CN114596926A

CN114596926A - Steel grade identification method, laser-induced breakdown spectroscopy device and storage medium

Info

Publication number: CN114596926A
Application number: CN202210501654.7A
Authority: CN
Inventors: 潘从元; 汪浩; 贾军伟; 张兵
Original assignee: Hefei Gstar Intelligent Control Technical Co Ltd
Current assignee: Hefei Gstar Intelligent Control Technical Co Ltd
Priority date: 2022-05-10
Filing date: 2022-05-10
Publication date: 2022-06-07
Anticipated expiration: 2042-05-10
Also published as: CN114596926B

Abstract

The application discloses a steel grade identification method, a laser-induced breakdown spectroscopy device and a readable storage medium. The steel grade identification method comprises the following steps: acquiring original spectrum data of test point positions of different grades of steel samples based on a laser-induced breakdown technology, wherein the test point positions of each grade of steel sample are multiple; processing the original spectral data to obtain a training data set and a test data set; establishing a single element nesting model by utilizing a training data set; and inputting the test data set into a nested model for processing, and determining the grade of the steel sample according to the output result. By the laser-induced breakdown technology, the concentration difference of each element of the samples to be classified is fully utilized, a single element nested model is established, the steel samples are detected, sampling and sample preparation are not needed, the detection speed is high, and the steel grades are quickly identified.

Description

Steel grade identification method, laser-induced breakdown spectroscopy device and storage medium

Technical Field

The application relates to the technical field of spectral analysis, in particular to a steel grade identification method, a laser-induced breakdown spectroscopy device and a readable storage medium.

Background

The steel is used as an important basic raw material in a plurality of industries such as manufacturing industry, transportation industry, construction industry and the like, has large market demand, has various steel types, and is mainly classified according to purposes: the steel is used for construction and engineering, structural steel, tool steel, special performance steel, professional steel and the like, and the steel with different grades is suitable for different application scenes. Although the component compositions of the steel with different grades have certain differences, the steel is difficult to distinguish from the characteristics such as appearance and the like only by manual experience, and in addition, because the production processes and raw material sources of different manufacturers are different, even if the product with the same grade has different components and properties. In steel production and processing enterprises and complex process flows, the situation of steel grade confusion is inevitable due to more types of grades, and on an automatic production line, the traditional sampling and testing method has the defects of tedious sampling and long detection period and cannot meet the requirement of rapid detection.

Disclosure of Invention

The embodiment of the application provides a steel grade identification method, a laser-induced breakdown spectroscopy device and a readable storage medium.

The steel grade identification method provided by the embodiment of the application is characterized by comprising the following steps:

acquiring original spectrum data of test point positions of different grades of steel samples based on a laser-induced breakdown technology, wherein the test point positions of each grade of steel sample are multiple;

processing the original spectral data to obtain a training data set and a test data set;

establishing a single element nesting model by using the training data set;

and inputting the test data set into a nested model for processing, and determining the grade of the steel sample according to an output result.

In some embodiments, processing the raw spectral data and obtaining a training dataset and a test dataset comprises:

removing surface impurity layer spectral data in the original spectral data to obtain effective spectral data;

and processing the effective spectral data to obtain the training data set and the test data set.

In some embodiments, processing the effective spectral data and obtaining the training dataset and the test dataset comprises:

preprocessing the effective spectrum data to obtain processed spectrum data, wherein the preprocessing comprises at least one of background light removal and normalization;

and randomly selecting a plurality of processed spectral data as the training data set, and using the rest processed spectral data as the test data set, wherein the number of the training data sets is more than that of the test data sets.

In some embodiments, inputting the test data set into a nesting model for processing, and determining the grade of the steel sample according to the output result, comprises:

based on the test data set, dividing the different grades of steel samples into m grades of samples according to the concentration difference of a first preset single element, and dividing the samples with similar first preset single element concentration into n categories, wherein m and n are natural numbers and are more than 1;

in case m = n, in case the number of samples in each category is 1, determining the number of the steel sample according to the first predetermined single element.

in the case that m < n, in the case that the number samples in the category are more than 1, the category of which the number samples are more than 1 is taken as a re-classification category;

dividing the steel samples in the re-classified categories into M brand samples according to the concentration difference of a second preset single element, and dividing the samples with similar concentration of the second preset single element into N categories, wherein M, N is a natural number and is more than 1;

in case of M = N, in case of 1 brand sample in each category, determining the brand of the steel sample according to the second predetermined single element.

