Adaptive calibration method and device for material detection model based on LIBS

Abstract

The present invention provides an adaptive calibration method and device for a material detection model based on LIBS, the method comprising: obtaining spectral data of a mixture collected by a LIBS device, and the actual concentration of a target element in a finished sintered ore obtained after the mixture reacts; obtaining the actual concentration of the target element in the mixture according to the actual concentration of the target element in the finished sintered ore; obtaining the predicted concentration of the target element in the mixture according to the spectral data and the material detection model; obtaining a calibration function according to the actual concentration and predicted concentration of the target element in the mixture; and calibrating the material detection model using the calibration function. In this process, no manual sampling and analysis is required, and no additional workload is added. The calibration is automatically completed using the analysis results of the finished sintered ore, and the production on site is not affected.

Description

Technical Field

[0001] The present invention relates to the technical field of laser spectrum analysis, and in particular to a method and device for adaptively calibrating a material detection model based on LIBS. Background Art

[0002] LIBS (Laser-Induced Breakdown Spectroscopy) is a powerful analytical technique used to determine the chemical composition of materials. LIBS technology uses high-power laser pulses to irradiate the sample surface, form a plasma, and analyze the spectrum emitted by the plasma to determine the types of elements in the sample and their concentrations. This technology has attracted widespread attention due to its rapidity, lack of complex sample preparation, ability to be operated remotely, and multi-element detection capabilities.

[0003] Taking the detection of mixed materials as an example, after the LIBS device collects spectral data at the detection point of the mixed material, it will input the spectral data into the preset material detection model to analyze the types of elements in the mixed material and their concentrations. This material detection model requires manual sampling and testing to obtain the test results, and is constructed based on the test results and spectral data. This workload is very large. After the material detection model is built, the LIBS device will be affected by changes in field conditions during long-term field use, which will cause the test results to shift. Based on this problem, the general practice now is to rebuild the material detection model through manual sampling and testing, or to calibrate the results through manual sampling and testing combined with some algorithms. Both solutions will increase the workload and bring inconvenience to on-site production. Moreover, both solutions are carried out actively, and it is difficult to achieve real-time calibration. Summary of the invention

[0004] In view of the above defects in the prior art, the present invention provides a method and device for adaptively calibrating a material detection model based on LIBS, so as to solve the technical problem that the detection results of the material detection model are offset.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides an adaptive calibration method for a material detection model based on LIBS, comprising: acquiring spectral data of a mixture collected by a LIBS device, and an actual concentration of a target element in a finished sintered ore obtained after the mixture reacts; obtaining an actual concentration of the target element in the mixture based on the actual concentration of the target element in the finished sintered ore; obtaining a predicted concentration of the target element in the mixture based on the spectral data and the material detection model; obtaining a calibration function based on the actual concentration and predicted concentration of the target element in the mixture; and calibrating the material detection model using the calibration function.

[0006] In one embodiment of the present invention, spectral data of a mixture collected by a LIBS device and an actual concentration of a target element in a finished sintered ore obtained after the mixture reacts are obtained, including: obtaining spectral data of the mixture collected by the LIBS device in a first time period; obtaining a second time period according to the size and speed of a conveying channel between a discharge point of the mixture and a collection point of the finished sintered ore, a spectral detection time from the discharge point to the LIBS device, and the first time period; and obtaining the actual concentration of the target element in the finished sintered ore in the second time period.

[0007] In one embodiment of the present invention, the predicted concentration of the target element in the mixture is obtained based on the spectral data and the material detection model, including: obtaining multiple first predicted concentrations of the target element in the mixture in the first time period based on the spectral data of the mixture in the first time period and the material detection model; obtaining the average value and variance of the multiple first predicted concentrations based on the multiple first predicted concentrations; eliminating the first predicted concentrations that deviate greatly from the average value based on the average value and variance of the multiple first predicted concentrations; and averaging the eliminated first predicted concentrations to obtain the predicted concentration of the target element in the mixture.

