Online detection system and method for solid waste in iron ore

Through near-infrared spectroscopy technology, the iron ore and solid waste database is established, real-time, non-destructive and radioactive online detection of iron ore is achieved, solving the problems of low efficiency and high maintenance costs in the existing technology, reducing detection costs and supporting Easy to exchange and share data.

CN119023613APending Publication Date: 2024-11-26SHANGHAI BAOSIGHT SOFTWARE CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411014463.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing iron ore composition detection methods are mainly offline laboratory testing, which is inefficient and has the use of radioactive equipment, resulting in high maintenance costs and the inability to achieve real-time and lossless online testing.

Method used

A database of iron ore and solid waste is established using near-infrared spectroscopy technology, and real-time detection is carried out through a near-infrared spectroscopy detection device to calculate the spectral similarity to determine whether solid waste is contained, so as to achieve online detection without radioactive and non-destructive sampling.

Benefits of technology

Real-time and non-destructive testing of iron ore components is realized, testing costs are reduced, the impact of changes in transportation volume is avoided, and it supports the easy exchange, sharing and iteration of imported typical iron ore and solid waste.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119023613A_ABST
    Figure CN119023613A_ABST
Patent Text Reader

Abstract

The invention provides an on-line detection method and system for solid wastes in iron ore. The method comprises the following steps: S1, establishing a near infrared spectrum database of sample iron ore meeting preset requirements; s2, acquiring a near infrared reflection spectrum of the to-be-detected iron ore by using a near infrared spectrum detection device, and pretreating the acquired near infrared reflection spectrum of the to-be-detected iron ore; s3, calculating the similarity between the near-infrared reflection spectrum of the to-be-detected iron ore and the spectrum in the near-infrared spectrum database, and when the similarity is smaller than a preset value, considering that the current to-be-detected iron ore contains solid wastes; and when the similarity is greater than a preset value, determining that the current to-be-detected iron ore does not contain solid wastes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of on-line detection of solid waste in iron ore, and in particular to an on-line detection system and method for solid waste in iron ore. Background Art

[0002] The screening of suspected or adulterated solid waste is the focus of customs supervision on imported iron ore. The most important part of solid waste inspection of iron ore is ore composition testing. The composition testing can determine the ore grade and quality, and then make a solid waste determination.

[0003] The traditional method for detecting iron ore composition is offline laboratory testing. Common methods include wet chemical analysis, inductively coupled plasma mass spectrometry (ICM-MS), and X-ray fluorescence spectroscopy (XRF). The test results are relatively accurate, but offline testing takes a long time and can only be performed by sampling, so the overall efficiency is not high.

[0004] The online detection technology of ore composition eliminates the steps of manual sampling, sample preparation, and testing, analyzes the ore in real time and sends the results to the control system. It has the characteristics of strong representativeness of ore composition, real-time reliability, reduced sampling personnel, and reduced production costs. At present, the mainstream technology for online detection of ore composition is prompt gamma-ray neutron activation technology (PGNAA).

[0005] The main advantage of neutron activation technology is that it can conduct penetrating and overall detection of samples without being affected by the surface conditions of the ore. However, the equipment is radioactive, and the licensing and operation are relatively complicated. The radiation source and neutron tube need to be replaced every two years, and the subsequent maintenance cost is high.

[0006] Patent document CN116148212A (application number: 202310430858.0) discloses a method for quickly determining the type and content of clay minerals in ores based on near-infrared spectroscopy analysis, which relates to the field of analysis. The method includes: S1. Collecting ore samples and pre-processing the samples; S2. Comprehensively analyzing the samples using chemical analysis and automatic mineral analysis to obtain the type and content of clay minerals in the samples; S3. Collecting the raw near-infrared spectrum data of the samples using a near-infrared spectrometer; S4. Pre-processing the raw near-infrared spectrum data and eliminating abnormal samples; S5. Randomly dividing the remaining samples into a calibration sample set and a verification sample set; S6. Using the data of the calibration sample set to establish a calibration model; S7. Optimizing the calibration model to obtain a prediction model; S8. Using the prediction model to predict and determine the type and content of clay minerals in the sample to be analyzed.

[0007] Patent document CN109030388A (application number: 201810783651.0) discloses a method for detecting the total iron content of iron ore based on spectral data, comprising the following steps: obtaining spectral data of an iron ore sample to be detected, wherein the spectral data comprises m spectral features; inputting the spectral data into an iron ore classification model to obtain the iron ore type of the iron ore sample to be detected; according to the obtained iron ore type, inputting the spectral data into an iron ore total iron content detection model of the corresponding iron ore type to obtain the total iron content of the iron ore corresponding to the spectral data.