In some embodiments, the steel grade identification method comprises:

and in the case that N is less than M, the grade of the steel sample cannot be confirmed through the second predetermined single element.

In some embodiments, the steel grade identification method comprises:

and in the case that n is less than m, the grade of the steel sample cannot be confirmed through the first predetermined single element.

The laser-induced breakdown spectroscopy apparatus of an embodiment of the present application includes:

the sample table is used for bearing a steel sample;

the laser is used for emitting laser to the steel sample;

the spectrometer is used for receiving the laser reflected by the steel sample and comprises a processor, and the processor is used for realizing the steel grade identification method in any one of the above embodiments.

In some embodiments, the laser induced breakdown spectroscopy apparatus comprises an optical assembly disposed between the laser and the sample stage, the optical assembly configured to direct laser light emitted by the laser onto the steel sample.

The embodiment of the application provides a readable storage medium storing a computer program, and when the computer program is executed by one or more processors, the method for identifying the steel grade according to the embodiment is realized.

In the steel grade identification method, the laser-induced breakdown spectroscopy device and the readable storage medium in the embodiment of the application, the laser-induced breakdown technology is adopted, the concentration difference of each element of the samples to be classified is fully utilized, a single element nested model is established, the steel samples are detected, the sampling and the sample preparation are not needed, the detection speed is high, and the steel grade is quickly identified.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a schematic flow chart of a steel grade identification method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a laser induced breakdown spectroscopy apparatus according to an embodiment of the present application;

FIG. 3 is a spectrum of different grade steel samples according to embodiments of the present application;

FIG. 4 is a graph of features as a function of number of spectra for efficient line screening in accordance with an embodiment of the present application;

FIG. 5 is a schematic view of another flow chart of the steel grade identification method according to the embodiment of the present application;

FIG. 6 is another schematic flow chart of a steel grade identification method according to an embodiment of the present application;

FIG. 7 is a schematic view of another process of the steel grade identification method according to the embodiment of the present application;

FIG. 8 is a schematic view of another process of the steel grade identification method according to the embodiment of the present invention;

FIG. 9 is a schematic view of another process of the steel grade identification method according to the embodiment of the present invention;

fig. 10 is a schematic view of another process of the steel grade identification method according to the embodiment of the present invention.

Description of the main element symbols:

a laser induced breakdown spectroscopy device 100;

the device comprises a laser 1, a processor 11, an optical assembly 20, a beam expander 2, a reflector 3, a focusing lens 4, a sample stage 5, a collecting lens 6, an optical fiber 7 and a spectrometer 8.

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and are only for the purpose of explaining the present application and are not to be construed as limiting the present application.

In this application, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may comprise direct contact of the first and second features, or may comprise contact of the first and second features not directly but through another feature in between. Also, the first feature "on," "above" and "over" the second feature may include the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly under and obliquely below the second feature, or simply meaning that the first feature is at a lesser elevation than the second feature.

The following disclosure provides many different embodiments or examples for implementing different features of the application. To simplify the disclosure of the present application, the components and settings of a specific example are described below. Of course, they are merely examples and are not intended to limit the present application. Moreover, the present application may repeat reference numerals and/or reference letters in the various examples, which have been repeated for purposes of brevity and clarity and do not in themselves dictate a relationship between the various embodiments and/or configurations discussed. In addition, examples of various specific processes and materials are provided herein, but one of ordinary skill in the art may recognize the application of other processes and/or the use of other materials.

Referring to fig. 1, the method for identifying a steel grade according to the embodiment of the present application includes:

s10, acquiring original spectrum data of the test point locations of different grades of steel samples based on a laser-induced breakdown technology, wherein the test point location of each grade of steel sample is multiple;

s20, processing the original spectrum data to obtain a training data set and a test data set;

s30, establishing a single element nesting model by using the training data set;

and S40, inputting the test data set into the nested model for processing, and determining the grade of the steel sample according to the output result.

