An intelligent identification device and method for different qualities of Ganoderma lucidum based on infrared spectroscopy

Abstract

The present invention relates to the field of identification of ganoderma lucidum components, and specifically to an intelligent identification device and method for ganoderma lucidum of different qualities based on infrared spectroscopy. The method first obtains infrared absorption spectrum curves of different ganoderma lucidum samples, extracts the absorption peak of each spectrum curve, analyzes the position distribution of the absorption peaks in the same column of each spectrum curve, obtains the position deviation of each absorption peak of the spectrum curve, and adjusts the position of each absorption peak of the spectrum curve through the compensation coefficient of each absorption peak obtained to obtain an adjusted target spectrum curve, and identifies the components of the ganoderma lucidum sample corresponding to the spectrum curve based on the adjusted target spectrum curve. The present invention can eliminate the phenomenon of absorption peak deviation in the infrared absorption spectrum, and improve the accuracy of identifying ganoderma lucidum components of different qualities.

Description

Technical Field

[0001] The invention relates to the field of identification of ganoderma lucidum components, and in particular to an intelligent identification device and method for ganoderma lucidum of different qualities based on infrared spectroscopy. Background Art

[0002] Lingzhi has a long history in traditional Chinese medicine and is highly favored for its rich medicinal value. The quality of Lingzhi on the market varies greatly, and its quality directly affects its efficacy and safety. Therefore, it is particularly important to identify the quality of Lingzhi.

[0003] In the related art, the infrared absorption spectrum of Ganoderma lucidum samples is usually analyzed to identify the characteristic absorption peaks corresponding to specific chemical bonds or functional groups, and the identified characteristic peaks are compared with the infrared spectrum data of known compounds to identify the components of Ganoderma lucidum. However, due to the impurities or other interfering substances contained in Ganoderma lucidum, the absorption peaks in the collected infrared absorption spectrum will be offset, resulting in errors in the infrared absorption spectrum data, which makes it impossible to accurately identify the components in Ganoderma lucidum of different qualities using existing methods. Summary of the invention

[0004] In order to solve the technical problem that the existing methods cannot accurately identify the components of Ganoderma lucidum of different qualities, the purpose of the present invention is to provide an intelligent identification device and method of Ganoderma lucidum of different qualities based on infrared spectroscopy. The technical scheme adopted is as follows:

[0005] The present invention proposes an intelligent identification method for Ganoderma lucidum of different qualities based on infrared spectroscopy, the method comprising:

[0006] Obtaining infrared absorption spectra of different ganoderma samples, wherein the infrared absorption spectra include spectrum curves of different ganoderma samples, and the spectrum curves include absorbances at different wavelengths;

[0007] The spectral curve of any Ganoderma lucidum sample is taken as the target spectral curve, the wavelength of each maximum point on the target spectral curve is taken as the maximum wavelength, and the absorption peak of the target spectral curve is obtained according to the difference between the absorbance of each wavelength in the preset neighborhood of each maximum wavelength and the absorbance of each maximum wavelength; the wavelength of the maximum point of each absorption peak is taken as the position parameter of each absorption peak, any absorption peak of the target spectral curve is taken as the target absorption peak, and other spectral curves except the target spectral curve are taken as reference spectral curves, and according to the difference in the position parameters between the target absorption peak and each absorption peak of the reference spectral curve, the reference absorption peak of the target absorption peak is selected from the absorption peaks of each reference spectral curve; according to the position parameter of the target absorption peak and the distribution of the position parameters of all reference absorption peaks, the position deviation of the target absorption peak is obtained; according to the position deviation of all absorption peaks of the target spectral curve, the overall deviation of the target spectral curve is obtained;

[0008] According to the difference of the position parameters between the target absorption peak and each reference absorption peak, and the overall deviation of the target spectrum curve, a compensation coefficient of the target absorption peak is obtained; based on the compensation coefficient of each absorption peak of the target spectrum curve, the position of each absorption peak of the target spectrum curve is adjusted to obtain an adjusted target spectrum curve;

[0009] Based on the adjusted target spectral curve, the components of the Ganoderma lucidum sample corresponding to the target spectral curve are identified.

[0010] Further, the obtaining of the absorption peak of the target spectrum curve comprises:

[0011] Taking any maximum wavelength of the target spectrum curve as the target maximum wavelength, and taking the absolute value of the difference between the absorbance of each wavelength in a preset neighborhood of the target maximum wavelength and the absorbance of the target maximum wavelength as the absorbance difference value of each wavelength in the preset neighborhood;

[0012] Taking the average value of the absorbance difference values ​​between all wavelengths in the preset neighborhood and the target maximum wavelength as the overall absorbance difference parameter of the preset neighborhood;

[0013] Normalizing the absolute value of the difference between the absorbance difference value of each wavelength in the preset neighborhood and the overall absorbance difference parameter of the preset neighborhood to obtain a difference evaluation value of each wavelength in the preset neighborhood;

[0014] Based on the difference evaluation value of each wavelength in a preset neighborhood of the target maximum wavelength, an absorption peak of the target spectrum curve at the target maximum wavelength is obtained.