[0008] Patent document CN114252581A (application number: 202011023510.2) discloses an online ore detection system, comprising: a sampling device, configured to be connected to an ore conveyor for conveying ore, and directly obtain an original ore sample from the ore conveyed on the ore conveyor; a particle size analysis module, connected to the sampling device through a conveyor path, and configured to perform online particle size analysis on a portion of the original ore samples obtained by the sampling device; a sample preparation device, connected to the online particle size analysis module, configured to retain another portion of the original ore samples obtained by the sampling device, and prepare a laboratory component analysis sample based on the original ore sample; a central control platform, signal-connected to the sampling device, the particle size analysis module and the sample preparation device, configured to issue inspection task instructions to the sampling device, the particle size analysis module and the sample preparation device, and obtain inspection information returned by the sampling device, the particle size analysis module and the sample preparation device, so as to provide a query interface for the customs system.

[0009] Therefore, how to realize online detection of iron ore solid waste can not only effectively improve the supervision efficiency, but also reduce the time and cost of logistics suspension due to inspection, and speed up the turnover of imported materials, which has important economic and social benefits. Summary of the invention

[0010] In view of the defects in the prior art, the object of the present invention is to provide an online detection method and system for solid waste in iron ore.

[0011] According to the present invention, an online detection method for solid waste in iron ore comprises:

[0012] Step S1: establishing a near infrared spectrum database of sample iron ore that meets preset requirements;

[0013] Step S2: using a near-infrared spectrum detection device to obtain a near-infrared reflection spectrum of the iron ore to be tested, and preprocessing the obtained near-infrared reflection spectrum of the iron ore to be tested;

[0014] Step S3: Calculate the similarity between the near-infrared reflectance spectrum of the iron ore to be tested and the spectrum in the near-infrared spectrum database. When the similarity is less than a preset value, it is considered that the current iron ore to be tested contains solid waste; when the similarity is greater than the preset value, it is considered that the current iron ore to be tested does not contain solid waste.

[0015] Preferably, the step S1 comprises: establishing a near infrared spectrum database of imported iron ore that meets preset requirements and iron-containing solid waste that meets preset requirements.

[0016] Preferably, the step S1 comprises:

[0017] Step S1.1: Retrieving a physical sample of iron ore or solid waste with known contents of nine components; wherein the nine components include: Fe, SiO2, CaO, Al2O3, MgO, TiO2, MnO, P and S;

[0018] Step S1.2: Use a near-infrared spectrum detection device to detect the physical sample to obtain the near-infrared spectrum data corresponding to the sample; change the surface distribution of a single sample, repeat the detection for a preset number of times, and obtain multiple detection results;

[0019] Step S1.3: Perform weighted average processing on multiple test results of a single sample to obtain the comparison relationship between component content and near-infrared spectrum data;

[0020] Step S1.4: Model the relationship between component content and near-infrared spectral data through linear regression.

[0021] Preferably, the step S2 comprises: performing denoising and normalization processing on the acquired near-infrared reflection spectrum of the iron ore to be tested, so as to obtain a processed near-infrared reflection spectrum of the iron ore to be tested.

[0022] Preferably, the method further comprises: selecting a near-infrared spectrum with the highest similarity and a similarity greater than a preset value, and obtaining a sample ore corresponding to the near-infrared spectrum, and obtaining a corresponding country of origin and brand based on a constructed sample ore database.

[0023] Preferably, the method further comprises: selecting a near-infrared spectrum with the highest similarity and a similarity greater than a preset value, acquiring a sample ore corresponding to the near-infrared spectrum, and obtaining corresponding component detection data based on a constructed sample ore database.

[0024] Preferably, the method further comprises: issuing an early warning when it is detected that the iron ore to be tested currently contains solid waste.

[0025] According to the present invention, an online detection system for solid waste in iron ore includes:

[0026] Module M1: Establish a near-infrared spectral database of sample iron ore that meets preset requirements;

[0027] Module M2: using a near-infrared spectrum detection device to obtain a near-infrared reflection spectrum of the iron ore to be tested, and preprocessing the obtained near-infrared reflection spectrum of the iron ore to be tested;

[0028] Module M3: Calculate the similarity between the near-infrared reflectance spectrum of the iron ore to be tested and the spectrum in the near-infrared spectrum database. When the similarity is less than a preset value, it is considered that the current iron ore to be tested contains solid waste; when the similarity is greater than the preset value, it is considered that the current iron ore to be tested does not contain solid waste.

[0029] Preferably, the module M2 comprises: performing denoising and normalization processing on the acquired near-infrared reflection spectrum of the iron ore to be tested, so as to obtain the processed near-infrared reflection spectrum of the iron ore to be tested.