[0008] In one embodiment of the present invention, the actual concentration of the target element in the mixture is obtained according to the actual concentration of the target element in the finished sintered ore, including: obtaining the actual concentration of the target element in the mixture according to the actual concentration of the target element in the finished sintered ore and a preset first relationship; wherein the first relationship is obtained by the following steps: obtaining the actual concentration of the target element in the finished sintered ore in the third time period; obtaining the actual concentration of the target element in the mixture in the fourth time period by offline analysis, wherein the mixture in the fourth time period is reacted to obtain the finished sintered ore in the third time period; obtaining the first relationship according to the actual concentration of the target element in the finished sintered ore in the third time period and the actual concentration of the target element in the mixture in the fourth time period.

[0009] In one embodiment of the present invention, the actual concentration of the target element in the mixture is obtained according to the actual concentration of the target element in the finished sintered ore, including: obtaining the concentration of the target element in the mixture before reaction according to the actual concentration of the target element in the finished sintered ore; obtaining the actual concentration of the target element in the mixture according to the concentration of the target element in the mixture before reaction.

[0010] In one embodiment of the present invention, the concentration of the target element in the mixture before reaction is obtained based on the actual concentration of the target element in the finished sintered ore, including: obtaining the concentration of the target element in the mixture before reaction based on the actual concentration of the target element in the finished sintered ore and a preset second relationship; wherein the second relationship is obtained by the following steps: obtaining the ratio of each ingredient in the mixture; obtaining the content of other elements that react with the target element in each of the ingredients; and obtaining the second relationship based on the ratio and the content.

[0011] In one embodiment of the present invention, the actual concentration of the target element in the mixture is obtained based on the concentration of the target element in the mixture before reaction, including: obtaining the actual concentration of the target element in the mixture based on the concentration of the target element in the mixture before reaction and a preset third relationship; wherein the third relationship is obtained by the following steps: obtaining the actual concentration of the target element in the finished sintered ore in the third time period; obtaining the actual concentration of the target element in the mixture in the fourth time period by offline analysis, wherein the mixture in the fourth time period is reacted to obtain the finished sintered ore in the third time period; obtaining the concentration of the target element in the mixture before reaction in the fourth time period based on the actual concentration of the target element in the finished sintered ore in the third time period and the second relationship; obtaining the third relationship based on the actual concentration of the target element in the mixture in the fourth time period and the concentration of the target element in the mixture in the fourth time period before reaction.

[0012] In one embodiment of the present invention, the material detection model is obtained through the following steps: obtaining spectral data of the mixture collected by the LIBS device and the mixture sample corresponding to the spectral data; obtaining the type and concentration of elements in the mixture sample by offline analysis; and obtaining the material detection model based on the spectral data of the mixture and the type and concentration of elements in the corresponding sample.

[0013] In one embodiment of the present invention, a calibration function is obtained based on the actual concentration and predicted concentration of the target element in the mixture, including: obtaining the calibration function based on a first set consisting of a plurality of actual concentrations of the target element in the mixture within a preset time, and a second set consisting of a plurality of predicted concentrations.

[0014] To achieve the above-mentioned purpose and other related purposes, the present invention also provides an adaptive calibration device for a material detection model based on LIBS, comprising: a data acquisition module, used to acquire spectral data of a mixture collected by a LIBS device, and the actual concentration of a target element in a finished sintered ore obtained after the mixture reacts; a first calculation module, used to obtain the actual concentration of the target element in the mixture according to the actual concentration of the target element in the finished sintered ore; a second calculation module, used to obtain the predicted concentration of the target element in the mixture according to the spectral data and the material detection model; a third calculation module, used to obtain a calibration function according to the actual concentration and predicted concentration of the target element in the mixture; and a calibration module, used to calibrate the material detection model using the calibration function.

[0015] Beneficial effects of the present invention: The present invention proposes an adaptive calibration method and device for a material detection model based on LIBS. The method analyzes the concentration of a target element in a finished sintered ore to infer the actual concentration of the target element in the mixture. At the same time, the predicted concentration of the target element in the mixture can be obtained according to the material detection model. By comparing the actual concentration and the predicted concentration of the target element, a calibration function can be obtained to calibrate the material detection model. In this process, no manual sampling and analysis is required, and no additional workload is added. The calibration is automatically completed using the analysis results of the finished sintered ore, and on-site production is not affected. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be 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.