[0015] Further, obtaining the absorption peak of the target spectrum curve at the target maximum wavelength includes:

[0016] In a preset neighborhood of the target maximum wavelength, the wavelength whose difference evaluation value is less than a preset difference threshold is used as the absorption peak wavelength in the preset neighborhood;

[0017] The portion of the target spectrum curve between the minimum value of the absorption peak wavelength and the maximum value of the absorption peak wavelength within a preset neighborhood of the target maximum wavelength is taken as the absorption peak of the target spectrum curve at the target maximum wavelength.

[0018] Further, the step of selecting a reference absorption peak of a target absorption peak from the absorption peaks of each reference spectrum curve comprises:

[0019] Taking any reference spectrum curve as a target reference spectrum curve, and taking the absolute value of the difference between the target absorption peak and each absorption peak of the target reference spectrum curve as the distance parameter between the target absorption peak and each absorption peak of the target reference spectrum curve;

[0020] On the target reference spectrum curve, the absorption peak corresponding to the minimum value of the distance parameter is used as the reference absorption peak of the target absorption peak.

[0021] Further, obtaining the position deviation of the target absorption peak includes:

[0022] Taking the average value of the position parameters of all reference absorption peaks of the target absorption peak as the overall reference position parameter of the target absorption peak;

[0023] The standard deviation of the position parameters of all reference absorption peaks of the target absorption peak is used as the reference position dispersion of the target absorption peak;

[0024] The absolute value of the difference between the position parameter of the target absorption peak and the overall reference position parameter is used as the shift coefficient of the target absorption peak, and the sum of the shift coefficient of the target absorption peak and the reference position discreteness is used as the position shift degree of the target absorption peak.

[0025] Further, the obtaining of the overall deviation of the target spectral curve comprises:

[0026] The average value of the position shifts of all absorption peaks of the target spectral curve is taken as the overall shift of the target spectral curve.

[0027] Further, the compensation coefficient for obtaining the target absorption peak includes:

[0028] Taking any reference spectrum curve as the reference spectrum curve to be measured;

[0029] The absolute value of the difference between the position parameter of the target absorption peak and the position parameter of the reference absorption peak of the reference spectrum curve to be measured is used as the initial position difference value of the target absorption peak with respect to the reference spectrum curve to be measured;

[0030] Taking the average of all the initial position difference values ​​of all the absorption peaks of the target spectrum curve with respect to the reference spectrum curve to be measured as the overall position difference value of the reference spectrum curve to be measured;

[0031] The initial position difference value of the target absorption peak with respect to the reference spectrum curve to be measured is used as the numerator, the overall position difference value of the reference spectrum curve to be measured is used as the denominator, and the comparison value is normalized to obtain the initial deviation parameter of the target absorption peak with respect to the reference spectrum curve to be measured;

[0032] The product value of the average value of the initial deviation parameters of the target absorption peak with respect to all reference spectral curves and the overall deviation degree of the target spectral curve is used as the compensation coefficient of the target absorption peak.

[0033] Further, obtaining the adjusted target spectrum curve includes:

[0034] Using the product value of the compensation coefficient and the position parameter of each absorption peak of the target spectrum curve as the adjustment position parameter of each absorption peak of the target spectrum curve, and using the difference between the adjustment position parameter and the position parameter of each absorption peak of the target spectrum curve as the position adjustment amount of each absorption peak of the target spectrum curve;

[0035] Any absorption peak of the target spectrum curve is used as the absorption peak to be adjusted. If the position adjustment amount of the absorption peak to be adjusted is greater than a value of 0, the absorption peak to be adjusted is moved to the right, wherein the moving distance is the absolute value of the position adjustment amount of the absorption peak to be adjusted;

[0036] If the position adjustment amount of the absorption peak to be adjusted is less than the value 0, the absorption peak to be adjusted is moved to the left, wherein the moving distance is the absolute value of the position adjustment amount of the absorption peak to be adjusted;

[0037] If the position adjustment amount of the absorption peak to be adjusted is equal to the value 0, the absorption peak to be adjusted will not be moved;

[0038] All absorption peaks of the target spectrum curve are traversed, and each absorption peak is moved to obtain an adjusted target spectrum curve.

[0039] Furthermore, the identifying of the components of the ganoderma lucidum sample corresponding to the target spectrum curve includes:

[0040] The adjusted target spectrum curve is compared with the standard infrared absorption spectrum curve in the database to identify the components of the Ganoderma lucidum sample corresponding to the target spectrum curve.

[0041] The present invention also proposes an intelligent identification system for Ganoderma lucidum of different qualities based on infrared spectroscopy. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any one of the steps of an intelligent identification method for Ganoderma lucidum of different qualities based on infrared spectroscopy.