Referring to fig. 2, a laser-induced breakdown spectroscopy apparatus 100 according to an embodiment of the present disclosure includes a sample stage 5, a laser 1, and a spectrometer 8, where the sample stage 5 is configured to carry a steel sample, the laser 1 is configured to emit laser to the steel sample, the spectrometer 8 is configured to receive the laser reflected by the steel sample, the spectrometer 8 includes a processor 11, and the processor 11 is configured to implement the steel brand identification method according to the above embodiment. That is, the processor 11 may be configured to obtain, based on a laser-induced breakdown technology, original spectrum data of test point locations of different grades of steel samples, where the number of test point locations of each grade of steel sample is multiple; and for processing the raw spectral data and obtaining a training data set and a test data set; the method is also used for establishing a single element nesting model by utilizing the training data set; and the embedded model is used for inputting the test data set into the embedded model for processing, and determining the grade of the steel sample according to the output result.

In the steel grade identification method, the laser-induced breakdown spectroscopy device 100 and the readable storage medium according to the embodiment of the application, the laser-induced breakdown technology is adopted, the concentration difference of each element of the samples to be classified is fully utilized, a single element nested model is established, the steel samples are detected, the sampling and the sample preparation are not needed, the detection speed is high, and the steel grade is quickly identified.

Referring to fig. 2, in some embodiments, the laser induced breakdown spectroscopy apparatus 100 includes an optical assembly 20, the optical assembly 20 is disposed between the laser 1 and the sample stage 5, and the optical assembly 20 is used for guiding the laser emitted by the laser 1 onto the steel sample.

In this way, the laser 1 is used for generating laser light, and the optical assembly 20 can guide the laser light to the steel sample on the sample stage 5 to detect the steel sample. The optical assembly 20 can focus laser generated by the laser 1 and the like, and can avoid the problem that a steel sample is difficult to place on the sample stage 5 due to the fact that the laser 1 is too close to the sample stage 5.

Specifically, the optical assembly 20 may include a beam expander 2, a reflector 3, and a focusing lens 4, the beam expander 2 being connected to the laser 1 such that laser light generated by the laser 1 changes a laser beam diameter and a divergence angle when passing through the beam expander 2. The focusing lens 4 is arranged opposite to the sample stage 5, the reflector 3 is arranged between the beam expander 2 and the focusing lens 4, so that laser emitted from the beam expander 2 can pass through the reflector 3 and then irradiate towards the focusing lens 4, and the sample stage 5 can adjust the height of a steel sample, so that the focusing lens 4 can collect the laser and irradiate towards the sample stage 5. At the moment, a steel sample is arranged on the sample stage 5, laser irradiates a plurality of test point positions on the steel sample, high-energy pulse laser focuses on the surface of the steel sample to form plasma, and then spectral signals are collected through the collecting lens 6 and transmitted back to the spectrometer 8 through the optical fiber 7, so that spectral data of the steel sample are obtained. Please refer to fig. 3 and 4, in which fig. 3 is a spectrum diagram of different grades of steel samples detected by the spectrometer 8 of the present application, and fig. 4 is a graph of characteristic variation with the number of spectra during effective spectral line screening.

In the embodiment of the present application, the types of the spectrometer 8 and the laser 1 are not limited, for example, the laser 1 may be a YAG laser, and the spectrometer 8 may be a middle-step spectrometer, so as to meet various requirements.

For example, in step S10, 20 test sites may be randomly selected for each surface of each steel sample, and each test site may be subjected to 500 consecutive laser pulse strikes to obtain raw spectral data. Then, the original spectrum data is randomly selected to be a part of the original spectrum data as a training data set, and the rest is used as a testing data set through step S20. In one example, processor 11 may treat three fifths of the raw spectral data as a training data set and two fifths of the raw spectral data as a test data set. Therefore, the method can ensure that more training data sets are trained to establish the single element nested model in the step S30, and ensure the accuracy of the single element nested model. Finally, in step S40, the remaining test data sets are input into the nested model for processing, and the grade of the steel sample can be determined according to the output result. It should be noted that the single element nested model is a support vector machine model, and the optimal solution of the model can be obtained by combining the grid optimization C and gamma parameters, so as to ensure the accuracy of the model detection.

Referring to fig. 5, in some embodiments, processing raw spectral data and obtaining a training data set and a test data set (step S20) includes:

s21, removing the surface impurity layer spectrum data in the original spectrum data to obtain effective spectrum data;

s22, the valid spectral data is processed and a training dataset and a test dataset are obtained.