[0017] Figure 1 A flow chart of a calibration method provided by an embodiment of the present invention;

[0018] Figure 2 A flowchart of step S100 provided in one embodiment of the present invention;

[0019] Figure 3 A first relationship acquisition flow chart provided by an embodiment of the present invention;

[0020] Figure 4 A flowchart of step S200 provided in one embodiment of the present invention;

[0021] Figure 5 A flowchart of obtaining a second relationship provided by an embodiment of the present invention;

[0022] Figure 6 A flowchart of obtaining a third relationship provided by an embodiment of the present invention;

[0023] Figure 7 A flow chart for obtaining a material detection model provided by an embodiment of the present invention;

[0024] Figure 8 A flow chart for calculating the predicted concentration of a target element in a mixture provided by an embodiment of the present invention;

[0025] Fig. 9 A schematic diagram of the structure of a calibration device provided in one embodiment of the present invention.

[0026] Explanation of reference numerals: 101, data acquisition module; 102, first calculation module; 103, second calculation module; 104, third calculation module; 105, calibration module. DETAILED DESCRIPTION

[0027] The following describes the embodiments of the present invention through specific specific embodiments, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. It should be noted that the following embodiments and the features in the embodiments can be combined with each other without conflict. In addition to the specific methods, equipment, and materials used in the embodiments, according to the technical personnel in this technical field's grasp of the prior art and the records of the present invention, any methods, equipment, and materials of the prior art that are similar or equivalent to the methods, equipment, and materials described in the embodiments of the present invention can also be used to implement the present invention.

[0028] It should be understood that the terms used in the embodiments of the present invention are for describing specific embodiments rather than for limiting the scope of protection of the present invention. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those generally understood by those skilled in the art.

[0029] 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 some of the 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.

[0030] The flowchart and block diagram in the accompanying drawings illustrate the system architecture, functions and operations that may be implemented according to the methods and computer program products of various embodiments disclosed in the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0031] In the present invention, based on the spectral data collected by the LIBS device, the material detection model can be used to analyze the element types and concentration information in the mixture, including the concentration of the target element, which can be called the predicted concentration. The material detection model is relatively accurate at the beginning, and the predicted concentration obtained is basically consistent with the actual concentration, but as time goes by and the detection environment changes, the predicted concentration will be offset. At the same time, the finished sintered ore generated after the mixture reacts, since the reaction process is known, the concentration of the target element in the mixture can be inferred based on the concentration of the target element in the finished sintered ore, and this concentration can be considered as the actual concentration. The core idea of ​​the present invention is to calculate the calibration function based on the predicted concentration and actual concentration of the target element calculated by these two methods to calibrate the material detection model, thereby ensuring that the element types and concentration information obtained by the material detection model analysis are accurate enough.

[0032] It should be noted that although the concentration of elements in the mixture can be inferred based on the test results of the finished sintered ore, this method can only be used for some elements. For some elements, they no longer exist in the finished sintered ore after the reaction, and the concentration of the element in the mixture cannot be calculated by inversion. In addition, the concentration of each element changes differently before and after the reaction, so the calculation process for different elements is different. Therefore, although more accurate concentration information of some elements can be obtained by inversion, the inversion method cannot detect the concentration of all elements in the mixture.

[0033] The predicted concentration obtained by using the material detection model is different. This method can analyze the element types in the mixture and the concentration information of each element. Therefore, in the present invention, only the predicted concentration and actual concentration of the target element are used to obtain the calibration function, and then the calibrated material detection model is used to obtain the element types and concentration information in the mixture. The following is a detailed description of the invention idea.

[0034] See also Figure 1 , Figure 1 An adaptive calibration method for a material detection model based on LIBS is provided in accordance with an embodiment of the present invention, and includes steps S100 to S500. Each step is described in detail below.

[0035] Step S100, obtaining the spectrum data of the mixture collected by the LIBS device, and the actual concentration of the target element in the finished sintered ore obtained after the mixture reacts. The mixture reacts to obtain the finished sintered ore, and the spectrum data of the mixture is collected by the LIBS device. The actual concentration of the target element in the finished sintered ore can be obtained, for example, by X-ray fluorescence spectrometry (XRF), atomic absorption spectrometry, manual sampling and testing, etc. These methods can accurately determine the content of multiple elements in the finished sintered ore.