[0042] The present invention has the following beneficial effects:

[0043] The present invention takes into account that the existing methods cannot accurately identify the components in Ganoderma lucidum of different qualities, so firstly obtain the infrared absorption spectra of different Ganoderma lucidum samples. Since the components in Ganoderma lucidum are manifested as specific absorption peaks in the spectrum curve, and the absorption peaks generally appear at the maximum point position of the spectrum curve, the absorption peaks in the target spectrum curve can be firstly identified, and then the location of each absorption peak can be realized through the position parameter, so as to facilitate the subsequent analysis of the absorption peaks at the same position in different spectrum curves. Considering that the infrared absorption spectrum data of different Ganoderma lucidum are different due to the different growth environments, which is specifically manifested in the absorption peaks on the spectrum curve of Ganoderma lucidum There is a shift phenomenon, so firstly select from the absorption peaks of each reference spectrum curve A reference absorption peak of the target absorption peak is obtained, the positions of the reference absorption peak and the target absorption peak are the same, and the degree of position shift of the target absorption peak is reflected by the obtained position shift degree, and then the overall situation of the position shift of the absorption peak of the target spectrum curve is analyzed, and the overall level of position shift of the absorption peak of the target spectrum curve is reflected by the obtained overall shift degree, and then the position of each absorption peak of the target spectrum curve is adjusted by the obtained compensation coefficient, so as to achieve the position adjustment of the absorption peak with shift phenomenon in the target spectrum curve, reduce the error of the spectral data, and identify the components of the Ganoderma lucidum sample corresponding to the target spectrum curve based on the adjusted target spectrum curve, so as to improve the accuracy of identifying the components of the Ganoderma lucidum sample. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A flow chart of an intelligent identification method for Ganoderma lucidum of different qualities based on infrared spectroscopy provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of an intelligent identification device and method of different qualities of Ganoderma lucidum based on infrared spectroscopy proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0047] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0048] The specific scheme of the intelligent identification device and method of different qualities of Ganoderma lucidum based on infrared spectroscopy provided by the present invention is described in detail below with reference to the accompanying drawings.

[0049] See also Figure 1 , which shows a flow chart of an intelligent identification method of different qualities of Ganoderma lucidum based on infrared spectroscopy provided by an embodiment of the present invention, the method comprising:

[0050] Step S1: Obtain infrared absorption spectra of different Ganoderma lucidum samples, wherein the infrared absorption spectra include spectral curves of different Ganoderma lucidum samples, and the spectral curves include absorbances at different wavelengths.

[0051] In the identification of the ingredients of Ganoderma lucidum of different qualities, traditional identification methods often require professional knowledge and experience, resulting in a cumbersome and inefficient identification process. The introduction of infrared absorption spectroscopy technology provides a new way to quickly identify the quality of Ganoderma lucidum. This method captures the infrared absorption characteristics of Ganoderma lucidum samples at the molecular level to reveal their intrinsic chemical composition and structural information. Since each chemical bond or functional group has a specific absorption position and shape in the infrared absorption spectrum, the characteristic absorption peaks corresponding to specific chemical bonds or functional groups can be identified and compared with the infrared spectrum data of known compounds, thereby achieving the identification of Ganoderma lucidum ingredients.

[0052] Therefore, the embodiment of the present invention first selects a plurality of Ganoderma lucidum samples, and the number of Ganoderma lucidum samples is usually in the range of 10 to 20. In one embodiment of the present invention, 15 Ganoderma lucidum samples are selected. In other embodiments of the present invention, the number of Ganoderma lucidum samples can also be set by the implementer according to the specific real-time scenario, which is not limited here. Each Ganoderma lucidum sample is ground into powder and mixed with dry KBr powder, and then pressed into transparent thin slices under high pressure, so as to prepare sample slices corresponding to different Ganoderma lucidum samples. Then, infrared spectroscopy equipment such as Fourier transform infrared spectrometer is used to collect spectral data of the sample slices of each Ganoderma lucidum sample to obtain infrared absorption spectra of different Ganoderma lucidum samples, wherein the infrared absorption spectra contain spectral curves of different Ganoderma lucidum samples, and the spectral curves contain absorbances of different wavelengths, that is, the abscissa of the infrared absorption spectra is the wavelength, and the ordinate is the absorbance. It should be noted that before collecting spectral data, it is usually necessary to collect a background spectrum when there is no sample in order to perform background correction and eliminate the influence of the instrument and the environment.

[0053] Step S2: taking the spectral curve of any ganoderma lucidum sample as the target spectral curve, taking the wavelength of each maximum point on the target spectral curve as the maximum wavelength, and obtaining the absorption peak of the target spectral curve according to the difference between the absorbance of each wavelength in a preset neighborhood of each maximum wavelength and the absorbance of each maximum wavelength; taking the wavelength of the maximum point of each absorption peak as the position parameter of each absorption peak, taking any absorption peak of the target spectral curve as the target absorption peak, taking other spectral curves except the target spectral curve as reference spectral curves, and selecting the reference absorption peak of the target absorption peak from the absorption peaks of each reference spectral curve according to the difference in position parameters between the target absorption peak and each absorption peak of the reference spectral curve; obtaining the position deviation of the target absorption peak according to the position parameter of the target absorption peak and the distribution of the position parameters of all reference absorption peaks; and obtaining the overall deviation of the target spectral curve according to the position deviation of all absorption peaks of the target spectral curve.