Referring to fig. 2, in some embodiments, the steps S21-S22 may be executed by the processor 11. That is, the processor 11 may be configured to remove the surface impurity layer spectrum data in the original spectrum data to obtain effective spectrum data; and for processing the effective spectral data and obtaining a training data set and a test data set.

Therefore, when the original spectrum data are acquired through the laser-induced breakdown technology, the surface of the steel sample is not required to be cleaned, only the spectral lines of the impurity layers are required to be removed, and the effective spectrum data are reserved. And processing the effective spectrum data to obtain a training data set and a test data set, so that the single element nested model can be trained according to the training data set, and the test data set can be input into the nested model to be processed to confirm the brand of the steel sample.

It can be understood that dust and other impurities with different thicknesses are often formed on the surface of the steel in the steel production and transportation processes, and the surface impurity layer spectral data in the original spectral data can be removed in step S21 to avoid the surface impurity layer spectral data from affecting the normal detection of the steel sample. The steel sample surface impurity layer and the steel sample spectral data are different, the surface impurity layer is firstly punctured along with the breakdown of the laser pulse from outside to inside, then the steel sample spectral data are collected, the spectrum tends to be stable at the moment, the original spectral data are intercepted, after the surface impurity layer spectral data are removed, the effective spectral data can be obtained, and then the step S22 is executed to randomly divide the effective spectral data into a training data set and a testing data set. Training the training data set to establish a single element nested model, inputting the testing data set into the nested model for processing, and determining the grade of the steel sample according to the output result.

Referring to fig. 6, in some embodiments, processing the effective spectral data to obtain a training data set and a test data set (step S22) includes:

s221, preprocessing the effective spectrum data to obtain processed spectrum data, wherein the preprocessing comprises at least one of background light removal and normalization;

s222, randomly selecting a plurality of processed spectral data as training data sets, and using the remaining processed spectral data as test data sets, wherein the number of the training data sets is more than that of the test data sets.

Referring to fig. 2, in some embodiments, the steps S221 to S222 may be executed by the processor 11. That is, the processor 11 may be configured to perform a preprocessing on the effective spectral data to obtain processed spectral data, where the preprocessing includes at least one of background light removal and normalization; and the spectrum data processing device is used for randomly selecting a plurality of processed spectrum data as training data sets, and using the rest processed spectrum data as test data sets, wherein the number of the training data sets is more than that of the test data sets.

Therefore, the processed spectrum data is obtained by removing the background light and carrying out normalization processing on the effective spectrum data, the reliability of the spectrum data can be ensured, and the precision of the training data set and the test data set is improved. The number of the training data sets is more than that of the testing data sets so as to ensure that a single element nested model is established according to the training data sets, the prediction precision is high, and the grade of the steel sample can be identified by detecting the testing data sets.

Specifically, in step S221, the preprocessing may be background light removal, or normalization, or background light removal and normalization may be performed simultaneously, and then step S222 is performed to establish a single element nested model and test the test data set to determine the grade of steel. In addition, the number of the training data sets is larger than that of the testing data sets, so that the training data sets can establish a single element nested model with higher precision.

Referring to fig. 7, in some embodiments, inputting a test data set into a nesting model for processing, and determining a grade of a steel sample according to an output result (step S40), includes:

s41, based on the test data set, dividing different grades of steel samples into m grades of samples according to the concentration difference of a first preset single element, and dividing samples with similar first preset single element concentration into n categories, wherein m and n are natural numbers and are larger than 1;

and S42, under the condition that m = n, under the condition that the number samples in each category are 1, determining the number of the steel sample according to the first predetermined single element.

Referring to fig. 2, in some embodiments, the steps S41-S42 may be executed by the processor 11. That is, the processor 11 may be configured to divide the different grades of steel samples into m grades of samples according to the first predetermined single element concentration difference based on the test data set, and divide the samples with similar first predetermined single element concentrations into n categories, where m and n are natural numbers and are greater than 1; and determining the grade of the steel sample according to the first predetermined single element in the case that the grade samples in each category are 1 in the case that m = n.

Thus, different grades and types of the steel samples are determined according to the concentration difference of the first predetermined single element, and when the m grades of the samples are equal to the n types of the samples, the steel samples with one grade in each type can be determined, so that the grades of the steel samples can be confirmed.