[0036] The target element mentioned here refers to a certain element that exists in both the finished sintered ore and the mixture. In a specific embodiment of the present invention, the mixture is, for example, a mixture of fuel, dolomite, and limestone, and the target element can be calcium. The embodiments below are also described in detail using calcium as an example. It can be understood that when the materials in the mixture are other types, the target element can also be other elements.

[0037] The above-mentioned spectral data and the actual concentration of the target element in the finished sintered ore are generally collected in real time on site and stored in a database, so in step S100, these data can be read from the historical data for subsequent analysis. In a specific embodiment of the present invention, for example, M days can be used as a window, and a calibration function can be calculated based on the spectral data in these M days and the actual concentration of the target element in the finished sintered ore. When the next window comes, the calibration function is calculated in the same way, and so on.

[0038] See also Figure 2In a specific embodiment of the present invention, step S100 includes: S110, obtaining the spectral data of the mixture collected by the LIBS device in the first time period; S120, obtaining the second time period according to the size and speed of the conveying channel between the unloading point of the mixture and the collection point of the finished sintered ore, the spectral detection time from the unloading point to the LIBS device, and the first time period; S130, obtaining the actual concentration of the target element in the finished sintered ore in the second time period. In this step, the second time period is calculated based on the first time period in order to correspond the spectral data with the actual concentration of the target element in the finished sintered ore, that is, the mixture corresponding to the spectral data of the first time period is obtained after the reaction of the finished sintered ore corresponding to the second time period, so that the spectral data and concentration data corresponding to the two have a corresponding relationship.

[0039] In a specific embodiment of the present invention, the start time of the first time period is t1 and the end time is t2, and the start time of the second time period is t3 and the end time is t4. Then their relationship can be calculated as follows: (1) First, the spectral detection time ∆t1 from the unloading point to the LIBS device is obtained. Then the spectral data in the time period [t1, t2] corresponds to the mixed material in the time period [t1-∆t1, t2-∆t1]. (2) The transportation channel from the mixed material to the finished sintered ore includes a sintering machine, an annular cooler and other conveyor belts. The sintering machine trolley is recorded as v1 and its length is l1. The annular cooler is recorded as v2 and its length is l2. The transportation time of other conveyor belts is recorded as ∆t2. This value can be calculated by the length and speed of other conveyor belts. Based on these parameters, the following relationship can be obtained:

[0040] ,

[0041] ,

[0042] According to the above relationship, the relationship between the first time period [t1, t2] and the second time period [t3, t4] is established. When calculating the calibration function, the estimated concentration of the target element in the mixture calculated based on the spectral data of the first time period and the actual concentration of the target element in the mixture calculated based on the actual concentration of the target element in the finished sintered ore in the second time period should be taken as a data pair, and the calibration function should be obtained based on one or more data pairs.

[0043] Step S200, according to the actual concentration of the target element in the finished sintered ore, the actual concentration of the target element in the mixture is obtained. In this step, the reaction process of the mixture is determined, so there is a certain mapping relationship between the actual concentration of the target element in the finished sintered ore and the actual concentration of the target element in the mixture, so the actual concentration of the target element in the mixture can be calculated according to the actual concentration of the target element in the finished sintered ore and the mapping relationship.

[0044] See also Figure 3 In a specific embodiment of the present invention, step S200 includes: obtaining the actual concentration of the target element in the mixture according to the actual concentration of the target element in the finished sintered ore and a preset first relationship; wherein the first relationship is obtained by the following steps: S201, obtaining the actual concentration of the target element in the finished sintered ore in the third time period; S202, obtaining the actual concentration of the target element in the mixture in the fourth time period by offline analysis, wherein the mixture in the fourth time period is reacted to obtain the finished sintered ore in the third time period; S203, obtaining the first relationship according to the actual concentration of the target element in the finished sintered ore in the third time period and the actual concentration of the target element in the mixture in the fourth time period.

[0045] In this step, the first relationship reflects the corresponding relationship between the concentration of the target element in the mixture and the finished sintered ore before and after the reaction. The first relationship is fixed and can be obtained in an experimental environment according to steps S201 to S203, and the obtained first relationship is saved as a preset known quantity. Considering that some parameters of the on-site equipment will affect the first relationship during actual production, the data in steps S201 and S202 are preferably obtained from the actual production scene, so that the first relationship constructed is more accurate.