[0054] Since there are differences in the absorption spectrum data of different Ganoderma samples, it is necessary to analyze specific spectrum curves. First, the spectrum curve of any Ganoderma sample is used as the target spectrum curve. Since the infrared absorption spectrum can identify a variety of chemical components in Ganoderma, such as polysaccharides, triterpenoids and other components, the chemical bonds or functional groups of these components have specific absorption positions and shapes in the infrared absorption spectrum, which are usually manifested as specific absorption peaks. The absorption peak generally appears at the position of the maximum point of the spectrum curve. Therefore, the embodiment of the present invention first uses the wavelength of each maximum point on the target spectrum curve as the maximum wavelength, wherein the maximum point can be obtained by the existing Newton method or other methods, which are not limited here. It should be noted that the maximum wavelength can be considered as a point on the horizontal axis.

[0055] At the same time, since the absorption peak usually spans multiple wavelengths, and the smaller the difference between the absorbance of each wavelength around a maximum wavelength and the absorbance of the maximum wavelength, the greater the possibility that the wavelengths around the maximum wavelength belong to the same absorption peak, the difference between the absorbance of each wavelength in the preset neighborhood of each maximum wavelength and the absorbance of each maximum wavelength can be analyzed to identify multiple absorption peaks of the target spectral curve, and the offset of the absorption peak in the spectral curve can be analyzed subsequently to achieve correction of the spectral data, thereby improving the accuracy of identification of Ganoderma lucidum components of different qualities, wherein the preset neighborhood of a maximum wavelength includes a preset number of other wavelengths closest to the maximum wavelength. In one embodiment of the present invention, the preset number is set to 10, and the preset number can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0056] Preferably, in one embodiment of the present invention, the method for obtaining the absorption peak of the target spectrum curve specifically includes:

[0057] First, since each maximum point of the target spectral curve can represent an absorption peak, any maximum wavelength of the target spectral curve is first analyzed, and any maximum wavelength of the target spectral curve is taken as the target maximum wavelength. The absolute value of the difference between the absorbance of each wavelength in a preset neighborhood of the target maximum wavelength and the absorbance of the target maximum wavelength is taken as the absorbance difference value of each wavelength in the preset neighborhood. The larger the absorbance difference value, the greater the difference in absorbance between each wavelength in the preset neighborhood and the target maximum wavelength.

[0058] The average value of the absorbance difference values ​​between all wavelengths in the preset neighborhood and the target maximum wavelength is taken as the overall absorbance difference parameter of the preset neighborhood, and the overall absorbance difference parameter reflects the overall level of the absorbance difference values ​​of all wavelengths in the preset neighborhood of the target maximum wavelength.

[0059] The smaller the difference between the absorbance difference value of each wavelength in the preset neighborhood and the overall absorbance difference parameter of the preset neighborhood, the more likely each wavelength in the preset neighborhood belongs to the same absorption peak. Therefore, the absolute value of the difference between the absorbance difference value of each wavelength in the preset neighborhood and the overall absorbance difference parameter of the preset neighborhood can be normalized to limit the settlement result to range, thereby obtaining a difference evaluation value for each wavelength in the preset neighborhood. The smaller the difference evaluation value, the more likely each wavelength in the preset neighborhood is to belong to the absorption peak represented by the target maximum wavelength.

[0060] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be described in detail.

[0061] As an example, in one embodiment of the present invention, the expression of the difference evaluation value of each wavelength in the preset neighborhood may be specifically, for example, as follows:

[0062]

[0063]

[0064] in, The first The difference evaluation value of wavelengths; The first The absorbance difference at each wavelength; The first The absorbance difference at each wavelength; represents the number of wavelengths within a preset neighborhood of the target maximum wavelength; The first The absorbance at each wavelength; Indicates the absorbance at the target maximum wavelength; represents the normalization function; Represents the overall absorbance difference parameter of a preset neighborhood.

[0065] Furthermore, based on the difference evaluation value of each wavelength in a preset neighborhood of the target maximum wavelength, the absorption peak of the target spectrum curve at the target maximum wavelength can be obtained.

[0066] Preferably, in one embodiment of the present invention, the method for obtaining the absorption peak of the target spectrum curve at the target maximum wavelength specifically includes:

[0067] Within the preset neighborhood of the target maximum wavelength, the wavelength with a difference evaluation value less than the preset difference threshold is taken as the absorption peak wavelength within the preset neighborhood, and the part of the target spectral curve between the minimum value of the absorption peak wavelength and the maximum value of the absorption peak wavelength within the preset neighborhood of the target maximum wavelength is taken as the absorption peak of the target spectral curve at the target maximum wavelength, wherein the preset difference threshold is set to 0.6, and the specific value of the preset difference threshold can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0068] By using the same method as above, the absorption peak of the target spectrum curve at each maximum wavelength can be obtained, thereby obtaining multiple absorption peaks of the target spectrum curve, and further by using the same method, multiple absorption peaks of the spectrum curve of each Ganoderma lucidum sample can be obtained.

