A method and system for measuring and analyzing ion concentration of raw ore

Abstract

The present invention discloses a method and system for measuring and analyzing the ion concentration of raw ore, which relates to the technical field of ion concentration analysis, including collecting spectral data of raw ore samples through a collection device and performing standardization processing; using a Gaussian model to extract features of the collected spectral data and construct a characteristic variable set; analyzing feature weights according to the features of the characteristic variable set, and calculating a comprehensive prediction value for the ion concentration of the sample through the feature weights. The method of the present invention can accurately extract the absorption peak features in the spectral data by smoothing and Gaussian fitting the spectral data, effectively integrate more spectral information through the feature weight function, improve the model's processing ability for complex spectral signals, and thus improve the prediction accuracy, and comprehensively consider multiple dimensional information of the spectral data through the calculation of the comprehensive prediction function, and accurately describe the influence of the characteristic variables within their wavelength range.

Description

Technical Field

[0001] The invention relates to the technical field of ion concentration analysis, in particular to a method and system for measuring and analyzing the ion concentration of a raw ore. Background Art

[0002] The measurement and analysis of ion concentration of raw ore is a key link in mineral exploration, resource assessment and mining production. Traditional ion concentration measurement methods mainly include chemical titration, atomic absorption spectroscopy and inductively coupled plasma mass spectrometry. These methods have high accuracy and sensitivity and are widely used in the determination of ion concentration of various mineral samples. However, these methods usually require complex pre-treatment steps and expensive instruments and equipment, and the operation is time-consuming, which is not conducive to the rapid analysis of large-scale samples.

[0003] With the development of spectral technology and computer science, spectral analysis has gradually become an emerging technology for measuring the ion concentration of raw ores. Although spectral analysis has many advantages in measuring the ion concentration of raw ores, the existing processing methods often only focus on a single feature or a simple combination of features and fail to fully utilize the rich information in the spectral data. This leads to insufficient model prediction accuracy and limits the widespread application of spectral analysis. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing measurement and analysis methods and systems for raw ore ion concentration, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the existing processing methods often only focus on a single feature or a simple feature combination, and fail to fully utilize the rich information in the spectral data, which leads to insufficient model prediction accuracy and limits the widespread application of spectral analysis.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for measuring and analyzing the ion concentration of raw ore, comprising:

[0007] The spectral data of the raw ore samples are collected through the collection equipment and standardized;

[0008] Use the Gaussian model to extract features from the collected spectral data and construct a set of characteristic variables;

[0009] Analyze the feature weights according to the features of the feature variable set, and calculate the comprehensive prediction value of the ion concentration of the sample through the feature weights;

[0010] The maximum and minimum thresholds are set based on historical data to determine the credibility of the comprehensive prediction value, and the spectral data is stored and backed up through wireless encrypted transmission and local storage media.

[0011] As a preferred solution of the method for measuring and analyzing the ion concentration of the raw ore of the present invention, the spectral data of the raw ore sample is collected by the collection device and standardized, including:

[0012] Select the raw ore sample to be tested, and use the UV-visible spectrophotometer to collect the sample spectrum data;

[0013] The collected spectral data were preprocessed, the background noise in the spectral data was removed using the baseline correction method, and the spectral data were standardized.

[0014] As a preferred solution of the measurement and analysis method of the raw ore ion concentration of the present invention, wherein: the Gaussian model is used to extract features from the collected spectral data to construct a feature variable set, including:

[0015] The Savitzky-Golay filter is used to smooth the spectral data, and the Gaussian model is used to fit the smoothed spectral data, including:

[0016] Calculate the Gaussian absorption value at wavelength λ:

[0017]

[0018] Where G(λ) represents the Gaussian absorption value of wavelength λ, A represents the peak height, μ represents the central wavelength of the absorption peak, and σ represents the width of the absorption peak;

[0019] Calculate the Gaussian model fitting error, and the error function is expressed as:

[0020]

[0021] Where E represents the fitting error value, N represents the number of data points, S'(λ i ) represents the spectrum data after smoothing of the i-th wavelength, G(λ i ) represents the Gaussian absorption value of the i-th wavelength λ;

[0022] Use the gradient descent method to minimize the error function E and determine the optimal A, μ, and σ.

