A bauxite composition online detection method and related equipment

Abstract

The present application discloses an online detection method for bauxite composition and related equipment, relating to the field of ore detection. The method comprises: controlling a LIBS system to collect n actual spectral data on the bauxite to be tested on a conveyor belt at a preset speed; performing a preprocessing operation on the n actual spectral data to obtain a preprocessed actual spectral data set; calculating a screening distance between each preprocessed actual spectral data in the preprocessed actual spectral data set and a bauxite category spectrum, and adding the preprocessed actual spectral data with the screening distance less than or equal to the preset distance to an effective spectral data set, wherein the category spectrum is obtained by statically measuring a standard sample with known composition; taking the average value of the first m spectral data in the effective spectral data set as actual continuous transmission spectral data; and inputting the actual continuous transmission spectral data into an optimal model to obtain the bauxite composition corresponding to each spectral data.

Description

Technical Field

[0001] This specification relates to the field of ore detection, and more specifically, to an online detection method for bauxite composition and related equipment. Background Art

[0002] Alumina is a critical industrial raw material and resource-based commodity. Slurry preparation is the first step in alumina production, with bauxite being its primary raw material. The composition of the bauxite determines the material ratio for slurry preparation. Fluctuations in slurry composition can impact the entire alumina production line, causing fluctuations in actual dissolution and decomposition rates, increased material and energy consumption, and reduced product quality. Due to factors such as bauxite's complex composition, volatile chemical composition, increasing resource scarcity, and declining quality, solutions to ensure high quality and stability of bauxite are difficult to find.

[0003] Testing and analyzing the composition of bauxite can derive strategies for adding various material components, guide the batching process, and stabilize the original slurry environment. However, most of the process and technical indicators of alumina companies currently use manual timed sampling and laboratory manual analysis methods for sample testing. The sampling time interval is long, the analysis results are delayed, and it is easy to cause human errors, which cannot provide timely and effective guidance for ore batching. Domestic and foreign online detection technologies for ore and metal components mainly include neutron activation analysis (PGNAA), near-infrared spectroscopy (NIR), X-ray fluorescence spectroscopy (XRF) and other technologies for research and industrial trial application. However, the main problems are that PGNAA has serious radiation risks, NIR cannot directly measure elements and has high adaptability requirements for field applications, and XRF cannot directly measure elements with smaller atomic numbers.

[0004] Laser-induced breakdown spectroscopy (LIBS) is a multi-element analysis technique based on atomic emission spectroscopy. It uses a high-energy laser source to generate a high-temperature plasma on the sample surface. The elements contained in the sample are vaporized, atomized, and excited in the hot plasma, producing atomic and ion spectra that are characteristic of the sample's elemental composition. Compared to traditional analytical methods, LIBS is fast, requires no complex sample preparation, and allows for remote analysis. This overcomes the limitations of conventional analytical techniques as online detection technologies and can be used for samples in any physical state, such as solids, liquids, and gases, including aerosols, and can be used for online analysis.

[0005] Due to the complexity of ores and the stringent latency requirements of industrial production, LIBS technology has yet to be applied to online ore composition monitoring, hindered by factors such as matrix effects, self-absorption, and interference from overlapping peaks. There is an urgent need for an online bauxite composition detection method and system to enable online analysis of bauxite composition, thereby enabling intelligent control of ore blending, reducing production costs, improving product quality, and accelerating the automation, informatization, and intelligentization of the alumina production process. Summary of the Invention

[0006] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention of this application is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0007] In the first aspect, the present application proposes an online detection method for bauxite composition, comprising:

[0008] Control the LIBS system to collect n actual spectral data on the bauxite to be tested on the conveyor belt at a preset speed;

[0009] Performing a preprocessing operation on the n actual spectral data to obtain a preprocessed actual spectral data set;

[0010] Calculating a screening distance between each preprocessed actual spectrum data set and the alumina category spectrum in the preprocessed actual spectrum data set, and adding the preprocessed actual spectrum data sets having the screening distance less than or equal to a preset distance to the effective spectrum data set, wherein the category spectrum is obtained by statically measuring a standard sample with known composition;

[0011] The average value of the first m spectral data in the above valid spectral data set is used as the actual continuous transmission spectral data;

[0012] The actual continuous transmission spectral data are input into the optimal model to obtain the bauxite composition corresponding to each spectral data, wherein the optimal model is based on standard continuous transmission spectral data, which is the average value of the first m spectral data of the standard sample collected on the preset speed conveyor belt based on the LIBS system and obtained through the preprocessing operation and the screening distance operation.