[0030] Preferably, the system further comprises: selecting a near infrared spectrum with the highest similarity and a similarity greater than a preset value, obtaining a sample ore corresponding to the near infrared spectrum, and obtaining a corresponding country of origin and brand based on a constructed sample ore database;

[0031] Select the near-infrared spectrum with the highest similarity and a similarity greater than a preset value, obtain the sample ore corresponding to the near-infrared spectrum, and obtain the corresponding component detection data based on the constructed sample ore database;

[0032] When it is detected that the iron ore to be tested contains solid waste, an early warning is issued.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The technical feature of the present invention is to conduct online detection of iron ore through near-infrared spectroscopy technology, which achieves the technical effects of non-destructive sampling, real-time detection, no radioactivity, and no influence from changes in the transport volume and load of the conveyor belt;

[0035] 2. The present invention achieves the effect of easy exchange and sharing of near-infrared spectra of typical imported iron ores and iron-containing solid wastes, and sustainable accumulation and iteration by establishing a near-infrared spectrum database of typical imported iron ores and iron-containing solid wastes;

[0036] 3. Online detection of iron ore is carried out through near-infrared spectroscopy detection equipment. The main consumables are halogen bulbs that emit near-infrared light. The annual consumables are about 2,000 to 3,000 yuan. The subsequent maintenance cost is low, which is a low-cost operation technology route. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0038] Figure 1 The figure is a flow chart of the on-line detection method of solid waste in iron ore.

[0039] Figure 2 Schematic diagram of the online detection system for solid waste in iron ore. DETAILED DESCRIPTION

[0040] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0041] Example 1

[0042] According to an online detection method for solid waste in iron ore provided by the present invention, Figures 1 to 2 As shown, including:

[0043] Step S1: Establish a database of typical imported iron ore brands;

[0044] In this embodiment, step S1 includes:

[0045] Step S1.1: Collect the inspection and testing data of imported iron ore. The main information items include element detection data, country, and brand name information. Among them, the countries include: Australia, Brazil, Canada, Chile, Mauritania, Peru, Sweden, a total of 7, the brands include 27, and the element detection data include: Fe, SiO2, CaO, Al2O3, MgO, TiO2, MnO, P and S, a total of 9 components.

[0046] Step S1.2: The data are grouped according to the brand, and the 9 element detection data in each group of data are statistically analyzed using the quartile method to form a data distribution box plot of the detection data of each element under each brand.

[0047] Step S1.3: Q1 represents the lower quartile, Q2 represents the median, and Q3 represents the upper quartile, and the interquartile range IQR = Q3-Q1 is obtained. Q3+1.5IQR and Q1-1.5IQR are used as the upper and lower limits of the normal value of a certain detection element under this brand respectively. If the sample value is not within the upper and lower limits, it will be marked as an outlier.

[0048] Step S1.4: Remove samples with abnormal values ​​and do not use them as data sources for database establishment to ensure data quality. The cumulative samples removed include 42 Fe abnormal samples, 31 SiO2 abnormal samples, and 31 Al2O3 abnormal samples, and finally 1279 valid samples were obtained.

[0049] Step S1.5: Create a two-dimensional table in the relational database for valid samples to store and back up data.

[0050] Step S2: Establishing a table of element content thresholds for typical imported iron ores;

[0051] Among them, the threshold table is the most common content standard for positively judging the object to be tested as iron ore. The element content threshold of iron ore includes 9 components required by regulatory inspection, namely Fe, SiO2, CaO, Al2O3, MgO, TiO2, MnO, P, and S;

[0052] The specific threshold data is set dynamically by the regulatory authorities based on policy requirements.

[0053] Step S3: Establishing a near-infrared spectral database of typical imported iron ores and iron-containing solid wastes;

[0054] Among them, the database includes the brand name of iron ore or the name of iron-containing solid waste, the elemental composition content of iron ore, and near-infrared spectral data;

[0055] Among them, the near-infrared spectrum data consists of absorption intensity (%), wavelength λ (nm) and wave number ν (nm -1 )composition;

[0056] The iron ore element content includes 9 components required for regulatory inspection, namely Fe, SiO2, CaO, Al2O3, MgO, TiO2, MnO, P, and S;

[0057] Specifically, step S3 includes:

[0058] Step S3.1: Obtain physical samples of iron ore or solid waste with known 9 types of cost contents. The number of physical samples for each type shall be no less than 3.

[0059] Step S3.2: Use a near-infrared spectrum detection device to detect the physical sample and obtain the near-infrared spectrum data corresponding to the sample: absorption intensity (%), wavelength λ (nm) and wave number ν (nm -1 ). By changing the surface distribution of a single sample, repeat the test for no less than 10 times to obtain multiple test results.

[0060] Step S3.3: Perform weighted average processing on multiple test results of a single sample to obtain the comparison relationship between component content and near infrared spectrum data. The data is stored in a relational database.