[0023] Record the wavelength λ of each absorption peak i and peak height A i , and combined into a set of feature variables, expressed as:

[0024] F={(λ1,A1), (λ2,A2),…, (λ i ,A i )};

[0025] Where F represents the set of characteristic variables, A irepresents the peak height of the i-th absorption peak, λ i represents the wavelength of the i-th absorption peak.

[0026] As a preferred solution of the method for measuring and analyzing the ion concentration of the raw ore of the present invention, wherein: the characteristic weight of the characteristic analysis based on the characteristic variable set includes:

[0027] The wavelength λ of each absorption peak based on the characteristic variable set F i and peak height A i , and set the integration range based on the width σ of the absorption peak;

[0028] Integral calculation is introduced to accumulate the weight value of each feature and calculate the feature weight, which is expressed as:

[0029]

[0030] Where W(λ i ,A i ) represents the i-th feature weight, and κ is represented as an integral variable.

[0031] As a preferred embodiment of the method for measuring and analyzing the ion concentration of the raw ore of the present invention, the method of calculating the comprehensive prediction value of the ion concentration of the sample by the feature weight includes:

[0032] Calculate the exponential decay integral part D of each feature i , expressed as:

[0033]

[0034] Where T represents the temperature constant;

[0035] Based on the calculation of each feature weight and the exponential decay integral part in the feature variable set F, the comprehensive prediction of ion concentration is achieved by summing up, which is expressed as:

[0036]

[0037] Where P(F) represents the comprehensive predicted value of ion concentration, and M represents the number of features.

[0038] As a preferred solution of the measurement and analysis method of the raw ore ion concentration of the present invention, wherein: the maximum threshold and the minimum threshold are set based on historical data to determine the credibility of the comprehensive prediction value, including:

[0039] Based on the application scenario's demand for raw ore ion concentration and historical data, calculate the mean of historical raw ore sample ion concentrations And standard deviation τ, and set the maximum threshold and minimum threshold for threshold determination, expressed as:

[0040]

[0041]

[0042] Where P min represents the minimum threshold, P max represents the maximum threshold;

[0043] If P min <P(F)≤P max When , it means that the predicted value is reliable;

[0044] If P min ≥P(F) and P(F)>P max , it means that there is an error in the calculation of the predicted value, and the spectral data is re-collected to predict the original ore ion concentration.

[0045] As a preferred solution of the method for measuring and analyzing the ion concentration of the raw ore of the present invention, the spectral data is stored and backed up through wireless encrypted transmission and local storage media, including:

[0046] After the calculation of the comprehensive prediction value P(F) and the threshold determination, the spectral data is encrypted using the AES encryption standard, and the encrypted spectral data is stored in a local storage medium;

[0047] The spectral data is transmitted wirelessly via a wireless network, and the transmission of the spectral data is encrypted by the Secure Sockets Layer (SSL), and the spectral data is transmitted to a cloud service platform for backup storage.

[0048] Another object of the present invention is to provide a system for measuring and analyzing the ion concentration of raw ore, which comprises:

[0049] The spectrum data acquisition module collects spectrum data of the raw ore sample through the ultraviolet visible spectrophotometer equipment and pre-processes the collected spectrum data;

[0050] The feature extraction module uses the Gaussian model to extract features from the standardized spectral data, identifies and extracts the main absorption peaks in the spectrum, and constructs a set of feature variables;

[0051] The feature prediction module performs feature weight analysis based on the feature variable set, calculates the weight of each feature, and uses the feature weight to make a comprehensive prediction of the ion concentration of the sample;

[0052] A threshold determination module sets a maximum threshold and a minimum threshold based on historical data and performs threshold determination on the comprehensive prediction value;

[0053] The data storage module stores and backs up data through wireless encrypted transmission and local storage media.

[0054] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned method for measuring and analyzing the ion concentration of the raw ore when executing the computer program.

[0055] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for measuring and analyzing the ion concentration of the raw ore.

[0056] The beneficial effects of the present invention are as follows: by smoothing and Gaussian fitting the spectral data, the absorption peak characteristics in the spectral data can be accurately extracted; more spectral information can be effectively integrated through the characteristic weight function, thereby improving the model's processing capability for complex spectral signals, thereby improving the prediction accuracy; through the calculation of the comprehensive prediction function, the multi-dimensional information of the spectral data is fully considered, the influence of the characteristic variables within their wavelength range is accurately described, ensuring that the contribution of each feature to the prediction result is accurately evaluated, thereby improving the model's anti-noise capability and robustness. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0058] Figure 1 Schematic diagram of the flow chart of the measurement and analysis method of the raw ore ion concentration.