[0013] In one embodiment, it further includes:

[0014] preparing n1 bulk bauxite samples with different compositions, grinding them, and pressing them into tablets to form the above-mentioned standard samples;

[0015] Controlling the LIBS system to collect n1 standard spectral data of the standard sample in a static state;

[0016] Performing a preprocessing operation on the n1 standard spectral data to obtain a preprocessed standard spectral data set;

[0017] The average value of the spectral data in the preprocessed standard spectral data set is used as the category spectrum.

[0018] In one embodiment, the preparation of n1 bulk bauxite samples with different compositions and the grinding and tableting to form the standard sample comprises:

[0019] The above-mentioned bulk bauxite samples with different compositions refer to bauxite samples with different contents of elements; the particle size of the above-mentioned bulk bauxite samples is less than 20 mm, and the above-mentioned n1 is greater than or equal to 30;

[0020] The steps of the above-mentioned grinding and tableting process specifically include:

[0021] Grinding the bauxite sample using a mortar for a maximum time of less than 2 minutes to form a granular bauxite sample having a particle size of less than or equal to 2 μm;

[0022] The granular bauxite sample is pressed at a pressure of at least 15 MPa for at least 30 seconds to form the bulk bauxite sample.

[0023] In one embodiment, the preprocessing operation includes a baseline correction operation and a noise removal operation;

[0024] The baseline correction operation includes one or more of a derivative method, an iterative polynomial fitting method, and a penalty-based least squares method.

[0025] In one embodiment, the noise removal operation includes wavelet transform and / or Savitzky-Golay.

[0026] In one embodiment, the optimal model is a partial least squares regression model. 2 A model that evaluates detection accuracy and uses grid search methods for parameter tuning.

[0027] In one embodiment, the parameters tuned in the above parameter tuning process include the number of principal components, the maximum number of iterations, and the convergence criterion.

[0028] In a second aspect, the present application proposes an online detection device for bauxite composition, comprising:

[0029] An acquisition unit, used to control the LIBS system to acquire n actual spectral data on the bauxite to be tested on a conveyor belt at a preset speed;

[0030] a preprocessing unit, configured to perform a preprocessing operation on the n actual spectral data to obtain a preprocessed actual spectral data set;

[0031] a screening unit, configured to calculate a screening distance between each preprocessed actual spectral data set in the preprocessed actual spectral data set and a class spectrum of alumina, and add the preprocessed actual spectral data sets having the screening distance less than or equal to a preset distance to the effective spectral data set, wherein the class spectrum is obtained by statically measuring a standard sample with known composition;

[0032] an averaging unit, configured to take the average of the first m spectral data in the valid spectral data set as the actual continuous transmission spectral data;

[0033] an acquisition unit, configured to input the actual continuous transmission spectral data into an optimal model to obtain the bauxite composition corresponding to each piece of spectral data, wherein the optimal model is based on standard continuous transmission spectral data, which is the average of the first m spectral data of the standard sample collected on the preset speed conveyor belt based on the LIBS system and obtained through the preprocessing operation and the screening distance operation.

[0034] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the method for online detection of bauxite composition according to any one of the first aspects described above when executing the computer program stored in the memory.

[0035] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the online detection method for bauxite composition of any one of the first aspects.

[0036] In summary, the LIBS-based online detection method for bauxite composition in an embodiment of the present application includes: controlling the LIBS system to collect n actual spectral data from the bauxite to be tested on a conveyor belt at a preset speed; performing preprocessing operations on the n actual spectral data to obtain a preprocessed actual spectral data set; calculating the screening distance between each preprocessed actual spectral data in the preprocessed actual spectral data set and the bauxite category spectrum, and adding the preprocessed actual spectral data with the screening distance less than or equal to the preset distance to the effective spectral data set, wherein the category spectrum is obtained by statically measuring a standard sample with known composition; taking the average of the first m spectral data in the effective spectral data set as the actual continuous transmission spectral data; inputting the actual continuous transmission spectral data into an optimal model to obtain the bauxite composition corresponding to each spectral data, wherein the optimal model is based on standard continuous transmission spectral data, which is the average of the first m spectral data collected by the LIBS system on the conveyor belt at the preset speed and obtained through the preprocessing and screening distance operations. The methods of the related art require manual sampling and laboratory analysis, which have long time intervals and delayed analysis results. This application uses LIBS technology to achieve online real-time detection of bauxite components, which can obtain data in a timely manner and guide the production process. Through preprocessing and screening operations, the high quality and accuracy of spectral data are ensured, human errors and external interference are reduced, and more accurate detection results are provided. Compared with the PGNAA method, LIBS technology avoids radiation risks and ensures the safety of operators. LIBS technology can be used for the detection of solid, liquid and gas samples, and does not require complex sample preparation, and is suitable for a variety of industrial environments. Through online detection and intelligent control, labor costs and laboratory analysis costs are reduced, while production efficiency and product quality are improved, and overall production costs are reduced. This solution provides a reliable online detection method for the alumina production process, promotes the automation, informatization and intelligent development of the production process, and enhances the competitiveness of the industry.