[0046] See also Figure 4 In a specific embodiment of the present invention, step S200 includes: S210, according to the actual concentration of the target element in the finished sintered ore, obtaining the concentration of the target element in the mixture before reaction; S220, according to the concentration of the target element in the mixture before reaction, obtaining the actual concentration of the target element in the mixture. In the previous embodiment, the first relationship between the actual concentration of the target element in the finished sintered ore and the actual concentration of the target element in the mixture was directly established. This embodiment is different. The mapping relationship between the actual concentration of the target element in the finished sintered ore and the actual concentration of the target element in the mixture is established through two steps, step S210 and step S220. Step S210 and step S220 are described in detail below.

[0047] See also Figure 5 Step S210 includes: obtaining the concentration of the target element in the mixture before reaction according to the actual concentration of the target element in the finished sintered ore and a preset second relationship; wherein the second relationship is obtained through steps S211 to S213.

[0048] Step S211, obtain the ratio of each ingredient in the mixture. The ratio of each material in the mixture will be tested by special equipment at regular intervals. Therefore, in this step, the test results of other equipment can be directly obtained to obtain the ratio data. For example, in an actual production scenario, the ratio of fuel, dolomite, and limestone in the mixture is P1, P2, and P3.

[0049] Step S212, obtaining the content of other elements that react with the target element in each ingredient. Taking calcium as the target element, for example, other elements that react with the target element are carbon and sulfur, then this step is to obtain the content of carbon and sulfur in each ingredient. Taking the above scenario as an example, the carbon and sulfur content in the fuel is decomposed into C1 and S1, the carbon content in dolomite is C2, and the carbon content in limestone is C3.

[0050] Step S213, according to the ratio and content, obtain the second relationship. This step is mainly to construct the second relationship in combination with the reaction relationship of the mixture. Taking the above scenario as an example, the following relationship can be obtained: Ca1=(1-(P1×(C1+S1)+P2×C2+P3×C3))×Ca2, where Ca1 is the concentration of the target element in the mixture before reaction, and Ca2 is the actual concentration of the target element in the finished sintered ore. This relationship is the second relationship.

[0051] See also Figure 6 In a specific embodiment of the present invention, step S220 includes: obtaining the actual concentration of the target element in the mixture according to the concentration of the target element in the mixture before reaction and a preset third relationship; wherein the third relationship is obtained by the following steps: S221, obtaining the actual concentration of the target element in the finished sintered ore in the third time period; S222, obtaining the actual concentration of the target element in the mixture in the fourth time period by offline analysis, wherein the mixture in the fourth time period is reacted to obtain the finished sintered ore in the third time period; S223, obtaining the concentration of the target element in the mixture before reaction in the fourth time period according to the actual concentration of the target element in the finished sintered ore in the third time period and the second relationship; S224, obtaining the third relationship according to the actual concentration of the target element in the mixture in the fourth time period and the concentration of the target element in the mixture before reaction in the fourth time period. Theoretically, Ca1 calculated based on Ca2 in step S213 is actually equal to the actual concentration of the target element in the mixture. However, taking into account factors such as scale accuracy, material feeding speed, test level, actual ratio, etc. in actual production, there is a certain difference between the calculated Ca1 and the actual concentration of the target element in the mixture. Therefore, the third relationship can be obtained by fitting historical data.

[0052] In the above steps, the third time period and the fourth time period mentioned are to distinguish from the first time period and the second time period. In essence, they are both for matching the data. The correspondence between the third time period and the fourth time period can be calculated based on the size and speed of the conveying channel between the unloading point of the mixture and the collection point of the finished sintered ore.

[0053] In the above steps, two calculation methods of step S200 are proposed, and the actual concentration of calcium in the finished sintered ore in the third period is recorded as Ca2, and the actual concentration of calcium in the mixture in the fourth period is recorded as Ca0.

[0054] The first relationship is the relationship between Ca2 and Ca0, which can be represented by the function F(), for example. Then we can get: Ca0=F(Ca2). By substituting this formula into Ca2, we can get the corresponding Ca0.

