Adaptive analysis method, system, equipment and medium for multi-material component detection

Abstract

The present invention discloses an adaptive analysis method, system, equipment and medium for multi-material component detection. The method obtains spectral information of the material to be tested, determines the type of the material to be tested according to the spectral information of the material to be tested and the material characteristic spectral library, matches the corresponding quantitative analysis model in the quantitative analysis model library according to the type of the material to be tested, so as to perform component detection of the material to be tested. The adaptive analysis method for multi-material component detection of the present invention can be applied to the multi-material alternating online scene at the industrial site, and the online detection results of the multi-material components can be obtained without manual operation. Compared with the existing method of manual sampling and then offline laboratory testing, it has the characteristics of high real-time performance and accurate results, and can truly reflect the current status of the material.

Description

Technical Field

[0001] The present invention relates to the technical field of material component detection, and in particular to an adaptive analysis method, system, equipment and medium for multi-material component detection. Background Art

[0002] The material composition of industries such as metallurgy is the core parameter of process control and the evaluation index of product quality. Composition detection plays a very important role in various technical and economic indicators such as the smelting degree of smelting products, the quality of smelting products, and the recovery rate of metals. Its online real-time detection is one of the difficult problems in the intelligent improvement and upgrading of smelting. At present, the material composition detection in the smelting process mostly adopts manual sampling + offline laboratory detection. There are problems such as insufficient real-time performance, insufficient reliability, insufficient guidance, and insufficient safety. It is not conducive to the real-time monitoring, fine control and process improvement of material composition, and cannot support the intelligent upgrading of corresponding process nodes. The composition analyzer based on Laser Induced Breakdown Spectroscopy (LIBS) can detect the composition of process materials. It has the characteristics of no sampling, no sample preparation, no contact, and no radiation. It helps to realize closed-loop control based on real-time composition guidance process control, thereby realizing precise process control, optimizing process connection efficiency, and supporting intelligent construction.

[0003] In the application scenarios of LIBS technology in industrial sites, it is often necessary to detect multiple materials at the same application point, such as the steel industry, where the same belt alternately transports different types of solid materials such as flux and mixed ore, or where the dragon ditch at the iron outlet of a large blast furnace alternately flows out different types of molten materials such as molten iron and slag. In this case, a fixed single quantitative analysis model cannot be applied on site, and the manual switching model method requires manual confirmation of the type of online samples in advance, which will increase the intensity of manual labor and is difficult to apply in practice on industrial sites. Summary of the invention

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide an adaptive analysis method, system, equipment and medium for multi-material component detection, which is used to solve the technical problems in the prior art that a fixed single quantitative analysis model cannot be applied on site and manual switching of models will increase the intensity of manual labor.

[0005] To achieve the above objectives and other related objectives, the present invention provides an adaptive analysis method for multi-material component detection, which includes:

[0006] Obtain spectral information of the material to be tested;

[0007] Determine the type of the material to be tested according to the spectral information of the material to be tested and the material characteristic spectral library, wherein the material characteristic spectral library includes spectral information of different types of material samples in a preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are all lower than a first threshold value and includes all characteristic elements of the different types of material samples;

[0008] According to the type of the material to be tested, a corresponding material analysis model is matched in a material analysis model library to perform component detection on the material to be tested, wherein the material analysis model library includes material analysis models corresponding to different types of material samples.

[0009] Based on the same inventive concept, the present invention also provides an adaptive analysis system for multi-material component detection, which comprises:

[0010] Distance measurement module, used to measure the distance between the material to be tested and the spectrometer;

[0011] A motion control module, used for adjusting the focal length of the spectrometer according to the result of the distance measurement module;

[0012] A laser module, using laser pulses to generate a plasma spectrum on the surface of the material to be tested;

[0013] A spectrum acquisition module, used to obtain spectrum information of the material to be tested;

[0014] A model selection module, used to determine the type of the material to be tested based on the spectral information of the material to be tested and a material characteristic spectral library, wherein the material characteristic spectral library includes spectral information of different types of material samples in a preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are all lower than a first threshold value and include all characteristic elements of the different types of material samples; matching a corresponding material analysis model in a material analysis model library according to the type of the material to be tested, wherein the material analysis model library includes material analysis models corresponding to the different types of material samples;

[0015] The quantitative analysis module is used to detect the composition of the material to be tested according to the corresponding quantitative analysis model.

[0016] Based on the same inventive concept, the present invention also provides an electronic device, comprising:

[0017] one or more processors;

[0018] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the electronic device implements the adaptive analysis method for multi-material component detection as described above.