[0069] When determining the composition and content of Ganoderma lucidum by infrared absorption spectroscopy, it is necessary to judge the composition and content of Ganoderma lucidum based on the different absorption abilities of different components to infrared light. However, when obtaining the infrared absorption spectrum of Ganoderma lucidum samples, due to the different chemical environments, physical states and intermolecular interactions of different Ganoderma lucidum, the vibration frequency of the molecules will change, which will be manifested as a shift in the position of the absorption peak in the absorption spectrum. In addition, changes in factors such as the physical state, temperature and pressure of the sample will also affect the vibration mode of the molecules, thereby causing the absorption peak to shift. In quantitative analysis, the shift of the absorption peak will lead to measurement errors. Therefore, in subsequent steps, the shift of the absorption peak needs to be corrected to improve the accuracy of the collected spectral data.

[0070] Therefore, the embodiment of the present invention first uses the wavelength of the maximum value point of each absorption peak as the position parameter of each absorption peak, and realizes the positioning of each absorption peak through the position parameter, and then uses any absorption peak of the target spectral curve as the target absorption peak, and uses other spectral curves except the target spectral curve as reference spectral curves, and according to the difference in position parameters between the target absorption peak and each absorption peak of the reference spectral curve, selects the absorption peak with the same position as the target absorption peak from the absorption peaks of each reference spectral curve, that is, the reference absorption peak of the target absorption peak, to facilitate the subsequent analysis of the absorption peaks at the same position in different spectral curves.

[0071] Preferably, in one embodiment of the present invention, the method for obtaining the reference absorption peak of the target absorption peak specifically includes:

[0072] Take any reference spectrum curve as the target reference spectrum curve, and take the absolute value of the difference between the position parameters of the target absorption peak and each absorption peak of the target reference spectrum curve as the distance parameter between the target absorption peak and each absorption peak of the target reference spectrum curve. The smaller the distance parameter is, the more likely it is that each absorption peak of the target reference spectrum curve and the target absorption peak are in the same column in the infrared absorption spectrum graph, which further means that the positions of each absorption peak of the target reference spectrum curve and the target absorption peak are more likely to be the same.

[0073] Then, on the target reference spectrum curve, the absorption peak corresponding to the minimum value of the distance parameter is used as the reference absorption peak of the target absorption peak. The same method can be used to select the reference absorption peak of the target absorption peak on each reference spectrum curve, and for the target absorption peak, there is only one reference absorption peak on each reference spectrum curve. The target absorption peak and the reference absorption peak have the same position and appear as absorption peaks in the same column in the infrared absorption spectrum diagram.

[0074] There are differences in the spectral data of different Ganoderma lucidums. The reason is that the growth environment of Ganoderma lucidum has an important influence on the accumulation of its nutrients. For example, the mineral content in the soil, the purity of the water source, the humidity in the air, etc. will affect the growth and metabolism of Ganoderma lucidum. In different environments, Ganoderma lucidum may absorb different nutrients, resulting in differences in the content of its components, which in turn leads to position differences between absorption peaks at the same position. Therefore, the position parameters of the target absorption peak and the distribution of the position parameters of all reference absorption peaks can be analyzed. The position offset degree obtained reflects the degree of position offset of the target absorption peak. Subsequently, the position of the target absorption peak can be adjusted based on the position offset degree to improve the accuracy of the spectral data.

[0075] Preferably, in one embodiment of the present invention, the method for obtaining the position shift of the target absorption peak specifically includes:

[0076] The average value of the position parameters of all reference absorption peaks of the target absorption peak is taken as the overall reference position parameter of the target absorption peak. The overall level of the position parameters of all reference absorption peaks of the target absorption peak is reflected by the overall reference position parameter. Subsequently, the offset of the target absorption peak position can be analyzed based on the difference between the position parameters of the target absorption peak and the overall reference position parameters.

[0077] Since there are certain differences in the position parameters of each reference absorption peak, the standard deviation of the position parameters of all reference absorption peaks of the target absorption peak can be used as the reference position discreteness of the target absorption peak. Therefore, the reference position discreteness can be used to reflect the discrete degree of the position parameters of all reference absorption peaks of the target absorption peak, thereby improving the calculation accuracy of the subsequent position offset.

[0078] The absolute value of the difference between the position parameter of the target absorption peak and the overall reference position parameter is taken as the shift coefficient of the target absorption peak. The larger the shift coefficient, the greater the degree of position shift of the target absorption peak. At the same time, the reference position discreteness is used to fine-tune the shift coefficient, and the sum of the shift coefficient of the target absorption peak and the reference position discreteness is taken as the position shift of the target absorption peak.

[0079] As an example, in one embodiment of the present invention, the expression of the position shift degree of the target absorption peak can be specifically, for example, as follows:

[0080]

[0081] in, Indicates the position shift of the target absorption peak; Represents the position parameter of the target absorption peak; Represents the overall reference position parameter of the target absorption peak; Indicates the reference position dispersion of the target absorption peak.

[0082] The position shift of each absorption peak of the target spectral curve can be obtained by the same method as above, and then the overall shift of the target spectral curve can be obtained according to the position shift of all absorption peaks of the target spectral curve. The overall shift reflects the overall level of position shift of the absorption peaks of the target spectral curve. The larger the overall shift, the greater the overall degree of position shift of each absorption peak on the target spectral curve, which provides a data basis for the subsequent calculation of the compensation coefficient of each absorption peak of the target spectral curve.