[0055] The second and third relationships are decompositions of the first relationship, and an intermediate value Ca1 is introduced. For example, in the above embodiment, the second relationship is expressed by the formula: Ca1=(1-(P1×(C1+S1)+P2×C2+P3×C3))×Ca2, and the third relationship is expressed by the function G(): Ca0=G(Ca1), and the combination yields: Ca0=G((1-(P1×(C1+S1)+P2×C2+P3×C3))×Ca2). By substituting this formula into Ca2, the corresponding Ca0 can be obtained.

[0056] Understandably, for different target elements and reaction relationships, the second relationship will be different; for a fixed scene, the third relationship is certain; for a fixed scene and the same reaction process, the first relationship is certain. These relationships only need to be calculated once and saved, and can be directly referenced later.

[0057] Step S300: Obtain the predicted concentration of the target element in the mixture according to the spectral data and the material detection model. The predicted concentration of the target element in the mixture is calculated according to the material detection model in order to facilitate the construction of the calibration function.

[0058] See also Figure 7 In a specific embodiment of the present invention, the material detection model is obtained by the following steps: S311, obtaining the spectral data of the mixture collected by the LIBS device and the mixture sample corresponding to the spectral data; S312, obtaining the type and concentration of the elements in the mixture sample by offline analysis; S313, obtaining the material detection model according to the spectral data of the mixture and the type and concentration of the elements in the corresponding sample. The material detection model can calculate the type and concentration of all elements according to the spectral data, but in this step, only the concentration of the target element is used and used as the predicted concentration of the target element in the mixture.

[0059] In step S200, the actual concentration of the target element in the mixture needs to be obtained based on the actual concentration of the target element in the finished sintered ore in the second time period. In step S300, the predicted concentration of the target element in the mixture needs to be obtained based on the spectral data of the first time period and the material detection model. Since the time interval between the first time period and the second time period can be long or short, the actual concentrations of the target element in multiple finished sintered ores may be collected in the second time period, and the LIBS device may collect multiple spectral data in the first time period, so it is necessary to process multiple data into one data.

[0060] See also Figure 8 In a specific embodiment of the present invention, step S300 is taken as an example. Step S300 includes: S321 obtains a plurality of first predicted concentrations of the target element in the mixture in the first period of time according to the spectral data of the mixture in the first period of time and the material detection model, recorded as (a1, a2, ..., a n ); S322, according to the multiple first predicted concentrations, obtain an average value of the multiple first predicted concentrations and variance σ, wherein the mean value and the variance can be calculated according to a specific calculation formula; S323, according to the mean values ​​and variances of the plurality of first predicted concentrations, eliminating the first predicted concentrations with a large deviation from the mean value, for example, eliminating (a1, a2, ..., a n ) is less than and greater than S324, calculate the average value of the first predicted concentration after elimination to obtain the predicted concentration of the target element in the mixture in the first period, and the result is a numerical value.

[0061] Step S400: Obtain a calibration function according to the actual concentration and predicted concentration of the target element in the mixture.

[0062] In a specific embodiment of the present invention, step S400 includes: obtaining a calibration function according to a first set of actual concentrations of target elements in a plurality of mixtures within a preset time and a second set of predicted concentrations. In an actual scenario, the preset time is, for example, M days, and the predicted concentration of the target element in the mixture in the first time period obtained according to the spectral data of the first time period is recorded as A i According to the actual concentration of the target element in the finished sintered ore in the second period, the actual concentration of the target element in the mixed material in the first period is obtained and recorded as B i , the subscript i indicates the corresponding relationship between the two. Based on M days of historical data, we can get the first set (A1, A2, …, A m ) and the second set (B1,B2,…,B m ), m is the total number of data pairs calculated within M days.

[0063] Then, we can calculate the m ) and (B1,B2,…,B m ) is used to obtain the calibration function J(θ). When calculating, when the actual concentration of the target element of the sample of the finished sintered ore is obtained by sampling and offline testing, there will be some abnormal points due to the representativeness of the sample. Therefore, in the specific solution, the calibration function J(θ) can be solved by robust regression.

[0064] Step S500: Calibrate the material detection model using the calibration function. Substitute the calibration function J(θ) obtained above into the material detection model to complete a model calibration. The calibrated model can process the spectral data to obtain more accurate element type and concentration information.