[0019] Based on the same inventive concept, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the adaptive analysis method for multi-material component detection as described above.

[0020] As described above, the adaptive analysis method for multi-material component detection provided by the present invention can be applied to the online scene of multiple materials alternating in industrial sites, by obtaining the spectral information of the material to be tested, and determining the type of the material to be tested according to the spectral information of the material to be tested and the material characteristic spectral library, and matching the corresponding material analysis model in the material analysis model library according to the type of the material to be tested, so as to perform component detection of the material to be tested. The adaptive analysis method for multi-material component detection of the present invention can perform adaptive LIBS quantitative analysis according to the types of different materials, and can obtain the online detection results of multi-material components without manually switching models. Compared with the existing manual sampling + offline laboratory detection method, it has the characteristics of strong real-time performance and high accuracy. In addition, since there is no need to manually confirm the type of material to be tested, the intensity of manual labor is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic flow chart of an adaptive analysis method for multi-material component detection provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of an application scenario of an adaptive analysis method for multi-material component detection provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a system flow of an adaptive analysis method for multi-material component detection provided by an embodiment of the present invention;

[0024] Figure 4 A first measured spectrum diagram of an adaptive analysis method for multi-material component detection provided by an embodiment of the present invention;

[0025] Figure 5 A second measured spectrum diagram of an adaptive analysis method for multi-material component detection provided by an embodiment of the present invention;

[0026] Figure 6 A schematic diagram of the structure of an adaptive analysis system for multi-material component detection provided by an embodiment of the present invention;

[0027] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0029] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0030] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0031] The present invention provides an adaptive analysis method for multi-material component detection, which can be applied to the online scene of multiple materials alternating in industrial sites, and can perform adaptive LIBS quantitative analysis according to the types of different materials. The online detection results of multi-material components can be obtained without manually switching models. Compared with the existing manual sampling + offline laboratory detection method, it has the characteristics of strong real-time performance and high accuracy. In addition, since there is no need to manually confirm the type of material to be tested, the labor intensity is reduced. Please refer to Figure 1 As shown, the adaptive analysis method for multi-material component detection includes the following steps:

[0032] S100: Acquire spectrum information of the material to be tested;

[0033] S200: determining the type of the material to be tested according to the spectral information of the material to be tested and a material characteristic spectral library, wherein the material characteristic spectral library includes spectral information of different types of material samples within a preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are all lower than a first threshold and includes all characteristic elements of the different types of material samples;

[0034] S300: matching a corresponding material analysis model in a material analysis model library according to the type of the material to be tested, so as to detect the composition of the material to be tested, wherein the material analysis model library includes material analysis models corresponding to different types of material samples.

[0035] First, before executing step S100, in other words, before performing online detection of the material components to be tested, it is necessary to establish a material characteristic spectrum library and a material analysis model library. The establishment of the material characteristic spectrum library includes the following steps:

[0036] S010: Obtaining spectral information of different types of material samples;

[0037] S020: Obtaining wavelengths of all characteristic elements corresponding to different types of material samples according to a standard spectral line database;

[0038] S030: comparing the spectral correlation of the spectral information of different types of material samples in sections to obtain multiple groups of spectral correlation coefficients;

[0039] S040: selecting a spectral band whose spectral correlation coefficients between different types of material samples are all lower than a first threshold and includes all characteristic elements of different types of material samples as a preferred band;

[0040] S050: Acquire spectral information of different types of material samples within a preferred wavelength band to form a material characteristic spectral library.

[0041] It should be noted that, in step S030, the segmented comparison of spectral correlations of spectral information of different types of material samples to obtain multiple groups of spectral correlation coefficients further includes the following steps:

[0042] S031: Divide the full spectrum wavelength of different types of material samples into a plurality of equally spaced band intervals;

[0043] S032: performing pairwise correlation analysis on the spectral information of different types of material samples in each band interval to obtain multiple groups of spectral correlation coefficients corresponding to each band interval.