[0037] The online detection method for bauxite composition proposed in this application, and other advantages, objectives and features of this application will be reflected in part through the following description, and in part will be understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present description. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0039] Figure 1A schematic diagram of the process of an online detection method for bauxite composition provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of the principle of an online detection system for bauxite composition provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of the processing effect of a pre-processed LIBS spectrum provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of a spectrum S of a bauxite type provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of a continuous transmission bauxite composition detection method provided in an embodiment of the present application;

[0044] Figure 6 A schematic structural diagram of an online detection device for bauxite composition provided in an embodiment of the present application;

[0045] Figure 7 A schematic diagram of the structure of an electronic device for online detection of bauxite composition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments.

[0047] See also Figure 1 , which is a schematic flow diagram of an online detection method for bauxite composition provided in an embodiment of the present application, which may specifically include:

[0048] S110, controlling the LIBS system to collect n actual spectral data on the bauxite to be tested on the conveyor belt at a preset speed;

[0049] For example, the LIBS system is configured to collect n actual spectral data of the bauxite sample while it moves at a preset speed on a conveyor belt. These spectral data are generated by a high-energy laser source generating a high-temperature plasma on the surface of the bauxite sample, thereby exciting the emission spectra of the elements in the sample.

[0050] S120, performing a preprocessing operation on the n actual spectrum data to obtain a preprocessed actual spectrum data set;

[0051] Exemplarily, a preprocessing operation is performed on the collected n actual spectral data. The preprocessing operation may include but is not limited to noise removal, baseline correction, normalization, etc., so as to obtain a cleaner and standardized preprocessed actual spectral data set.

[0052] S130, calculating a screening distance between each preprocessed actual spectrum data set in the preprocessed actual spectrum data set and a class spectrum of alumina, and adding the preprocessed actual spectrum data set having the screening distance less than or equal to a preset distance to the valid spectrum data set, wherein the class spectrum is obtained by statically measuring a standard sample with known composition;

[0053] For example, by calculating the screening distance between each preprocessed actual spectral data set and the spectrum of a standard sample with known composition, spectral data with a distance less than or equal to a preset distance are screened out and added to the valid spectral data set. Furthermore, the standard sample spectra are measured under static conditions, ensuring the accuracy of the spectral data.

[0054] S140, taking the average value of the first m spectral data in the valid spectral data set as the actual continuous transmission spectral data;

[0055] For example, the average value of the first m spectral data in the valid spectral data set is calculated as the actual continuous transmission spectral data. This average value can represent the spectral characteristics of the bauxite sample to be tested during the continuous transmission process.

[0056] S150. Input the actual continuous transmission spectral data into an optimal model to obtain the bauxite composition corresponding to each spectral data, wherein the optimal model is based on standard continuous transmission spectral data, and the standard continuous transmission spectral data is the average value of the first m spectral data of the standard sample collected on the preset speed conveyor belt based on the LIBS system and obtained through the preprocessing operation and the screening distance operation.

[0057] For example, actual continuous transmission spectral data is fed into an optimization model, which then outputs the bauxite composition corresponding to each spectral data point. The optimization model is trained using standard continuous transmission spectral data, which is obtained by collecting standard sample spectra on a conveyor belt at a preset speed and then undergoing preprocessing and screening.

[0058] In summary, the methods of related technologies require manual sampling and laboratory analysis, with long time intervals and delayed analysis results. The present application uses LIBS technology to achieve online real-time detection of bauxite components, which can obtain data in a timely manner and guide the production process. Through preprocessing and screening operations, the high quality and accuracy of spectral data are ensured, human errors and external interference are reduced, and more accurate detection results are provided. Compared with the PGNAA method, LIBS technology avoids radiation risks and ensures the safety of operators. LIBS technology can be used for the detection of solid, liquid and gas samples, and does not require complex sample preparation, and is suitable for a variety of industrial environments. Through online detection and intelligent control, labor costs and laboratory analysis costs are reduced, while production efficiency and product quality are improved, and overall production costs are reduced. This solution provides a reliable online detection method for the alumina production process, promotes the automation, informatization and intelligent development of the production process, and enhances the competitiveness of the industry.