Specifically, after the processor 11 obtains the spectrum data and performs preprocessing to obtain the processed spectrum data, the processed spectrum data can be randomly divided into a training data set and a testing data set, a single element nesting model is established through the training data set, then the testing data set is input into the nesting model for processing, and then the steel sample can be divided into m brands of samples according to the concentration difference of single elements in the steel sample. And dividing the samples with the similar first predetermined single element concentration into n categories, wherein under the condition that m = n, under the condition that the grade samples in each category are 1, namely that the m grades and the n categories are in one-to-one correspondence, the grade of the steel sample can be determined according to the first predetermined single element.

Further, referring to fig. 8, in some embodiments, inputting the test data set into the nested model for processing, and determining the grade of the steel sample according to the output result (step S40), including:

s43, under the condition that n is less than m, and under the condition that the number samples in the category are more than 1, taking the category of which the number samples are more than 1 as a re-classification category;

s44, dividing the steel samples in the re-classification into M brands of samples according to the concentration difference of a second preset single element, and dividing the samples with similar concentration of the second preset single element into N classifications, wherein M, N is a natural number and is more than 1;

and S45, under the condition that M = N, under the condition that the number samples in each category are 1, determining the number of the steel sample according to a second predetermined single element.

Referring to fig. 2, in some embodiments, the steps S43-S45 may be executed by the processor 11. That is, the processor 11 may be configured to, in the case that n < m, consider as the re-classified category a category having a brand sample of more than 1, in the case that the brand sample in the category is more than 1; and for classifying the steel samples in the re-classified categories into M brand samples according to the second predetermined single element concentration difference, and classifying the samples with similar second predetermined single element concentration into N categories, wherein M, N is a natural number and is more than 1; it is also used to determine the grade of the steel sample from the second predetermined single element in case of M = N, in case of 1 grade sample in each category.

Thus, when a plurality of grade samples exist in one category, the steel samples in the category can be divided into M grade samples and N categories according to the second preset unit element, and when the M grade samples and the N categories of samples are equal, the sample categories and the grades can be determined to be in one-to-one correspondence, and then the grades of the steel samples can be determined. The method and the device classify the classes with similar element concentrations, effectively avoid simultaneous modeling of samples with large concentration difference, and improve the prediction accuracy of the model.

Specifically, after the step S41, the number of m grades may be larger than n categories, that is, in the case that n < m in the step S43, a steel sample including a plurality of grades in a certain category may appear. At this time, step S44 and step S45 may be executed to divide the steel samples in the category into M grades of samples by the second predetermined single element concentration difference, and divide the samples with the second predetermined single element concentration being similar into N categories, at this time, when M = N, in the case that the grade samples in each category are 1, that is, M grades and N categories are in one-to-one correspondence, the grade of the steel sample may be determined according to the second predetermined single element.

Of course, referring to fig. 9, in some embodiments, the steel grade identification method includes:

and S50, under the condition that N is less than M, the grade of the steel sample cannot be confirmed through the second predetermined single element.

Referring to fig. 2, in some embodiments, the step S50 may be executed by the processor 11. That is, the processor 11 may be configured to not confirm the grade of the steel sample with the second predetermined single element if N < M.

In this way, when M grades of the steel sample are larger than N grades in the second measurement process based on the second predetermined single element, it indicates that two or more grades are still present in one grade, and the grade of the steel sample cannot be determined. Of course, at this point, a third predetermined single element test may be performed to identify the brand of the entire steel sample.

Specifically, after the step S44, the number of M grades may be larger than that of N categories, that is, in the case that N < M in the step S44, a steel sample including a plurality of grades in a certain category may appear. That is, the grade of the steel sample cannot be confirmed by the second predetermined single element in step S50. At this time, the steel samples in the category can be divided into multiple grades and multiple categories by the third predetermined single element concentration difference, and in this way, the grades of all the steel samples can be confirmed by the fourth predetermined single element concentration difference, the fifth predetermined single element concentration difference and the like.

In the embodiment of the present application, the specific element types of the first predetermined single element and the second predetermined single element are not limited to meet various requirements. For example, the first predetermined single element may be elemental carbon and the second predetermined single element may be elemental iron. Of course, in some embodiments, the first predetermined single element and the second predetermined single element may be the same element, as long as the concentration ranges indicated by the first predetermined single element and the second predetermined single element are different.