[0065] It should be noted that the step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they contain the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0066] Starting from the actual scenario, the calibration steps can be divided into the following three steps: (1) For a new scenario, first construct the first relationship (or construct the second relationship and the third relationship) and save it; (2) Each time calibration is required, obtain the historical data of the previous M days, which includes the spectral data collected by the LIBS equipment and the concentration data of the target element in the finished sintered ore; (3) Establish the correspondence between the spectral data and the concentration data to obtain the first set (A1, A2, …, A m ) and the second set (B1,B2,…,B m ), and then according to these two sets, obtain the calibration function J(θ), and calibrate the material detection model. When calibration is required later, just repeat steps (2) and (3). These two steps can be completed automatically without manual intervention, so the equipment can be calibrated automatically during subsequent use.

[0067] See also Fig. 9 , Fig. 9An adaptive calibration device for a material detection model based on LIBS is provided for one embodiment of the present invention, comprising a data acquisition module 101, a first calculation module 102, a second calculation module 103, a third calculation module 104 and a calibration module 105, wherein the data acquisition module 101 is used to obtain the spectral data of the mixture collected by the LIBS device, and the actual concentration of the target element in the finished sintered ore obtained after the mixture reacts; the first calculation module 102 is used to obtain the actual concentration of the target element in the mixture according to the actual concentration of the target element in the finished sintered ore; the second calculation module 103 is used to obtain the predicted concentration of the target element in the mixture according to the spectral data and the material detection model; the third calculation module 104 is used to obtain a calibration function according to the actual concentration and predicted concentration of the target element in the mixture; and the calibration module 105 is used to calibrate the material detection model using the calibration function.

[0068] It should be noted that the adaptive calibration device of this embodiment is a device corresponding to the adaptive calibration method described above, and the functional modules in the adaptive calibration device may correspond to the corresponding steps in the adaptive calibration method. The adaptive calibration device of this embodiment can be implemented in conjunction with the adaptive calibration method, that is, in the absence of conflict, the relevant technical details mentioned in the adaptive calibration method of the above embodiment can also be applied to the adaptive calibration device of this embodiment.

[0069] 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 calibration method for a material detection model based on LIBS, characterized in that: include: Obtaining spectral data of the mixture collected by the LIBS device, as well as the actual concentration of the target element in the finished sintered ore obtained after the mixture reacts; According to the actual concentration of the target element in the finished sintered ore, the actual concentration of the target element in the mixed material is obtained; Obtaining a predicted concentration of a target element in the mixture according to the spectral data and the material detection model; Obtaining a calibration function based on the actual concentration and the predicted concentration of the target element in the mixture; Calibrate the material detection model using the calibration function; Obtaining the spectral data of the mixture collected by the LIBS device, and the actual concentration of the target element in the finished sintered ore obtained after the mixture reacts, including: Obtaining spectral data of the mixture collected by the LIBS device in the first period; A second time period is obtained according to the size and speed of the conveying channel between the unloading point of the mixed material and the collection point of the finished sintered ore, the spectrum detection time from the unloading point to the LIBS device, and the first time period; The actual concentration of the target element in the finished sintered ore in the second period is obtained.

2. The method for adaptively calibrating a material detection model based on LIBS according to claim 1, characterized in that: Obtaining a predicted concentration of a target element in the mixture according to the spectral data and the material detection model, including: Obtaining a plurality of first predicted concentrations of a target element in the mixture in the first period of time according to the spectral data of the mixture in the first period of time and the material detection model; According to the plurality of the first predicted concentrations, obtaining an average value and a variance of the plurality of the first predicted concentrations; Eliminate first predicted concentrations having a large deviation from the average value according to the average values ​​and variances of the plurality of first predicted concentrations; The average of the first predicted concentrations after elimination is calculated to obtain the predicted concentration of the target element in the mixture.