[0059] Figure 2 This is a schematic diagram of the structure of the measurement and analysis system for the raw ore ion concentration. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0063] Example 1

[0064] Reference Figure 1 , which is the first embodiment of the present invention, provides a method for measuring and analyzing the ion concentration of a raw ore, and the method for measuring and analyzing the ion concentration of a raw ore includes:

[0065] S1, collect the spectral data of the raw ore sample through the acquisition equipment and perform standardization processing;

[0066] Preferably, the spectral data of the raw ore sample is collected by a collection device and standardized, including:

[0067] Select the raw ore sample to be tested and use a UV-visible spectrophotometer to collect the sample spectrum data. The spectrum data should cover the wavelength range from 200nm to 800nm;

[0068] The collected spectral data were preprocessed, the background noise in the spectral data was removed using the baseline correction method, and the spectral data were standardized.

[0069] The calibration of the spectrophotometer ensures the accuracy and stability of the measurement results and improves the credibility of the data. The baseline correction removes the background noise, extracts the effective spectral signal, and enhances the signal-to-noise ratio of the data. The standardized spectral data eliminates the spectral intensity differences between different samples, making the data on the same scale, which is convenient for comparison and analysis, ensuring the consistency of the data and improving the accuracy of subsequent analysis and modeling. The standardized spectral data input provides a reliable basis for subsequent feature extraction and model building, reducing analytical errors caused by data problems.

[0070] S2, using the Gaussian model to extract features from the collected spectral data and construct a set of characteristic variables;

[0071] Preferably, a Gaussian model is used to extract features from the collected spectral data to construct a feature variable set, including:

[0072] The Savitzky-Golay filter is used to smooth the spectral data and remove high-frequency noise, which is expressed as:

[0073]

[0074] Where S'(λ) represents the spectrum data after wavelength λ smoothing, S(λ) represents the original spectrum data at wavelength λ, and c k represents the filter coefficient, m represents half of the filter window size, △λ represents the wavelength interval, and k represents the offset of each data point in the filter window relative to the center point wavelength λ;

[0075] Use the Gaussian model to fit the smoothed spectral data, including:

[0076] Calculate the Gaussian absorption value at wavelength λ:

[0077]

[0078] Where G(λ) represents the Gaussian absorption value of wavelength λ, A represents the peak height, μ represents the central wavelength of the absorption peak, and σ represents the width of the absorption peak;

[0079] Calculate the Gaussian model fitting error, and the error function is expressed as:

[0080]

[0081] Where E represents the fitting error value, N represents the number of data points, S'(λ i ) represents the spectrum data after smoothing of the i-th wavelength, G(λ i ) represents the Gaussian absorption value of the i-th wavelength λ;

[0082] Use the gradient descent method to minimize the error function E and determine the optimal A, μ, and σ.

[0083] Record the wavelength λ of each absorption peak i and peak height A i , and combined into a set of feature variables, expressed as:

[0084] F={(λ1,A1), (λ2,A2),…, (λ i ,A i )};

[0085] Where F represents the set of characteristic variables, A i represents the peak height of the i-th absorption peak, λ i represents the wavelength of the i-th absorption peak.

[0086] By smoothing the spectral data, high-frequency noise in the spectral data can be effectively removed, and the main features of the signal can be retained, thereby improving the signal-to-noise ratio of the data. The smoothed spectral data is smoother and more continuous, which is helpful for subsequent feature extraction and modeling, and improves data quality. Through Gaussian fitting, the absorption peak features in the spectral data can be accurately extracted. By minimizing the fitting error, the accuracy of the fitting results is ensured, and the feature extraction accuracy is improved. Through the construction of a set of characteristic variables, the extracted features are systematically recorded, which is convenient for subsequent data analysis and model building, and improves the systematic and scientific nature of data management.

