with the sample data, and the difference between the chemical properties of the fatty acids in the second key feature and the expected hydrogenation effect is compared; the consistency of the second key feature with the expected degree of hydrogenation is further verified to confirm whether the actual degree of hydrogenation of the fatty acids is consistent with that reflected by the second key feature; based on the results of comprehensive comparison and verification, the information related to the degree of hydrogenation in the second key feature is integrated and refined to form the third key feature.

[0048] Step S5 detects the second key feature with the help of chemometric tools to more accurately analyze the chemical composition of the sample, providing a reliable data basis for the subsequent calculation of the degree of hydrogenation; by using a variety of chemometric methods to calculate the degree of hydrogenation in the second key feature, the hydrogenation state of fatty acids is evaluated from different angles and dimensions, thereby improving the accuracy and reliability of the results; by using machine learning algorithms to perform pattern recognition and classification on the second key feature, the degree of hydrogenation of fatty acids is automatically identified, thereby improving the automation level and efficiency of detection; the physical properties and chemical properties of the second key feature are compared and verified to ensure that the final third key feature reflects the actual sample condition, thereby enhancing the scientificity and reliability of the results.

[0049] S6. Obtaining a comprehensive fatty acid hydrogenation evaluation model: Obtaining a comprehensive fatty acid hydrogenation evaluation model, and obtaining an analysis result of the third key feature through the third key feature according to the comprehensive fatty acid hydrogenation evaluation model.

[0050] Specifically, the comprehensive fatty acid hydrogenation evaluation model is a pre-constructed learning model. The third key feature is input into the comprehensive fatty acid hydrogenation evaluation model, and the comprehensive fatty acid hydrogenation evaluation model obtains the analysis result of the third key feature according to the third key feature.

[0051] Specifically, after obtaining the third key feature, the fatty acid hydrogenation degree detection system analyzes the third key feature through a comprehensive fatty acid hydrogenation evaluation model to obtain an evaluation result of the fatty acid hydrogenation degree; the comprehensive fatty acid hydrogenation evaluation model includes multiple linear regression, artificial neural network, and extreme learning machine; the selection of the comprehensive fatty acid hydrogenation evaluation model depends on the characteristics of the third key feature, and obtains fast and accurate analysis results.

[0052] S7. Display comprehensive fatty acid hydrogenation assessment report: Based on the comprehensive fatty acid hydrogenation assessment model, through the third key feature, the result of comprehensive analysis sends the fatty acid hydrogenation degree corresponding to the third key feature to the user in a preset display method.

[0053] Specifically, the preset display methods include intuitive charts and reports, so that users can clearly understand the specific situation of the degree of hydrogenation of fatty acids; among them, the specific numerical value of the degree of hydrogenation can provide accurate quantitative information, allowing users to intuitively understand the degree of hydrogenation of fatty acids; at the same time, the comprehensive analysis also includes possible uncertainty analysis, helping users to fully understand the limitations and potential risks of the evaluation results, so that users can fully consider these factors when making decisions.

[0054] As attached Figure 2 The fatty acid hydrogenation degree detection system based on spectral analysis shown includes a system operation database, a system central processing module and a user information segment, and also includes a first preprocessing feature acquisition module, a first preprocessing feature preprocessing module, a second preprocessing feature acquisition module, a second key feature acquisition module, a third key feature acquisition module, a comprehensive fatty acid hydrogenation evaluation model acquisition module, and a comprehensive fatty acid hydrogenation evaluation report output module.

[0055] Specifically, the system operation database includes all data texts of the fatty acid hydrogenation degree detection system, and collects the information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control system, and the user information terminal is an information output device for receiving the fatty acid hydrogenation degree detection system; A first preprocessing feature acquisition module: based on the analysis requirements of the sample, the sample to be detected is recorded as a sample to be tested, and a first preprocessing feature of the sample to be tested is acquired; First preprocessing feature preprocessing module: performs a preprocessing operation on the first preprocessing feature of the sample to be tested, and the preprocessing operation is used to obtain a first key feature corresponding to the first preprocessing feature of the sample to be tested; A second preprocessing feature acquisition module: acquiring a second preprocessing feature corresponding to the first key feature, wherein the second preprocessing feature is to collect spectral data of the first key feature using a high-resolution spectrometer, and the collection method uses a multimodal spectroscopy technology; A second key feature acquisition module: acquires a spectrum correction model, and acquires a second key feature corresponding to the second preprocessing feature through the second preprocessing feature according to the spectrum correction model; A third key feature acquisition module: acquires a third key feature corresponding to the second key feature through the second key feature according to stoichiometric analysis; Comprehensive fatty acid hydrogenation evaluation model acquisition module: obtain the comprehensive fatty acid hydrogenation evaluation model, and obtain the analysis result of the third key feature through the third key feature according to the comprehensive fatty acid hydrogenation evaluation model; Comprehensive fatty acid hydrogenation assessment report output module: Based on the comprehensive fatty acid hydrogenation assessment model, through the third key feature, the fatty acid hydrogenation degree corresponding to the third key feature is sent to the user in a preset display method based on the result of comprehensive analysis.