[0044] Specifically, first, the laser uses laser pulses to generate plasma on the surface of the material sample, and the spectrometer collects spectra of different types of material samples. It should be noted that the LIBS technology irradiates the surface of the material sample with high-power density laser pulses, causing the surface of the material sample to evaporate, gasify, and ionize rapidly to form a plasma. The plasma will emit a spectrum of specific wavelengths during the cooling process, and the spectrum contains characteristic information of the elements in the material sample. Then, based on the standard spectral line database (NIST database of the National Institute of Standards and Technology of the United States), combined with the known elements of the on-site materials, all characteristic element wavelengths corresponding to different types of material samples are obtained. Next, the spectral information of all material samples collected in step S010 is segmented and compared for spectral correlation. For example, if there are N types of material samples, the full spectrum wavelength range of the N types of material samples is M0~M1, and the segment spacing is set to Len, then the full spectrum wavelength is divided into (M1-M0) / Len Band intervals, among which, Next, the spectra of different types of material samples are subjected to pairwise correlation analysis in each band interval to obtain multiple groups of spectral correlation coefficients corresponding to each band interval. In this embodiment, the Peason correlation coefficient formula is used to calculate the spectral correlation coefficients between different types of materials:

[0045]

[0046] Among them, x and y are the normalized intensity arrays of the same characteristic peaks in the spectra of the two groups of material samples. , is the array mean of the normalized intensity of the same characteristic peaks in the spectra of the two groups of material samples, and r is the spectral correlation coefficient between the two groups of material samples. It is worth noting that the closer the absolute value of the r value is to 1, the stronger the linear relationship between the spectra of the two materials is, and the closer the r value is to 0, the weaker the linear relationship is.

[0047] Finally, the spectral bands whose spectral correlation coefficients between the different types of material samples are all lower than the first threshold and include all the characteristic elements of the different types of material samples are selected as the preferred bands, and the spectral information of the different types of material samples in the preferred bands is obtained and saved to form a material characteristic spectral library.

[0048] The establishment of the material analysis model library includes: preprocessing, feature extraction, data integration and model training of spectra of different types of material samples respectively to form a material analysis model library.

[0049] Specifically, after the spectral information of all material samples is collected, preprocessing, feature extraction, data integration and model training are performed to save the quantitative analysis model corresponding to all material samples. If the internal standard method is used, the formula of the quantitative analysis model is:

[0050]

[0051] The horizontal axis is the ratio of the spectral line intensity of the measured element and the internal standard element I C / I R The vertical axis is the reference concentration C obtained by other assay methods. C , K is the slope of the linear fitting curve, and B is the intercept of the linear fitting curve.

[0052] If the external standard method is used, the formula of the quantitative analysis model is:

[0053]

[0054] Among them, the horizontal axis is the spectral line intensity I of the measured element C The vertical axis is the reference concentration C obtained by other assay methods. C , K is the slope of the linear fitting curve, and B is the intercept of the linear fitting curve.

[0055] Next, after the material characteristic spectrum library and the material analysis model library are established, step S100 is executed to obtain the spectrum information of the material to be tested.

[0056] The step of obtaining the spectral information of the material to be tested further comprises the following steps:

[0057] S110: Acquire distance information between the material to be tested and the spectrometer;

[0058] S120: adjusting the focal length of the spectrometer according to the distance information, and collecting the spectrum of the material to be tested by using the spectrometer to obtain the spectrum information of the material to be tested.

[0059] For details, please refer to Figure 2 As shown, the high-energy pulse laser emitted by the laser is focused on the surface of the sample to be tested through the laser focusing lens to ablate the sample to generate plasma, and then the light signal emitted by the plasma is coupled to the optical fiber through the collection optical path and transmitted to the spectral spectrometer and detection device to obtain the spectral signal of the sample to be tested containing the elemental composition information, and the LIBS spectral data collection of the sample to be tested is completed. It should be noted that when the material to be tested is detected online, the distance information between the material to be tested and the spectrometer is obtained through the distance measurement module, and the focal length of the spectrometer is adjusted according to the distance information through the motion control module, and then the spectrum of the material to be tested is collected.

[0060] Next, step S200 is performed to determine the type of the material to be tested based on the spectral information of the material to be tested and a material characteristic spectral library, wherein the material characteristic spectral library includes spectral information of different types of material samples within a preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are all lower than a first threshold and include all characteristic elements of the different types of material samples;

[0061] It should be noted that the method of determining the type of the material to be tested based on the spectral information of the material to be tested and the material characteristic spectral library further includes the following steps:

[0062] S210: intercepting the spectrum information of the material to be tested within the preferred wavelength band;

[0063] S220: Compare the spectral information within the preferred wavelength band with the spectral information of different types of materials in the material characteristic spectrum library in turn for spectral correlation, and determine the type of the material to be tested according to the comparison result.

[0064] It is worth noting that the step of sequentially comparing the spectral correlation of the spectral information within the preferred wavelength band with the spectral information of different types of materials in the material characteristic spectral library and determining the type of the material to be tested according to the comparison result further includes the following steps:

[0065] S221: sequentially determining whether the spectral correlation coefficients between the spectral information of the material to be tested within the preferred wavelength band and the spectral information of different types of materials in the characteristic spectral library are higher than a second threshold;

[0066] S222: If yes, determine that the type of the material to be tested is the corresponding material type in the matched characteristic spectrum library; if no, return to step S221.