[0087] S3, analyzing feature weights according to the features of the feature variable set, and calculating a comprehensive prediction value for the ion concentration of the sample through the feature weights;

[0088] Preferably, the feature weights are analyzed based on the features of the feature variable set, including:

[0089] The wavelength λ of each absorption peak based on the characteristic variable set F i and peak height A i , and set the integration range based on the width σ of the absorption peak;

[0090] Integral calculation is introduced to accumulate the weight value of each feature and calculate the feature weight, which is expressed as:

[0091]

[0092] Where W(λ i ,A i ) represents the i-th feature weight. The weight of each feature is a specific value used to reflect the feature λ i and A i The influence of κ is expressed as an integral variable, which is used to calculate the function value in a specific interval;

[0093] Select the integration range in [λ i -σ,λ i +σ] allows the characteristics of Gaussian distribution to be within this range, which can effectively describe the data distribution around the characteristic wavelength. The standard deviation σ represents the width of the absorption peak, so that most of the characteristic information can be included in this integral range;

[0094] Gaussian function can effectively describe the shape and distribution of absorption peaks in spectral data and has a good fitting effect. i , i and σ correspond to the height, wavelength, and width of the absorption peak, respectively, so that the calculation of the Gaussian function can accurately reflect the spectral characteristics;

[0095] The denominator of the formula is used as a normalization factor to ensure that the integral of the Gaussian distribution is 1, making the calculation result standardized. The numerator is used as the exponential part. Describes the distance between wavelength λ and the center wavelength λ i The degree of deviation ensures that the farther away from the central wavelength, the smaller the contribution, which is in line with physical reality.

[0096] By calculating the feature weights, each absorption peak feature of the feature variable set is taken into account. By accumulating the influence area of ​​the features around their wavelengths, an accurate feature description is provided. This not only takes into account the local influence of the features, but also integrates the global spectral information to ensure that the model's weight assignment for each feature is more accurate. The smoothing characteristics of the Gaussian integral effectively reduce the high-frequency noise in the data, making feature extraction more accurate, thereby improving the model's predictive performance. By calculating the weight of each feature, the model can clearly explain which features play a key role in the prediction. The weight assignment method in the form of Gaussian integral is based on statistical principles and provides a solid theoretical foundation, increasing the credibility and interpretability of the model. By accumulating the influence area of ​​the features around their wavelengths, the feature weight function effectively integrates more spectral information, improving the model's ability to process complex spectral signals, thereby improving the prediction accuracy. Compared with simple linear weighting methods, the Gaussian integral form is more flexible and accurate, and can better capture the nonlinear relationship between features, improving the adaptability and robustness of the model.

[0097] Furthermore, the comprehensive prediction value of the ion concentration of the sample is calculated by the feature weight, including:

[0098] Calculate the exponential decay integral part D of each feature i , expressed as:

[0099]

[0100] Where T represents the temperature constant, which indicates the temperature influence during spectral measurement. The reported temperature constant T value can be obtained by consulting the literature in related fields, and the spectral measurement can be performed using standard samples at known temperatures to verify the accuracy of the literature data and ensure that the standard samples have similar physical and chemical properties to the actual samples under the measurement conditions.

[0101] Based on the calculation of each feature weight and the exponential decay integral part in the feature variable set F, the comprehensive prediction of ion concentration is achieved by summing up, which is expressed as:

[0102]

[0103] Where P(F) represents the comprehensive predicted value of ion concentration, and M represents the number of features;

[0104] The calculation of formula P(F) is done by introducing the feature weight function W(λ i ,A i ), not only the individual contribution of each feature is considered, but also their influence area around the wavelength, thus improving the accuracy of the prediction. Formula D i middle The part indicates that as the wavelength increases, the characteristic intensity decays exponentially. This is consistent with the actual situation in spectral measurement that the characteristic intensity gradually decreases as the wavelength increases. Formula D i middle It is a normalization factor that ensures that the results of the integration are consistent and comparable under different temperature conditions. It reflects the influence of temperature on the characteristic intensity distribution, so that the model can adapt to different experimental conditions. The integration range is from 0 to ∞, which means that all possible wavelength ranges are taken into account, ensuring the comprehensiveness of the calculation.