[0083] Preferably, in one embodiment of the present invention, the method for obtaining the overall deviation of the target spectrum curve specifically includes:

[0084] The average value of the position shifts of all absorption peaks of the target spectral curve is taken as the overall shift of the target spectral curve.

[0085] As an example, in one embodiment of the present invention, the expression of the overall deviation of the target spectrum curve may be specifically, for example, as follows:

[0086]

[0087] in, Indicates the overall deviation of the target spectral curve; Indicates the number of absorption peaks of the target spectrum curve; The target spectrum curve The position shift of the absorption peak.

[0088] At this point, the overall deviation of the target spectral curve is obtained.

[0089] Step S3: Obtain the compensation coefficient of the target absorption peak according to the difference in position parameters between the target absorption peak and each reference absorption peak, and the overall deviation of the target spectral curve; based on the compensation coefficient of each absorption peak of the target spectral curve, adjust the position of each absorption peak of the target spectral curve to obtain an adjusted target spectral curve.

[0090] However, different Ganoderma products may have different ingredients. This is because Ganoderma is a multi-species fungus, and different varieties of Ganoderma have different genetic compositions, which will affect their chemical composition and molecular structure. For example, some varieties may contain more polysaccharides, triterpenoids or other active ingredients. The differences in these ingredients will be reflected in the infrared spectrum, resulting in differences in spectral data. Therefore, it is necessary to compensate for the positional offset based on the positional distribution characteristics of each absorption peak, so as to more accurately represent the distribution of ingredients.

[0091] In infrared absorption spectra, when an absorption peak shift occurs, the position of the shifted absorption peak in the spectrum will change significantly. For example, an absorption peak originally located in a certain wavelength range may shift to another wavelength range. This position change is usually caused by changes in the internal molecular vibration mode of Ganoderma lucidum or the influence of external environment such as temperature and pressure. Therefore, the embodiment of the present invention first analyzes the difference in position parameters between the target absorption peak and each reference absorption peak, and at the same time combines the overall shift of the target spectrum curve, and reflects the degree of adjustment of the target absorption peak position through the obtained compensation coefficient. The position of the target absorption peak can be adjusted and corrected based on the compensation coefficient to improve the accuracy of the spectral data, thereby improving the accuracy of the subsequent identification of Ganoderma lucidum components of different qualities.

[0092] Preferably, in one embodiment of the present invention, the method for obtaining the compensation coefficient of the target absorption peak specifically includes:

[0093] First, any reference spectral curve is taken as the reference spectral curve to be measured, and the absolute value of the difference between the position parameter of the target absorption peak and the position parameter of the target absorption peak in the reference spectral curve to be measured is taken as the initial position difference value of the target absorption peak with respect to the reference spectral curve to be measured. The larger the initial position difference value is, the greater the position difference between the target absorption peak and the reference absorption peak of the reference spectral curve to be measured.

[0094] The same method can be used to obtain all initial position difference values ​​of each absorption peak of the target spectral curve relative to the reference spectral curve to be measured, and then the average value of all initial position difference values ​​of all absorption peaks of the target spectral curve relative to the reference spectral curve to be measured is taken as the overall position difference value of the reference spectral curve to be measured. The larger the overall position difference value, the greater the overall difference in the position of the absorption peaks in the same column between the target spectral curve and the reference spectral curve to be measured.

[0095] The initial position difference value of the target absorption peak with respect to the reference spectral curve to be measured is taken as the numerator, the overall position difference value of the reference spectral curve to be measured is taken as the denominator, and the comparison value is normalized to obtain the initial deviation parameter of the target absorption peak with respect to the reference spectral curve to be measured. The larger the initial deviation parameter is, the larger the position difference between the target absorption peak and the reference absorption peak of the reference spectral curve to be measured is.

[0096] The same method can be used to obtain the initial deviation parameters of the target absorption peak with respect to each reference spectral curve, and then the product of the average value of the initial deviation parameters of the target absorption peak with respect to all reference spectral curves and the overall deviation of the target spectral curve is used as the compensation coefficient of the target absorption peak.

[0097] As an example, in one embodiment of the present invention, the expression of the compensation coefficient of the target absorption peak may be specifically, for example, as follows:

[0098]

[0099]

[0100] in, Indicates the compensation coefficient of the target absorption peak; Indicates the overall deviation of the target spectral curve; Indicates the target absorption peak about The initial position difference value of the reference spectral curve; The number of reference spectral curves representing the target spectral curve; Represents the position parameter of the target absorption peak; Indicates that the target absorption peak is at The position parameters of the reference absorption peak of a reference spectrum curve; Indicates the target absorption peak about The initial position difference value of the reference spectral curve; The target spectrum curve The position parameters of the absorption peaks; The target spectrum curve The absorption peak is The position parameters of the reference absorption peak of a reference spectrum curve; The target spectrum curve The absorption peak is about The initial position difference of the reference spectral curves; Indicates the number of absorption peaks of the target spectrum curve; represents the normalization function; Indicates The overall position difference value of the reference spectral curve.