[0059] In some examples, this also includes:

[0060] preparing n1 bulk bauxite samples with different compositions, grinding them, and pressing them into tablets to form the above-mentioned standard samples;

[0061] Controlling the LIBS system to collect n1 standard spectral data of the standard sample in a static state;

[0062] Performing a preprocessing operation on the n1 standard spectral data to obtain a preprocessed standard spectral data set;

[0063] The average value of the spectral data in the preprocessed standard spectral data set is used as the category spectrum.

[0064] Exemplarily, n1 bulk samples are prepared from bauxite of different sources or compositions. These bulk samples are then ground and pressed to form uniform standard samples. Grinding and pressing processes help reduce the heterogeneity of the samples and improve the accuracy of the test results. The above-mentioned standard samples are tested in a static state using a LIBS system to collect n1 standard spectral data. Testing in a static state can ensure the stability and reliability of the spectral data. The collected n1 standard spectral data are preprocessed, and the preprocessing operations include but are not limited to denoising, baseline correction, normalization, etc., to obtain a more standardized preprocessed standard spectral data set. The average value of the spectral data in the preprocessed standard spectral data set is calculated as the category spectrum. The category spectrum represents the spectral characteristics of the standard sample and is used for the subsequent screening and comparison of actual spectral data.

[0065] In summary, preparing standard samples and performing pretreatment ensures the high quality and accuracy of the classification spectra, providing a reliable reference for subsequent actual testing. Grinding and tableting reduce sample heterogeneity and improve the consistency of test results. Collecting standard spectral data in a static state avoids fluctuations and errors that may occur during dynamic testing, ensuring the stability of spectral data. Standardized preprocessing and calculation of classification spectra facilitate the screening and comparison of subsequent actual spectral data, improving the efficiency and accuracy of data analysis.

[0066] In some examples, the step of preparing n1 bulk bauxite samples with different compositions and grinding and tableting them to form the standard sample comprises:

[0067] The above-mentioned bulk bauxite samples with different compositions refer to bauxite samples with different contents of elements; the particle size of the above-mentioned bulk bauxite samples is less than 20 mm, and the above-mentioned n1 is greater than or equal to 30;

[0068] The steps of the above-mentioned grinding and tableting process specifically include:

[0069] Grinding the bauxite sample using a mortar for a maximum time of less than 2 minutes to form a granular bauxite sample having a particle size of less than or equal to 2 μm;

[0070] The granular bauxite sample is pressed at a pressure of at least 15 MPa for at least 30 seconds to form the bulk bauxite sample.

[0071] For example, the bulk bauxite samples with different compositions are bauxites with different element contents. By selecting bauxites with different compositions, it is possible to ensure that the standard samples are diverse and more representative.

[0072] The particle size of bulk bauxite samples should be less than 20 mm, and at least 30 bulk samples with different compositions should be prepared to ensure the reliability and comprehensiveness of the data.

[0073] Grinding is performed in a mortar for a maximum of less than 2 minutes to prevent moisture absorption, resulting in a granular bauxite sample with a particle size of 2 μm or less. This particle size ensures a fine and uniform sample, facilitating subsequent spectral analysis.

[0074] The granular bauxite sample is pressed at a pressure of at least 15 MPa for at least 30 seconds. This high-pressure, short-time treatment method can form a dense, bulk bauxite sample, reduce internal voids, and improve sample uniformity and stability.

[0075] In summary, by selecting bauxite with different compositions, we ensure that the standard samples are representative and can cover various composition changes that may be encountered during the production process. During the sample preparation process, the sample particle size is controlled to be less than 20mm to ensure that the sample can be effectively processed during the grinding process. The particle size after grinding is required to be less than or equal to 2μm to ensure the fineness and uniformity of the sample, which is conducive to the accurate collection of spectral data. A pressure of at least 15MPa is used for tableting to ensure the density and stability of the sample, reduce internal voids, and avoid errors caused by sample heterogeneity during the detection process. The grinding operation time is less than 2 minutes to avoid moisture absorption, and the tableting operation time is at least 30 seconds to ensure that high-quality sample preparation is completed within a limited time and improve production efficiency.

[0076] In some examples, the preprocessing operation includes a baseline correction operation and a noise removal operation;

[0077] The baseline correction operation includes one or more of a derivative method, an iterative polynomial fitting method, and a penalty-based least squares method.