[0105] Through the calculation of the comprehensive prediction function, the weight of each feature and the integral of the exponential decay model are combined, and the multi-dimensional information of the spectral data is fully considered, thereby improving the accuracy of the prediction. Through the Gaussian integral and exponential decay model, the influence of the characteristic variable within its wavelength range is accurately described, ensuring that the contribution of each feature to the prediction result is accurately evaluated. Through the Gaussian integral and exponential decay model, the interference of noise on the prediction result can be effectively reduced, and the noise resistance and robustness of the model are improved. Through integration and weighted summation, the comprehensive prediction function can efficiently integrate the information of multiple features, reduce the need for multiple iterations and complex calculations, and improve the overall calculation efficiency. Through clear feature weights and prediction results, the subsequent data processing and model optimization process are simplified, making the calculation more concise and efficient. Through the calculation of the exponential decay model integral, the influence of temperature on the characteristic intensity distribution is reflected, and the influence of the characteristic wavelength on the predicted value is described. The exponential decay model can effectively deal with the situation where the influence of wavelength on the predicted value gradually decreases with increasing distance, so that the formula can adapt to different experimental conditions and reasonably describe the attenuation effect of spectral characteristics, accumulate the contribution of characteristic variables in the entire wavelength range, and ensure the comprehensiveness and accuracy of the model.

[0106] S4, setting the maximum threshold and the minimum threshold based on the historical data, determining the credibility of the comprehensive prediction value, and storing and backing up the spectral data through wireless encrypted transmission and local storage media;

[0107] Preferably, the maximum threshold and the minimum threshold are set based on historical data to determine the credibility of the comprehensive prediction value, including:

[0108] Based on the application scenario's demand for raw ore ion concentration and historical data, calculate the mean of historical raw ore sample ion concentrations And standard deviation τ, and set the maximum threshold and minimum threshold for threshold determination, expressed as:

[0109]

[0110]

[0111] Where P min represents the minimum threshold, P max represents the maximum threshold;

[0112] If P min <P(F)≤P max When , it means that the predicted value is reliable;

[0113] If P min ≥P(F) and P(F)>P max , it means that there is an error in the calculation of the predicted value, and the spectral data is re-collected to predict the original ore ion concentration.

[0114] By setting a reasonable threshold range and adjusting it based on historical data and application requirements, unreliable prediction results can be effectively filtered out, improving the reliability and practical application value of the prediction. The threshold determination step can ensure the credibility of the measurement results and avoid misjudgment caused by noise or outliers, thereby improving the overall performance and accuracy of the system.

[0115] Furthermore, the spectral data is stored and backed up via wireless encrypted transmission and local storage media, including:

[0116] After the calculation of the comprehensive prediction value P(F) and the threshold determination, the spectral data is encrypted using the AES encryption standard, and the encrypted spectral data is stored in a local storage medium;

[0117] The spectral data is transmitted wirelessly via a wireless network, and the transmission of the spectral data is encrypted by the Secure Sockets Layer (SSL), and the spectral data is transmitted to a cloud service platform for backup storage.

[0118] By encrypting the transmission and storage of the comprehensive prediction value P(F) and spectral data, the confidentiality, integrity and overall security of the data can be significantly improved. It can not only prevent data leakage and tampering, but also transmit and store the backup data on the cloud platform, providing a safe and reliable data processing and storage environment for the ion concentration measurement and analysis system.

[0119] Example 2

[0120] Reference Figure 2 , which is the second embodiment of the present invention, is different from the previous embodiment and provides a method and system for measuring and analyzing the ion concentration of raw ore, including:

[0121] The spectrum data acquisition module collects spectrum data of the raw ore sample through the ultraviolet visible spectrophotometer equipment and pre-processes the collected spectrum data;

[0122] The feature extraction module uses the Gaussian model to extract features from the standardized spectral data, identifies and extracts the main absorption peaks in the spectrum, and constructs a set of feature variables;

[0123] The feature prediction module performs feature weight analysis based on the feature variable set, calculates the weight of each feature, and uses the feature weight to make a comprehensive prediction of the ion concentration of the sample;

[0124] A threshold determination module sets a maximum threshold and a minimum threshold based on historical data and performs threshold determination on the comprehensive prediction value;

[0125] The data storage module stores and backs up data through wireless encrypted transmission and local storage media.