[0101] The compensation coefficient of each absorption peak of the target spectral curve can be obtained by the same method as above, and then based on the compensation coefficient of each absorption peak of the target spectral curve, the position of each absorption peak of the target spectral curve can be adjusted to obtain the adjusted target spectral curve, thereby reducing the interference of absorption peak offset in spectral data and improving the accuracy of subsequent identification of Ganoderma lucidum components of different qualities.

[0102] Preferably, in one embodiment of the present invention, the method for acquiring the adjusted target spectrum curve specifically includes:

[0103] Firstly, the product value of the compensation coefficient and the position parameter of each absorption peak of the target spectral curve is used as the adjustment position parameter of each absorption peak of the target spectral curve. The adjustment position parameter can be considered as the new wavelength corresponding to the maximum value point of each absorption peak of the target spectral curve. The difference between the adjustment position parameter and the position parameter of each absorption peak of the target spectral curve is used as the position adjustment amount of each absorption peak of the target spectral curve. The position adjustment amount can be considered as the direction and distance that each absorption peak needs to move.

[0104] Then, any absorption peak of the target spectrum curve is used as the absorption peak to be adjusted. If the position adjustment amount of the absorption peak to be adjusted is greater than the value 0, the absorption peak to be adjusted is moved to the right, wherein the moving distance is the absolute value of the position adjustment amount of the absorption peak to be adjusted.

[0105] If the position adjustment amount of the absorption peak to be adjusted is less than a value of 0, the absorption peak to be adjusted is moved to the left, wherein the moving distance is the absolute value of the position adjustment amount of the absorption peak to be adjusted.

[0106] If the position adjustment amount of the absorption peak to be adjusted is equal to a value of 0, the absorption peak to be adjusted will not be moved.

[0107] Then, all absorption peaks of the target spectrum curve are traversed, and each absorption peak is moved to obtain an adjusted target spectrum curve.

[0108] The same method as above can be used to adjust the shift phenomenon of the absorption peak of the spectrum curve of each Ganoderma lucidum sample.

[0109] Step S4: Based on the adjusted target spectrum curve, the components of the Ganoderma lucidum sample corresponding to the target spectrum curve are identified.

[0110] The positions of the absorption peaks of the adjusted target spectral curve are corrected, reducing the influence of the absorption peak shift on the spectral analysis. Based on the adjusted target spectral curve, the components of the Ganoderma lucidum sample corresponding to the target spectral curve can be identified, thereby improving the accuracy of identifying the components of Ganoderma lucidum of different qualities.

[0111] Preferably, in one embodiment of the present invention, the method for identifying the components of the ganoderma lucidum sample corresponding to the target spectrum curve specifically includes:

[0112] The database contains a large number of standard infrared absorption spectrum curves of known compounds, so the adjusted target spectrum curve can be compared with the standard infrared absorption spectrum curves in the database to identify the components of the Ganoderma lucidum sample corresponding to the target spectrum curve.

[0113] The same method as above can be used to accurately identify the ingredients of each Ganoderma lucidum sample.

[0114] An embodiment of the present invention provides an intelligent identification device for Ganoderma lucidum of different qualities based on infrared spectroscopy, the device comprising a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, the method described in steps S1 to S4 can be implemented.