Referring to fig. 10, in some embodiments, a steel grade identification method includes:

and S60, under the condition that n is less than m, the grade of the steel sample cannot be confirmed through the first predetermined single element.

Referring to fig. 2, in some embodiments, the step S60 may be executed by the processor 11. That is, the processor 11 may be configured to not confirm the grade of the steel sample by the first predetermined single element in the case where n < m.

In this way, when m grades of the steel sample are larger than n categories in the first measurement process according to the first predetermined single element, the steel sample still has two or more grades in one category, and the category of the steel sample cannot be determined. Of course, at this point, a second predetermined single element test may be performed to identify the brand of the entire steel sample.

Specifically, after the steps S41-S42, the number of m grades may be larger than n categories, that is, in the case that n < m in the step S60, a steel sample including a plurality of grades in a certain category may appear. That is, the grade of the steel sample cannot be confirmed by the first predetermined single element in step S60. At this time, the grade of the steel sample can be determined by the second predetermined single element concentration difference of the steel sample in the category, that is, the grade of the steel sample can be determined by the steps S43-S45.

In the embodiment of the application, the concentration difference of each element of the steel sample to be classified is fully utilized, firstly, the single element is screened to reduce the dimension of the classification number layer by layer, the interference of the elements with unobvious concentration discrimination is reduced, and then the elements are selected and discriminated according to the difference of the elements of different classifications, so that the range is gradually reduced. The prediction accuracy of a plurality of models is obviously improved compared with that of a single model by nesting. Please refer to table 1, where table 1 shows the classification results of the multi-element single model and the single-element nested model test set. From the table, the multi-element single model has good recognition rate for C, G, H, J and M brands, the recognition effect of other brands is poor, wherein all A brands are wrong in prediction, on the contrary, the single element nested model of the embodiment of the application has good recognition rate for all brands, and the recognition accuracy rate of brands with similar all-element content is influenced due to the heterogeneity of components of the steel sample. That is to say, the accuracy of the steel grade identification is improved remarkably by the single element nested model.

TABLE 1 Multi-element single model and single-element nested model test set classification result table

Referring to fig. 2, the present application provides a readable storage medium storing a computer program, which when executed by one or more processors 11, implements the steel grade identification method of the above embodiment.

For example, the computer program may be executed by the processor 11 to perform a steel grade identification method of:

In the description of the embodiments of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present invention, "a plurality" means two or more unless specifically limited otherwise.

In the description herein, references to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.

The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processing module-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of embodiments of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.

Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims

1. A steel grade identification method is characterized by comprising the following steps:

establishing a single element nesting model by using the training data set;

inputting the test data set into a nesting model for processing, and determining the grade of the steel sample according to an output result;

processing the raw spectral data and obtaining a training dataset and a test dataset, comprising:

2. The steel grade identification method of claim 1, wherein processing the effective spectral data and obtaining the training data set and the test data set comprises:

and randomly selecting a plurality of processed spectral data as the training data set, and using the rest of the processed spectral data as the test data set, wherein the number of the training data sets is more than that of the test data sets.

3. The steel grade identification method according to claim 1, wherein the step of inputting the test data set into a nested model for processing, and determining the grade of the steel sample according to the output result comprises:

4. The steel grade identification method according to claim 3, wherein the step of inputting the test data set into a nested model for processing and determining the grade of the steel sample according to the output result comprises:

5. The steel grade identification method according to claim 4, wherein the steel grade identification method comprises:

6. The steel grade identification method according to claim 3, wherein the steel grade identification method comprises:

7. A laser induced breakdown spectroscopy device, comprising:

the sample table is used for bearing a steel sample;

the laser is used for emitting laser to the steel sample;

the spectrometer is used for receiving the laser reflected by the steel sample and comprises a processor which is used for realizing the steel grade identification method of any one of claims 1 to 6.

8. The laser-induced breakdown spectroscopy apparatus of claim 7, comprising an optical assembly disposed between the laser and the sample stage, the optical assembly configured to direct the laser emitted by the laser onto the steel sample.

9. A readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, implements the steel grade identification method of any one of claims 1-6.