[0126] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0127] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0128] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0129] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for measuring and analyzing the ion concentration of raw ore, characterized in that: include, The spectral data of the raw ore samples are collected through the collection equipment and standardized; Use the Gaussian model to extract features from the collected spectral data and construct a set of characteristic variables; Analyze the feature weights according to the features of the feature variable set, and calculate the comprehensive prediction value of the ion concentration of the sample through the feature weights; Set the maximum and minimum thresholds based on historical data, determine the credibility of the comprehensive prediction value, and store and back up the spectral data through wireless encrypted transmission and local storage media; The spectral data of the raw ore sample is collected by the collection device and standardized, including: Select the raw ore sample to be tested, and use the UV-visible spectrophotometer to collect the sample spectrum data; Preprocess the collected spectral data, use the baseline correction method to remove the background noise in the spectral data, and standardize the spectral data; The Gaussian model is used to extract features from the collected spectral data and construct a feature variable set, including: The Savitzky-Golay filter is used to smooth the spectral data, and the Gaussian model is used to fit the smoothed spectral data, including: Calculate the Gaussian absorption value at wavelength λ: Where G(λ) represents the Gaussian absorption value of wavelength λ, A represents the peak height, μ represents the central wavelength of the absorption peak, and σ represents the width of the absorption peak; Calculate the Gaussian model fitting error, and the error function is expressed as: Where E represents the fitting error value, N represents the number of data points, S'(λ i ) represents the spectrum data after smoothing of the i-th wavelength, G(λ i ) represents the Gaussian absorption value of the i-th wavelength λ; Use the gradient descent method to minimize the error function E and determine the optimal A, μ, and σ. Record the wavelength λ of each absorption peak i and peak height A i , and combined into a set of feature variables, expressed as: F={(λ1,A1),(λ2,A2),……,(λ i ,A i )}; Where F represents the set of characteristic variables, A i represents the peak height of the i-th absorption peak, λ i represents the wavelength of the i-th absorption peak; The feature weights according to the feature analysis of the feature variable set include: The wavelength λ of each absorption peak based on the characteristic variable set F i and peak height A i , and set the integration range based on the width σ of the absorption peak; Integral calculation is introduced to accumulate the weight value of each feature and calculate the feature weight, which is expressed as: Where W(λ i ,A i ) represents the i-th feature weight, and κ represents the integral variable; The comprehensive prediction value of the ion concentration of the sample is calculated by the feature weight, including: Calculate the exponential decay integral part D of each feature i , expressed as: Where T represents the temperature constant; Based on the calculation of each feature weight and the exponential decay integral part in the feature variable set F, the comprehensive prediction of ion concentration is achieved by summing up, which is expressed as: Where P(F) represents the comprehensive predicted value of ion concentration, and M represents the number of features; The method of setting a maximum threshold and a minimum threshold based on historical data and determining the credibility of the comprehensive prediction value includes: Based on the application scenario's demand for raw ore ion concentration and historical data, calculate the mean of historical raw ore sample ion concentrations And standard deviation τ, and set the maximum threshold and minimum threshold for threshold determination, expressed as: Where P min represents the minimum threshold, P max represents the maximum threshold; If P min <P(F)≤P max When , it means that the predicted value is reliable; If P min ≥P(F) and P(F)>P max , it means that there is an error in the calculation of the predicted value, and the spectral data is re-collected to predict the original ore ion concentration.

2. The method for measuring and analyzing the ion concentration of raw ore according to claim 1, characterized in that: The storage and backup of spectral data through wireless encrypted transmission and local storage media includes: After the calculation of the comprehensive prediction value P(F) and the threshold determination, the spectral data is encrypted using the AES encryption standard, and the encrypted spectral data is stored in a local storage medium; The spectral data is transmitted wirelessly via a wireless network, and the transmission of the spectral data is encrypted by the Secure Sockets Layer (SSL), and the spectral data is transmitted to a cloud service platform for backup storage.

3. A system based on the measurement and analysis method of raw ore ion concentration according to any one of claims 1-2, characterized in that: include, The spectrum data acquisition module collects spectrum data of the raw ore sample through the ultraviolet visible spectrophotometer equipment and pre-processes the collected spectrum data; The feature extraction module uses the Gaussian model to extract features from the standardized spectral data, identifies and extracts the main absorption peaks in the spectrum, and constructs a set of feature variables; The feature prediction module performs feature weight analysis based on the feature variable set, calculates the weight of each feature, and uses the feature weight to make a comprehensive prediction of the ion concentration of the sample; A threshold determination module sets a maximum threshold and a minimum threshold based on historical data and performs threshold determination on the comprehensive prediction value; The data storage module stores and backs up data through wireless encrypted transmission and local storage media.

4. A computer device comprising: Memory and processor; The memory stores a computer program, wherein the processor implements the steps of the method for measuring and analyzing the ion concentration of the raw ore according to any one of claims 1 to 2 when executing the computer program.

5. 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 method for measuring and analyzing the ion concentration of raw ore according to any one of claims 1 to 2 are implemented.

Images