[0115] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent identification method for different qualities of Ganoderma lucidum based on infrared spectroscopy, characterized in that: The method comprises: Obtaining infrared absorption spectra of different ganoderma samples, wherein the infrared absorption spectra include spectrum curves of different ganoderma samples, and the spectrum curves include absorbances at different wavelengths; The spectral curve of any Ganoderma lucidum sample is taken as the target spectral curve, the wavelength of each maximum point on the target spectral curve is taken as the maximum wavelength, and the absorption peak of the target spectral curve is obtained according to the difference between the absorbance of each wavelength in the preset neighborhood of each maximum wavelength and the absorbance of each maximum wavelength; the wavelength of the maximum point of each absorption peak is taken as the position parameter of each absorption peak, any absorption peak of the target spectral curve is taken as the target absorption peak, and other spectral curves except the target spectral curve are taken as reference spectral curves, and according to the difference in the position parameters between the target absorption peak and each absorption peak of the reference spectral curve, the reference absorption peak of the target absorption peak is selected from the absorption peaks of each reference spectral curve; according to the position parameter of the target absorption peak and the distribution of the position parameters of all reference absorption peaks, the position deviation of the target absorption peak is obtained; according to the position deviation of all absorption peaks of the target spectral curve, the overall deviation of the target spectral curve is obtained; According to the difference of the position parameters between the target absorption peak and each reference absorption peak, and the overall deviation of the target spectrum curve, a compensation coefficient of the target absorption peak is obtained; based on the compensation coefficient of each absorption peak of the target spectrum curve, the position of each absorption peak of the target spectrum curve is adjusted to obtain an adjusted target spectrum curve; Based on the adjusted target spectral curve, identifying the components of the Ganoderma lucidum sample corresponding to the target spectral curve; The absorption peak of the target spectrum curve is obtained as follows: Taking any maximum wavelength of the target spectrum curve as the target maximum wavelength, and taking the absolute value of the difference between the absorbance of each wavelength in a preset neighborhood of the target maximum wavelength and the absorbance of the target maximum wavelength as the absorbance difference value of each wavelength in the preset neighborhood; Taking the average value of the absorbance difference values ​​between all wavelengths in the preset neighborhood and the target maximum wavelength as the overall absorbance difference parameter of the preset neighborhood; Normalizing the absolute value of the difference between the absorbance difference value of each wavelength in the preset neighborhood and the overall absorbance difference parameter of the preset neighborhood to obtain a difference evaluation value of each wavelength in the preset neighborhood; Based on the difference evaluation value of each wavelength in a preset neighborhood of the target maximum wavelength, obtaining an absorption peak of the target spectrum curve at the target maximum wavelength; The step of obtaining the absorption peak of the target spectrum curve at the target maximum wavelength comprises: In a preset neighborhood of the target maximum wavelength, the wavelength whose difference evaluation value is less than a preset difference threshold is used as the absorption peak wavelength in the preset neighborhood; The portion of the target spectrum curve between the minimum value of the absorption peak wavelength and the maximum value of the absorption peak wavelength in the preset neighborhood of the target maximum wavelength is taken as the absorption peak of the target spectrum curve at the target maximum wavelength; The reference absorption peak of the target absorption peak selected from the absorption peaks of each reference spectrum curve comprises: Taking any reference spectrum curve as a target reference spectrum curve, and taking the absolute value of the difference between the target absorption peak and each absorption peak of the target reference spectrum curve as the distance parameter between the target absorption peak and each absorption peak of the target reference spectrum curve; On the target reference spectrum curve, the absorption peak corresponding to the minimum value of the distance parameter is used as the reference absorption peak of the target absorption peak; The obtaining of the position deviation of the target absorption peak comprises: Taking the average value of the position parameters of all reference absorption peaks of the target absorption peak as the overall reference position parameter of the target absorption peak; The standard deviation of the position parameters of all reference absorption peaks of the target absorption peak is used as the reference position dispersion of the target absorption peak; The absolute value of the difference between the position parameter of the target absorption peak and the overall reference position parameter is used as the shift coefficient of the target absorption peak, and the sum of the shift coefficient of the target absorption peak and the reference position discreteness is used as the position shift degree of the target absorption peak; The overall deviation of the target spectral curve is obtained by: Taking the average value of the position shifts of all absorption peaks of the target spectrum curve as the overall shift of the target spectrum curve; The compensation coefficient for obtaining the target absorption peak includes: Taking any reference spectrum curve as the reference spectrum curve to be measured; The absolute value of the difference between the position parameter of the target absorption peak and the position parameter of the reference absorption peak of the reference spectrum curve to be measured is used as the initial position difference value of the target absorption peak with respect to the reference spectrum curve to be measured; Taking the average of all the initial position difference values ​​of all the absorption peaks of the target spectrum curve with respect to the reference spectrum curve to be measured as the overall position difference value of the reference spectrum curve to be measured; The initial position difference value of the target absorption peak with respect to the reference spectrum curve to be measured is used as the numerator, the overall position difference value of the reference spectrum curve to be measured is used as the denominator, and the comparison value is normalized to obtain the initial deviation parameter of the target absorption peak with respect to the reference spectrum curve to be measured; Taking the product of the average value of the initial deviation parameters of the target absorption peak with respect to all reference spectral curves and the overall deviation of the target spectral curve as the compensation coefficient of the target absorption peak; The obtaining of the adjusted target spectrum curve comprises: Using the product value of the compensation coefficient and the position parameter of each absorption peak of the target spectrum curve as the adjustment position parameter of each absorption peak of the target spectrum curve, and using the difference between the adjustment position parameter and the position parameter of each absorption peak of the target spectrum curve as the position adjustment amount of each absorption peak of the target spectrum curve; Any absorption peak of the target spectrum curve is used as the absorption peak to be adjusted. If the position adjustment amount of the absorption peak to be adjusted is greater than a value of 0, the absorption peak to be adjusted is moved to the right, wherein the moving distance is the absolute value of the position adjustment amount of the absorption peak to be adjusted; If the position adjustment amount of the absorption peak to be adjusted is less than the value 0, the absorption peak to be adjusted is moved to the left, wherein the moving distance is the absolute value of the position adjustment amount of the absorption peak to be adjusted; If the position adjustment amount of the absorption peak to be adjusted is equal to the value 0, the absorption peak to be adjusted will not be moved; All absorption peaks of the target spectrum curve are traversed, and each absorption peak is moved to obtain an adjusted target spectrum curve.

2. The intelligent identification method of Ganoderma lucidum of different qualities based on infrared spectroscopy according to claim 1, characterized in that: The identifying of the components of the ganoderma lucidum sample corresponding to the target spectrum curve comprises: The adjusted target spectrum curve is compared with the standard infrared absorption spectrum curve in the database to identify the components of the Ganoderma lucidum sample corresponding to the target spectrum curve.

3. An intelligent identification device for different qualities of Ganoderma lucidum based on infrared spectroscopy, the device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

Images