[0056] In this embodiment, the acquisition steps in the second key feature acquisition module are as follows: according to the second preprocessing feature, the second preprocessing feature is corrected to obtain the second key feature corresponding to the second preprocessing feature, the second key feature is the target correction spectrum feature corresponding to the second preprocessing feature, the target correction spectrum feature includes the chemical bond vibration frequency, the range of change of molecular polarizability and the change pattern of fluorescence emission intensity; the correction feature association value is obtained, the correction feature association value is the degree of association between the second preprocessing feature and the target correction spectrum feature, so as to determine whether the degree of association reaches a preset threshold; if the degree of association reaches the preset threshold, it is confirmed that the target correction spectrum feature is the second key feature corresponding to the second preprocessing feature; the spectrum correction set corresponding to the target correction spectrum feature is obtained, according to the spectrum correction set, the spectrum correction set includes feature recognition technology, signal separation algorithm, signal enhancement technology, and resolution optimization; the characteristic parameters and characteristic patterns corresponding to the target correction spectrum feature are obtained; according to the characteristic parameters and characteristic patterns, a spectrum correction model is constructed.

[0057] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis, characterized in that: include: S1. Obtaining a first preprocessing characteristic of the sample to be tested: Based on the analysis requirements of the sample, the sample to be tested is recorded as the sample to be tested, and a first preprocessing characteristic of the sample to be tested is obtained; S2, performing a preprocessing operation on the first preprocessing feature of the sample to be tested: performing a preprocessing operation on the first preprocessing feature of the sample to be tested, the preprocessing operation being used to obtain a first key feature corresponding to the first preprocessing feature of the sample to be tested; S3, obtaining a second preprocessing feature: obtaining a second preprocessing feature corresponding to the first key feature, the second preprocessing feature is to collect spectral data of the first key feature using a high-resolution spectrometer, and the collection method uses a multimodal spectroscopy technology; S4, obtaining a second key feature: obtaining a spectrum correction model, and obtaining a second key feature corresponding to the second preprocessing feature through the second preprocessing feature according to the spectrum correction model; S5. Obtaining a third key feature: Obtaining a third key feature corresponding to the second key feature through the second key feature according to the stoichiometric analysis; S6. Obtaining a comprehensive fatty acid hydrogenation evaluation model: Obtaining a comprehensive fatty acid hydrogenation evaluation model, and obtaining an analysis result of the third key feature through the third key feature according to the comprehensive fatty acid hydrogenation evaluation model; S7. Display comprehensive fatty acid hydrogenation assessment report: Based on the comprehensive fatty acid hydrogenation assessment model, through the third key feature, the fatty acid hydrogenation degree corresponding to the third key feature is sent to the user in a preset display method based on the result of comprehensive analysis.

2. A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 1, characterized in that: The step of obtaining the first preprocessing characteristic of the sample to be tested in S1 includes: A1: Record the basic information of each sample in the sample set, including the name of the sample, the source of the sample, the batch of the sample, and the storage conditions of the sample; A2: measuring the physical properties of each sample in the sample set, the physical properties including the color of the sample, the transparency of the sample and the texture of the sample; A3: Analyze the chemical properties of each sample in the sample set, the chemical properties including the pH value of the sample, the water content of the sample, and the fatty acid composition of the sample; A4: uniquely mark the original features of each sample to be tested in the sample set, mark each sample to be tested in the sample set with a number, and associate the marking information of each sample to be tested with the original features of each sample to be tested to form a first preprocessing feature.

3. A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 1, characterized in that: The preprocessing step of the first preprocessing feature of the sample to be tested in S2 comprises: B1: Solvent optimization: Based on the physical and chemical properties of the sample in the first pretreatment feature of the sample to be tested, a solvent is selected to maximize the purity of the fatty acids extracted from the sample to be tested; B2: Sample purification: The sample to be tested is subjected to solvent purification technology and homogenization technology to remove impurities and interfering substances in the sample to be tested, and obtain a pure fatty acid extract in the sample to be tested; B3: Sample concentration: The pure fatty acid extract in the sample to be tested is concentrated by reducing the volume of solvent through concentration technology to increase the concentration of fatty acids and obtain a concentrated fatty acid sample of the sample to be tested; B4: Obtaining the first key feature: Analyze the fatty acid sample after the sample to be tested is concentrated to obtain the first key feature related to the degree of hydrogenation of the fatty acid. The first key feature includes the double bond position, cis-trans configuration, and carbon chain length information of the fatty acid.

4. The method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 1, characterized in that: The spectral correction model is obtained in S4, specifically including: According to the second preprocessing feature, a correction operation is performed on the second preprocessing feature to obtain a second key feature corresponding to the second preprocessing feature, where the second key feature is a target correction spectral feature corresponding to the second preprocessing feature, and the target correction spectral feature includes a chemical bond vibration frequency, a range of change of molecular polarizability, and a change pattern of fluorescence emission intensity; In a preset spectral database, a spectral correction model corresponding to the key feature is obtained. The preset spectral database is used to store the corresponding relationship between the key feature and the spectral correction model.