[0078] For example, the purpose of baseline correction is to eliminate baseline drift in spectral data, thereby improving the accuracy and reliability of spectral signals. Baseline correction methods can include the following:

[0079] Derivative method: Eliminate baseline drift by calculating the first or second derivative of the spectral data. This method can effectively remove low-frequency noise and baseline drift, but may also enhance high-frequency noise.

[0080] Iterative Polynomial Fitting: Estimates and eliminates baseline drift in spectra by iteratively fitting a polynomial. This method is highly flexible and can adapt to baselines of varying shapes.

[0081] Penalized least squares method: Baseline correction is achieved by introducing a penalty term to control the smoothness of the polynomial fit. This method can effectively preserve the main characteristics of the spectral signal while eliminating baseline drift.

[0082] The purpose of noise removal is to reduce noise interference in spectral data and improve the quality of spectral signals. Common noise removal methods include:

[0083] Filtering method: Remove high-frequency noise by using low-pass filters, median filters, etc.

[0084] Smoothing method: Smooth spectral data through sliding window averaging, Savitzky-Golay filtering and other methods to reduce noise.

[0085] The present application embodiment eliminates baseline drift and noise interference in the spectral data through baseline correction and noise removal operations, obtaining a more accurate spectral signal. By selecting a variety of baseline correction methods, the processing process is made more flexible, and the most appropriate method can be selected according to actual conditions to improve the data processing effect. The spectral data quality after pretreatment is higher, which reduces the errors in subsequent analysis, ensures the reliability of the spectral data, and provides strong support for accurately detecting bauxite components.

[0086] In some examples, the noise removal operation includes wavelet transform and / or Savitzky-Golay.

[0087] For example, both the wavelet transform and the Savitzky-Golay filter can effectively remove noise from spectral data and improve signal quality. The wavelet transform is highly efficient in processing time and frequency information, while the Savitzky-Golay filter excels in preserving signal peaks. Combining the two can simultaneously remove noise and preserve the key features of the spectral signal. Depending on the characteristics of the actual spectral data, the wavelet transform and / or the Savitzky-Golay filter can be selected to flexibly perform noise removal operations and improve preprocessing effects.

[0088] In some examples, the optimal model is a partial least squares regression model. 2 A model that evaluates detection accuracy and uses grid search methods for parameter tuning.

[0089] For example, the spectral data and bauxite composition data were centered and standardized, and the PLS regression method was used to establish a regression model between the input variable (spectral data) and the output variable (composition data). 2 As an evaluation index, the detection accuracy of the PLS regression model is measured. By calculating R 2 The value of the model is used to evaluate the explanatory power and accuracy of the model for the detection of bauxite components. The parameter grid of the PLS regression model (such as the number of latent variables) is defined, and the model performance of each parameter combination is evaluated through cross-validation. 2 The parameter combination with the highest value is used to obtain the optimal PLS regression model.

[0090] In summary, this embodiment establishes the relationship between spectral data and component data through PLS regression model, and 2 Evaluate the model's detection accuracy to ensure high-precision component detection capabilities. Use a grid search method for parameter tuning, systematically traversing parameter combinations to ensure the optimal PLS regression model and improve its reliability and stability. PLS regression models can effectively process high-dimensional spectral data and address multicollinearity issues, making them suitable for complex bauxite composition detection.

[0091] In some examples, the parameters tuned in the parameter tuning process include the number of principal components, the maximum number of iterations, and the convergence criterion.

[0092] For example, the number of principal components is an important parameter in partial least squares regression (PLS regression), which determines the number of latent variables extracted from the raw spectral data. Choosing an appropriate number of principal components can balance the complexity and explanatory power of the model, avoiding overfitting or underfitting.

[0093] The maximum number of iterations determines the upper limit of the number of iterations during the training process of the PLS regression model. Setting a reasonable maximum number of iterations can ensure that the model is fully optimized during the training process, but will not waste computing resources due to excessive iterations.

[0094] Convergence criteria are used to determine whether the model training process has reached an optimal state, usually measured by the change in the loss function. Setting appropriate convergence criteria can prevent the model from falling into a local optimal solution while ensuring that the training process completes within a reasonable time.

[0095] By using the grid search method, different numbers of principal components are tried to select the one that maximizes R 2 Ensure the model can fully extract the features of the spectral data while avoiding overfitting. Set the maximum number of iterations within a reasonable range and select the number of iterations that achieves the best model performance through cross-validation to ensure that the model is fully optimized during training. Adjust the threshold of the convergence criterion and select the most appropriate convergence criterion through cross-validation to ensure that the model can effectively converge during training and avoid falling into local optimal solutions.