3. The method for adaptive calibration of a material detection model based on LIBS according to claim 1, characterized in that: According to the actual concentration of the target element in the finished sintered ore, the actual concentration of the target element in the mixed material is obtained, including: According to the actual concentration of the target element in the finished sintered ore and the preset first relationship, the actual concentration of the target element in the mixed material is obtained; The first relationship is obtained by the following steps: Obtaining the actual concentration of the target element in the finished sintered ore in the third time period; Obtaining the actual concentration of the target element in the mixture in the fourth period by means of an off-line assay, wherein the mixture in the fourth period is reacted to obtain the finished sintered ore in the third period; The first relationship is obtained according to the actual concentration of the target element in the finished sintered ore in the third time period and the actual concentration of the target element in the mixed material in the fourth time period.

4. The method for adaptively calibrating a material detection model based on LIBS according to claim 1, characterized in that: According to the actual concentration of the target element in the finished sintered ore, the actual concentration of the target element in the mixed material is obtained, including: According to the actual concentration of the target element in the finished sintered ore, the concentration of the target element in the mixed material before reaction is obtained; The actual concentration of the target element in the mixture is obtained according to the concentration of the target element in the mixture before the reaction.

5. The method for adaptively calibrating a material detection model based on LIBS according to claim 4, characterized in that: According to the actual concentration of the target element in the finished sintered ore, the concentration of the target element in the mixed material before reaction is obtained, including: According to the actual concentration of the target element in the finished sintered ore and the preset second relationship, the concentration of the target element in the mixed material before reaction is obtained; The second relationship is obtained by the following steps: Obtaining the proportion of each ingredient in the mixture; Obtaining the content of other elements that react with the target element in each of the ingredients; The second relationship is obtained according to the ratio and the content.

6. The method for adaptively calibrating a material detection model based on LIBS according to claim 5, characterized in that: Obtaining the actual concentration of the target element in the mixture according to the concentration of the target element in the mixture before the reaction, including: Obtaining an actual concentration of the target element in the mixture according to the concentration of the target element in the mixture before the reaction and a preset third relationship; The third relationship is obtained by the following steps: Obtaining the actual concentration of the target element in the finished sintered ore in the third time period; Obtaining the actual concentration of the target element in the mixture in the fourth period by means of an off-line assay, wherein the mixture in the fourth period is reacted to obtain the finished sintered ore in the third period; According to the actual concentration of the target element in the finished sintered ore in the third time period and the second relationship, the concentration of the target element in the mixed material before the reaction in the fourth time period is obtained; The third relationship is obtained according to the actual concentration of the target element in the mixture in the fourth time period and the concentration of the target element in the mixture before the reaction in the fourth time period.

7. The method for adaptively calibrating a material detection model based on LIBS according to claim 1, characterized in that: The material detection model is obtained through the following steps: Acquire spectral data of the mixture collected by the LIBS device and a mixture sample corresponding to the spectral data; Obtaining the types and concentrations of elements in the mixed material sample by means of off-line testing; The material detection model is obtained according to the spectral data of the mixture and the types and concentrations of elements in the corresponding sample.

8. The method for adaptively calibrating a material detection model based on LIBS according to claim 1, characterized in that: According to the actual concentration and predicted concentration of the target element in the mixture, a calibration function is obtained, including: The calibration function is obtained according to a first set consisting of a plurality of actual concentrations of target elements in the mixture within a preset time and a second set consisting of a plurality of predicted concentrations.

9. An adaptive calibration device for a material detection model based on LIBS, characterized in that: include: A data acquisition module is used to acquire the spectral data of the mixture collected by the LIBS device, as well as the actual concentration of the target element in the finished sintered ore obtained after the mixture reacts; A first calculation module is used to obtain the actual concentration of the target element in the mixed material according to the actual concentration of the target element in the finished sintered ore; A second calculation module, used for obtaining a predicted concentration of a target element in the mixture according to the spectral data and the material detection model; A third calculation module is used to obtain a calibration function according to the actual concentration and predicted concentration of the target element in the mixture; A calibration module, used for calibrating the material detection model using the calibration function; The spectral data of the mixture collected by the LIBS device and the actual concentration of the target element in the finished sintered ore obtained after the mixture reacts are obtained, including: Obtaining spectral data of the mixture collected by the LIBS device in the first period; A second time period is obtained according to the size and speed of the conveying channel between the unloading point of the mixed material and the collection point of the finished sintered ore, the spectrum detection time from the unloading point to the LIBS device, and the first time period; The actual concentration of the target element in the finished sintered ore in the second period is obtained.

Images