5. A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 4, characterized in that: The step S4 of obtaining the second key feature corresponding to the second preprocessing feature specifically includes: Obtaining a correction feature correlation value, where the correction feature correlation value is a correlation degree between the second preprocessing feature and the target correction spectrum feature, to determine whether the correlation degree reaches a preset threshold; If the correlation degree reaches a preset threshold, the target correction spectrum feature is confirmed to be the second key feature corresponding to the second preprocessing feature.

6. A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 4, characterized in that: The spectral correction model is obtained in S4, and before obtaining the target correction spectral feature corresponding to the second key feature through the second key feature according to the spectral correction model, the spectral correction model is constructed, which specifically includes: Obtaining a spectral correction set corresponding to a target correction spectral feature; According to the spectral correction set, characteristic parameters and characteristic patterns corresponding to the target correction spectral characteristics are obtained; A spectral correction model is constructed based on characteristic parameters and characteristic patterns.

7. A method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 6, characterized in that: The acquisition of the spectral correction set in S4 includes feature recognition technology, signal separation algorithm, signal enhancement technology, and resolution optimization.

8. The method for detecting the degree of hydrogenation of fatty acids based on spectral analysis according to claim 1, characterized in that: The step of obtaining the third key feature of the sample to be tested in S5 includes: C1: Detection of the second key feature with the help of chemometric tools; C2: Calculate the degree of hydrogenation in the second key feature using a variety of chemometric methods; C3: Applying machine learning algorithms to perform pattern recognition and classification on the second key feature to determine the degree of hydrogenation of fatty acids; C4: Compare the physical properties of the second key feature in the sample to be tested with the chemical properties, which, after verification, constitute the third key feature.

9. A fatty acid hydrogenation degree detection system based on spectral analysis, comprising a system operation database, a system central processing module and a user information segment, according to any one of claims 1 to 8 for a fatty acid hydrogenation degree detection method based on spectral analysis, characterized in that: Also includes: The system operation database includes all data texts of the fatty acid hydrogenation degree detection system, and collects the information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control system. The user information terminal is an information output device for receiving the fatty acid hydrogenation degree detection system; A first preprocessing feature acquisition module: based on the analysis requirements of the sample, the sample to be detected is recorded as a sample to be tested, and a first preprocessing feature of the sample to be tested is acquired; First preprocessing feature preprocessing module: performs a preprocessing operation on the first preprocessing feature of the sample to be tested, and the preprocessing operation is used to obtain a first key feature corresponding to the first preprocessing feature of the sample to be tested; A second preprocessing feature acquisition module: acquiring a second preprocessing feature corresponding to the first key feature, wherein the second preprocessing feature is to collect spectral data of the first key feature using a high-resolution spectrometer, and the collection method uses a multimodal spectroscopy technology; A second key feature acquisition module: acquires a spectrum correction model, and acquires a second key feature corresponding to the second preprocessing feature through the second preprocessing feature according to the spectrum correction model; A third key feature acquisition module: acquires a third key feature corresponding to the second key feature through the second key feature according to stoichiometric analysis; Comprehensive fatty acid hydrogenation evaluation model acquisition module: obtain the comprehensive fatty acid hydrogenation evaluation model, and obtain the analysis result of the third key feature through the third key feature according to the comprehensive fatty acid hydrogenation evaluation model; Comprehensive fatty acid hydrogenation assessment report output module: Based on the comprehensive fatty acid hydrogenation assessment model, through the third key feature, the fatty acid hydrogenation degree corresponding to the third key feature is sent to the user in a preset display method based on the result of comprehensive analysis.

10. A fatty acid hydrogenation degree detection system based on spectral analysis according to claim 9, characterized in that: The acquisition steps in the second key feature acquisition module are as follows: According to the second preprocessing feature, a correction operation is performed on the second preprocessing feature to obtain a second key feature corresponding to the second preprocessing feature, the second key feature is a target correction spectral feature corresponding to the second preprocessing feature, and the target correction spectral feature includes a chemical bond vibration frequency, a range of change of molecular polarizability, and a change pattern of fluorescence emission intensity; in a preset spectral database, a spectral correction model corresponding to the key feature is obtained, and the preset spectral database is used to store the correspondence between the key feature and the spectral correction model; a correction feature correlation value is obtained, and the correction feature correlation value is a correlation degree between the second preprocessing feature and the target correction spectral feature, so as to determine whether the correlation degree reaches a preset threshold value; if the correlation degree reaches the preset threshold value, it is confirmed that the target correction spectral feature is the second key feature corresponding to the second preprocessing feature; Obtain a spectral correction set corresponding to the target correction spectral feature, based on the spectral correction set, which includes a feature recognition technology, a signal separation algorithm, a signal enhancement technology, and resolution optimization; obtain characteristic parameters and characteristic patterns corresponding to the target correction spectral feature; A spectral correction model is constructed based on characteristic parameters and characteristic patterns.

Images