[0096] In summary, the method proposed in the embodiment of the present application ensures that the PLS regression model has optimal performance on high-dimensional spectral data through systematic parameter tuning, thereby improving the accuracy and reliability of bauxite composition detection. The parameter range and value during the tuning process can be adjusted according to the specific spectral data characteristics, with high flexibility and adaptability. By reasonably setting the maximum number of iterations and convergence criteria, it is ensured that the model converges to the optimal solution within a reasonable time, thereby improving training efficiency and model stability.

[0097] In some examples, the Figure 2 The LIBS system shown here consists of a laser, spectrometer, detector, and time delay. The laser has a wavelength of 1064 nm, a single pulse energy of 100 mJ, and a repetition rate of 10 Hz; the spectrometer is a two-channel spectrometer with a wavelength range of 200 nm to 500 nm and a resolution of 0.1 nm; the detector has 2048 pixels; and the time delay has a delay of 300 ns. This system can detect the three elements Al, Fe, and Si in bauxite.

[0098] The specific steps include:

[0099] S201: Prepare n1 (up to 30) bulk bauxite samples with different compositions, grind and tablet them, and collect n1 standard spectral data to obtain a standard spectral data set.

[0100] Specifically: the particle size of the selected bauxite sample is less than 20 mm; the bauxite sample is ground in a mortar for 2 minutes to prevent moisture absorption, the particle size is controlled below 2 μm, and a pressure of 15 MPa is used for 30 seconds to prepare a tablet sample; Figure 2 The LIBS system shown in the figure collects bauxite spectral data. During the collection process, each sample is excited 10 times, and the average of the 10 spectral data is taken as the spectral data of a single sample. The data size of the bauxite spectral data set is (4096, 30).

[0101] S202: Preprocess the standard spectral data to reduce the baseline drift and continuous background interference in the standard spectral data, and obtain a preprocessed bauxite spectral data set. Baseline drift is the overall deviation of the spectrum caused by factors such as instrument drift and light source fluctuation, while continuous background interference is the spectral background signal caused by factors such as scattering and absorption of the sample. The first-order derivative is used to reduce the baseline drift in the spectrum, and the influence of the baseline drift on the spectrum is reduced by reducing the overall slope and fluctuation of the spectrum. The Savitzky-Golay method is used to reduce continuous background interference, and the data of the sliding pane is weighted filtered. While filtering and smoothing, the signal change information is effectively retained. The window width is 5 and the polynomial order is 3. The schematic diagram of the preprocessing results is shown as follows: Figure 3 shown.

[0102] S203: Take the average value of the spectrum data obtained by S201 and S202 as the bauxite category spectrum S. There are 30 spectrum data obtained by S101 and S102, which are respectively recorded as {I1, I2, ..., I 30}, bauxite class spectrum S is as follows Figure 4 As shown, it is calculated by the following formula:

[0103]

[0104] S204: Bauxite with known composition is transported from Figure 2 The LIBS system shown is driven downward to collect spectral data of bauxite, and then performs S102 to obtain a pre-processed spectral data set.

[0105] S205: Calculate the spectral distance L between each spectral data in the preprocessed spectral data set of S204 and S in S203, remove spectral data with L>1.0, remove spectral data that fails due to sample gaps, ensure data validity, and obtain a spectral data set.

[0106] The distance L is calculated as follows:

[0107]

[0108] In the above formula, S′ is a single spectral data in the preprocessed spectral data set, and xi is the spectral value of each band of the spectral data;

[0109] S206: Select the first m (can be 10) spectral data of the spectral data set obtained in S105 and average them as the spectral data of the first transmission. The belt transmission time of the first transmission is set to 2s, that is, the continuous placement distance of the sample is 3m.

[0110] S207: Repeat S204 to S206 90 times to obtain a modeling dataset, and divide the modeling dataset into a training set and a validation set according to a ratio of 7:3. The data size of the modeling dataset is (4096, 90).

[0111] S208: Use the training set and the validation set to establish a partial least squares regression model (PLSR) for the detection of three elemental components: Al, Fe, and Si, and use the coefficient of determination R 2 Evaluate detection accuracy.

[0112] Coefficient of determination R 2 , which indicates the degree of fit of the detection model to the data set. The higher the determination coefficient, the better the detection model fits. 2 The calculation method is:

[0113]

[0114] S209: Repeat S208 and use the grid search method to tune the parameters of PLSR until the R of the detection model is 2 Reach the optimum and save the optimal model.

[0115] PLSR parameters that require tuning include the number of principal components, the maximum number of iterations, and the convergence criterion. The number of principal components ranges from {2, 3, …, 200}, the maximum number of iterations ranges from {1e3, 1e4, 1e5, 1e6}, and the convergence criterion is set to 1e-4.