[0067] Specifically, in this embodiment, the Peason correlation coefficient formula is used to calculate the spectral correlation between the spectrum of the material to be tested in the preferred band and the spectrum of each material in the material characteristic spectrum library in the preferred band. When the Peason correlation coefficient is higher than the second threshold, it is determined to be the current known material.

[0068] Finally, step S300 is executed to match the corresponding quantitative analysis model in the quantitative analysis model library according to the type of the material to be tested, so as to detect the composition of the material to be tested, wherein the quantitative analysis model library includes quantitative analysis models corresponding to different types of material samples. The spectrum of the material to be tested is preprocessed, feature extracted, and data integrated, and the quantitative analysis of the elements contained in the material to be tested is realized through the spectral data processing method according to the corresponding quantitative analysis model.

[0069] In summary, please refer to Figure 3As shown, the present invention provides an adaptive analysis method for multi-material component detection, which obtains spectral information of the material to be tested, determines the type of the material to be tested based on the spectral information of the material to be tested and the material characteristic spectral library, and matches the corresponding quantitative analysis model in the quantitative analysis model library according to the type of the material to be tested, so as to perform component detection of the material to be tested. The adaptive analysis method for multi-material component detection of the present invention can be applied to scenarios where multiple materials are alternately transported online in industrial sites. For example, it can be applied to scenarios where multiple materials are alternately transported in belts or dragon ditches, and adaptive LIBS quantitative analysis can be performed to obtain online detection results of the components of multiple materials without manual operation. Compared with the existing manual sampling + offline laboratory testing method, the adaptive analysis method for multi-material component detection of the present invention has the characteristics of strong real-time performance and high accuracy, and can truly reflect the current status of the material. Please refer to Figure 4 and Figure 5 As shown, Figure 4 and Figure 5 The first measured spectra and the second measured spectra of various materials are shown respectively. It can be seen from the figures that different types of materials have different elemental compositions, so the corresponding spectral characteristics are more clearly distinguished. If the same material model is used for quantitative analysis, the deviation will be significant. Therefore, it is necessary to adopt the adaptive LIBS quantitative analysis method of the present invention to realize online detection of various material components.

[0070] Based on the same inventive concept, please refer to Figure 6 As shown, another embodiment of the present invention further provides an adaptive analysis system 11 for detecting multiple material components, which includes:

[0071] The distance measuring module 111 is used to measure the distance between the material to be measured and the spectrometer;

[0072] A motion control module 112, configured to adjust the focal length of the spectrometer according to the result of the distance measurement module 111;

[0073] The laser module 113 generates a plasma spectrum on the surface of the material to be tested by using laser pulses;

[0074] A spectrum acquisition module 114 is used to obtain spectrum information of the material to be tested;

[0075] The model selection module 115 is used to determine the type of the material to be tested based on the spectral information of the material to be tested and the material characteristic spectral library, wherein the material characteristic spectral library includes spectral information of different types of material samples in a preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are lower than a first threshold and include all characteristic elements of the different types of material samples; according to the type of the material to be tested, the corresponding quantitative analysis model is matched in the quantitative analysis model library, wherein the quantitative analysis model library includes quantitative analysis models corresponding to the different types of material samples;

[0076] The quantitative analysis module 116 is used to detect the components of the material to be tested according to the corresponding quantitative analysis model.

[0077] It should be noted that the adaptive analysis system 11 for detecting multiple material components includes the adaptive analysis method for detecting multiple material components described in any of the above embodiments. Since the adaptive analysis system 11 for detecting multiple material components provided in this embodiment belongs to the same inventive concept as the adaptive analysis method for detecting multiple material components provided in any of the above embodiments, it has at least the same beneficial effects as the adaptive analysis method for detecting multiple material components, and will not be described in detail here.

[0078] Based on the same inventive concept, please refer to Figure 7 As shown, another embodiment of the present invention further provides an electronic device 1, which may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as an adaptive analysis program for multi-material component detection.

[0079] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 12 can also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code for adaptive analysis of multi-material component detection, etc., but also can be used to temporarily store data that has been output or is to be output.

[0080] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect various components of the entire electronic device 1, and executes or executes programs or modules (such as adaptive analysis programs for multi-material component detection, etc.) stored in the memory 12, and calls data stored in the memory 12 to execute various functions of the electronic device 1 and process data.