[0116] During the grid search process, the training set was divided into a parameter tuning training set and a parameter tuning verification set at a ratio of 4:1, and the grid search was performed. The optimal parameters obtained by the Al element composition detection model include the number of principal components 12, the maximum number of iterations 1e 3 and convergence criterion 1e -4 The optimal parameters of the Fe element composition detection model include the number of principal components 13, the maximum number of iterations 1e 3 and convergence criterion 1e -4 The optimal parameters of the Si element composition detection model include the number of principal components 16, the maximum number of iterations 1e 5 and convergence criterion 1e -4 .

[0117] S210: Repeat steps 104 to 105, and average every 10 spectral data to obtain the continuous transmission spectral data.

[0118] The belt transmission time of the continuous transmission is set to 4s, that is, the continuous placement distance of the sample is 6m. Since the transmission belt length is less than 6m, the block bauxite samples are continuously added to the transmission belt during the belt transmission process.

[0119] The data size of the continuous transmission spectrum data is (4096, n3). Since step 110 simulates a real production environment to test the composition of bauxite, n3 is not a fixed value, but it is necessary to ensure that n3 ≥ 2 during the test. Assuming that the spectrum data set obtained in step 105 contains n qualified spectra, n3 = n / m.

[0120] S211: Read the optimal model, input each spectral data of the continuous transmission spectral data into the optimal model, obtain the composition of the three elements Al, Fe, and Si in the bauxite corresponding to each spectral data, and average the obtained bauxite composition to obtain the composition detection values ​​of the three elements Al, Fe, and Si in the continuous transmission bauxite.

[0121] Figure 5This is a schematic diagram of the present invention's continuous transmission bauxite component detection. A total of 40 spectral data were collected in this detection. After spectral preprocessing, the distance from S was calculated. All 40 data met the requirements. By averaging every 10 spectra, we obtained Figure 5 Spectra 1 to 4 in the figure are calculated by the model to obtain components 1 to 4 corresponding to the four spectra. The Al, Fe, and Si elemental compositions are averaged to obtain the detection value of the bauxite composition of one continuous transmission.

[0122] In summary, the online detection method and system for bauxite composition disclosed in this application are different from traditional composition detection. Based on laser-induced breakdown spectroscopy technology and machine learning technology, bauxite composition information can be detected in real time without sampling and offline analysis. This application constructs a bauxite classification spectrum, screens out spectral data that is unqualified due to sample gaps, and improves the detection robustness of bulk samples on the production line. The use of spectral preprocessing technology eliminates baseline offset and background noise interference to a certain extent; the use of a three-level averaging strategy increases the representativeness of the detected data, improves the accuracy of online detection and analysis of bauxite composition, and promotes the application of online detection technology.

[0123] like Figure 6 As shown, this application proposes an online detection device for bauxite composition, comprising:

[0124] The acquisition unit 21 is used to control the LIBS system to acquire n actual spectral data of the bauxite to be tested on the conveyor belt at a preset speed;

[0125] A preprocessing unit 22 is used to perform a preprocessing operation on the n actual spectrum data to obtain a preprocessed actual spectrum data set;

[0126] a screening unit 23 configured to calculate a screening distance between each preprocessed actual spectrum data set in the preprocessed actual spectrum data set and the alumina class spectrum, and add the preprocessed actual spectrum data sets having the screening distance less than or equal to a preset distance to the effective spectrum data set, wherein the class spectrum is obtained by statically measuring a standard sample with known composition;

[0127] an averaging unit 24, configured to take the average of the first m spectral data in the valid spectral data set as the actual continuous transmission spectral data;

[0128] An acquisition unit 25 is configured to input the actual continuous transmission spectral data into an optimal model to obtain the bauxite composition corresponding to each piece of spectral data, wherein the optimal model is based on standard continuous transmission spectral data, which is the average of the first m spectral data of the standard sample collected on the preset speed conveyor belt based on the LIBS system and obtained through the preprocessing operation and the screening distance operation.

[0129] like Figure 7 As shown, an embodiment of the present application further provides an electronic device 300, comprising a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for online detection of bauxite composition are implemented.

[0130] Since the electronic device introduced in this embodiment is a device used to implement an online detection device for bauxite composition in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application falls within the scope of protection of this application.

[0131] In the specific implementation process, the computer program 311 can be implemented when executed by the processor Figure 1 Any implementation manner in the corresponding embodiments.

[0132] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0133] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0137] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of online detection of bauxite composition in the corresponding embodiment.

[0138] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0139] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0141] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0142] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0143] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0144] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for online detection of bauxite components, characterized in that: include: Control the LIBS system to collect n actual spectral data on the bauxite to be tested on the conveyor belt at a preset speed; performing a preprocessing operation on the n actual spectral data to obtain a preprocessed actual spectral data set; Calculating a screening distance between each preprocessed actual spectral data set and the alumina category spectrum in the preprocessed actual spectral data set, and adding the preprocessed actual spectral data sets with the screening distance less than or equal to a preset distance to the effective spectral data set, wherein the category spectrum is a standard sample with known composition measured in a static manner, and the screening distance is a Euclidean distance; taking an average value of every m pieces of spectrum data in the effective spectrum data set as actual continuous transmission spectrum data, wherein the actual continuous transmission spectrum data includes a plurality of spectrum data; The actual continuous transmission spectral data is input into the optimal model to obtain the bauxite composition corresponding to each spectral data, wherein the optimal model is based on standard continuous transmission spectral data, and the standard continuous transmission spectral data is the average value of every m spectral data obtained by collecting the standard sample on the preset speed conveyor belt based on the LIBS system and undergoing the preprocessing operation and the screening distance operation.

2. The method for online detection of bauxite composition according to claim 1, characterized in that: Also includes: preparing n1 bulk bauxite samples with different compositions and grinding and tableting them to form the standard samples; Controlling the LIBS system to collect n1 standard spectrum data of the standard sample in a static state; performing a preprocessing operation on the n1 standard spectral data to obtain a preprocessed standard spectral data set; The average value of the spectral data in the preprocessed standard spectral data set is used as the category spectrum.

3. The method for online detection of bauxite composition according to claim 2, characterized in that: The step of preparing n1 bulk bauxite samples with different compositions and grinding and tableting them to form the standard sample comprises: The bulk bauxite samples with different compositions refer to bauxite samples with different contents of elements; the particle size of the bulk bauxite samples is less than 20 mm, and the n1 is greater than or equal to 30; The steps of grinding and tableting specifically include: Grinding the bauxite sample using a mortar for a maximum time of less than 2 minutes to form a granular bauxite sample having a particle size of less than or equal to 2 μm; The granulated bauxite sample is pressed at a pressure of at least 15 MPa for at least 30 seconds to form the bulk bauxite sample.

4. The method for online detection of bauxite composition according to claim 1 or 2, characterized in that: The pre-processing operation includes a baseline correction operation and a noise removal operation; The baseline correction operation includes one or more of a derivative method, an iterative polynomial fitting method, and a penalty-based least squares method.

5. The method for online detection of bauxite composition according to claim 4, characterized in that: The noise removal operation includes wavelet transform and / or Savitzky-Golay.

6. The method for online detection of bauxite composition according to claim 1, characterized in that: The optimal model is a partial least squares regression model, and the optimal model is the R 2 A model that evaluates detection accuracy and uses grid search methods for parameter tuning.

7. The method according to claim 6, characterized in that The parameters tuned in the parameter tuning process include the number of principal components, the maximum number of iterations and the convergence standard.

8. An online detection device for bauxite composition, characterized in that: include: An acquisition unit, used to control the LIBS system to acquire n actual spectral data on the bauxite to be tested on a conveyor belt at a preset speed; a preprocessing unit, configured to perform a preprocessing operation on the n actual spectral data to obtain a preprocessed actual spectral data set; a screening unit, configured to calculate a screening distance between each preprocessed actual spectral data set and the alumina class spectrum in the preprocessed actual spectral data set, and add the preprocessed actual spectral data sets having the screening distance less than or equal to a preset distance to the effective spectral data set, wherein the class spectrum is a standard sample of known composition obtained by static measurement, and the screening distance is a Euclidean distance; an averaging unit, configured to use an average value of every m pieces of spectrum data in the valid spectrum data set as actual continuous transmission spectrum data, wherein the actual continuous transmission spectrum data includes a plurality of spectrum data; an acquisition unit, configured to input the actual continuous transmission spectral data into an optimal model to obtain a bauxite composition corresponding to each piece of spectral data, wherein the optimal model is based on standard continuous transmission spectral data, and the standard continuous transmission spectral data is an average value of every meter of spectral data obtained by collecting the standard sample on the preset speed conveyor belt based on the LIBS system and undergoing the preprocessing operation and the screening distance operation.

9. An electronic device comprising: A memory and a processor, wherein the processor is configured to implement the steps of the method for online detection of bauxite composition according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the on-line detection method for bauxite composition according to any one of claims 1 to 7 are implemented.

Images