[0081] The processor 13 executes the operating system and various installed applications of the electronic device 1. The processor 13 executes the applications to implement the steps in the above-mentioned adaptive analysis method for multi-material component detection.

[0082] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a ranging module 111, a motion control module 112, a laser module 113, a spectrum acquisition module 114, a model selection module 115, and a quantitative analysis module 116.

[0083] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium, and the computer-readable storage medium can be non-volatile or volatile. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of the adaptive analysis method for multi-material component detection described in various embodiments of the present application.

[0084] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An adaptive analysis method for multi-material component detection, characterized in that: include: Obtain spectral information of the material to be tested collected using LIBS technology; Intercepting the spectrum information of the material to be tested within the preferred wavelength band; Comparing the spectral information within the preferred band with the spectral information of different types of materials in the material characteristic spectral library in turn for spectral correlation, and determining the type of the material to be tested according to the comparison result, wherein the material characteristic spectral library includes spectral information of different types of material samples within the preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are all lower than a first threshold value and includes all characteristic elements of the different types of material samples; According to the type of the material to be tested, a corresponding material analysis model is matched in a material analysis model library to perform component detection on the material to be tested, wherein the material analysis model library includes material analysis models corresponding to different types of material samples.

2. The adaptive analysis method for multi-material component detection according to claim 1, characterized in that: The step of obtaining the spectral information of the material to be tested includes: Obtaining distance information between the material to be tested and the spectrometer; The focal length of the spectrometer is adjusted according to the distance information, and the spectrum of the material to be tested is collected by using the spectrometer to obtain the spectrum information of the material to be tested.

3. The adaptive analysis method for multi-material component detection according to claim 1, characterized in that: The establishment of the material characteristic spectrum library includes: Obtaining spectral information of different types of material samples; Acquire the wavelengths of all characteristic elements corresponding to different types of material samples according to the standard spectral line database; Comparing the spectral correlation of the spectral information of different types of material samples in sections to obtain multiple groups of spectral correlation coefficients; Selecting a spectral band whose spectral correlation coefficients between different types of material samples are all lower than a first threshold and includes all characteristic elements of different types of material samples as a preferred band; The spectral information of different types of material samples in the preferred wavelength band is obtained to form a material characteristic spectral library.

4. The adaptive analysis method for multi-material component detection according to claim 3, characterized in that: The segmented comparison of spectral correlations of spectral information of different types of material samples to obtain multiple groups of spectral correlation coefficients includes: Dividing the full spectrum wavelengths of different types of material samples into a plurality of equally spaced band intervals; In each band interval, pairwise correlation analysis is performed on the spectral information of different types of material samples to obtain multiple groups of spectral correlation coefficients corresponding to each band interval.

5. The adaptive analysis method for multi-material component detection according to claim 1, characterized in that: The establishment of the material analysis model library includes: The spectra of different types of material samples are preprocessed, feature extracted, data integrated and model trained respectively to form a material quantitative analysis model library.

6. The adaptive analysis method for multi-material component detection according to claim 1, characterized in that: The step of sequentially comparing the spectral correlation of the spectral information in the preferred wavelength band with the spectral information of different types of materials in the material characteristic spectral library, and determining the type of the material to be tested according to the comparison result comprises: sequentially determining whether the spectral correlation coefficients between the spectral information of the material to be tested within the preferred wavelength band and the spectral information of different types of materials in the characteristic spectral library are higher than a second threshold; If yes, it is determined that the type of the material to be tested is the corresponding material type in the matched characteristic spectrum library.

7. An adaptive analysis system for multi-material component detection, characterized in that: include: Distance measurement module, used to measure the distance between the material to be tested and the spectrometer; A motion control module, used for adjusting the focal length of the spectrometer according to the result of the distance measurement module; A laser module, using laser pulses to generate a plasma spectrum on the surface of the material to be tested; A spectrum acquisition module, used to obtain spectrum information of the material to be tested; A model selection module, used to determine the type of the material to be tested based on the spectral information of the material to be tested and a material characteristic spectral library, wherein the material characteristic spectral library includes spectral information of different types of material samples in a preferred band, and the preferred band refers to a spectral band in which the spectral correlation coefficients between the different types of material samples are lower than a first threshold and include all characteristic elements of the different types of material samples; matching a corresponding material analysis model in a material analysis model library according to the type of the material to be tested, wherein the material analysis model library includes material analysis models corresponding to the different types of material samples; The quantitative analysis module is used to detect the composition of the material to be tested according to the corresponding quantitative analysis model.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the adaptive analysis method for multi-material component detection as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the adaptive analysis method for multi-material component detection according to any one of claims 1 to 7.

Images