[0061] Step S3.4: Model the two in S3.3 by linear regression to obtain the conversion function y=F(x). Where y is the element value of the component content, x is the specific absorption intensity (%), wavelength λ (nm) and wave number ν (nm -1 )combination.

[0062] Step S4: deploy a near-infrared spectrum detection device above the conveyor belt, emit near-infrared light to illuminate the surface of the object to be detected, and complete the collection, preprocessing, normalization, and data transmission of the near-infrared reflectance spectrum of the object to be detected, and convert the object image into spectral data;

[0063] Step S5: Based on the significant characteristic differences of the near-infrared reflectance spectra of different brands of iron ores, the near-infrared spectral analysis service compares the spectral data collected in real time with the spectral data of the established near-infrared spectral database of typical imported iron ores and iron-containing solid wastes, substitutes them into the model calculation, and indirectly obtains the component detection data.

[0064] The iron ore composition detection data is output to the solid waste inspection model in real time in the form of compound composition content ratio;

[0065] Step S6: Based on the established database of typical imported iron ore brands, the solid waste inspection model uses machine learning algorithms to perform brand identification, element content threshold judgment, and near-infrared spectrum identification on the iron ore composition data, and issue risk warnings for suspected or adulterated solid waste.

[0066] Specifically, in step S1, the database supports non-programmatic addition of new iron ore brand categories.

[0067] Specifically, in step S2, the threshold table supports non-programmed adjustment and supports temporary shielding or activation of specific element content rules. To ensure a closed-loop decision logic, the element content of the iron ore brands in the database in S1 is within the range of the threshold table in S2.

[0068] Specifically, in step S3, the database supports adding the latest near-infrared spectral data and assay element content data of the same brand of iron ore for data fitting and parameter correction of the solid waste inspection model.

[0069] Specifically, in step S4, the near-infrared spectrum detection device includes spectrum analysis, signal acquisition, light source, intelligent self-calibration, intelligent self-cleaning, anti-collision protection and maintenance mechanisms.

[0070] Specifically, in step S5, the near-infrared spectroscopy analysis service will prioritize matching based on the brand declared in the iron ore customs declaration to improve the performance of the service. If a brand match cannot be declared, a match will be made within the complete database.

[0071] Specifically, in step S6, the solid waste inspection model simultaneously performs brand recognition, element content threshold judgment, and near-infrared spectrum recognition. When a mismatch occurs in the identification results, three risk level prompts of low, medium, and high are given for subsequent manual inspection and review, thereby achieving the purpose of online inspection.

[0072] The output results of the solid waste inspection model are finally prompted to the user through the information system interface. The prompt rules are as follows:

[0073] Low risk: The ore brand can be matched and the element content is matched, which is indicated by yellow font;

[0074] Medium risk: The ore brand is unknown or does not match the brand declared for import, indicated by orange font;

[0075] High risk: Any element exceeds the threshold, or the near-infrared spectrum matches the typical spectral characteristics of solid waste, which is indicated by red font.

[0076] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0077] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. An online detection method for solid waste in iron ore, characterized in that: include: Step S1: establishing a near infrared spectrum database of sample iron ore that meets preset requirements; Step S2: using a near-infrared spectrum detection device to obtain a near-infrared reflection spectrum of the iron ore to be tested, and preprocessing the obtained near-infrared reflection spectrum of the iron ore to be tested; Step S3: Calculate the similarity between the near-infrared reflectance spectrum of the iron ore to be tested and the spectrum in the near-infrared spectrum database. When the similarity is less than a preset value, it is considered that the current iron ore to be tested contains solid waste; when the similarity is greater than the preset value, it is considered that the current iron ore to be tested does not contain solid waste.

2. The method for online detection of solid waste in iron ore according to claim 1, characterized in that: The step S1 includes: establishing a near infrared spectrum database of imported iron ore that meets preset requirements and iron-containing solid waste that meets preset requirements.

3. The method for online detection of solid waste in iron ore according to claim 1, characterized in that: The step S1 comprises: Step S1.1: Retrieving a physical sample of iron ore or solid waste with known contents of nine components; wherein the nine components include: Fe, SiO2, CaO, Al2O3, MgO, TiO2, MnO, P and S; Step S1.2: Use a near-infrared spectrum detection device to detect the physical sample to obtain the near-infrared spectrum data corresponding to the sample; change the surface distribution of a single sample, repeat the detection for a preset number of times, and obtain multiple detection results; Step S1.3: Perform weighted average processing on multiple test results of a single sample to obtain the comparison relationship between component content and near-infrared spectrum data; Step S1.4: Model the relationship between component content and near-infrared spectral data through linear regression.

4. The method for online detection of solid waste in iron ore according to claim 1, characterized in that: The step S2 includes: performing denoising and normalization processing on the acquired near-infrared reflection spectrum of the iron ore to be tested, so as to obtain the processed near-infrared reflection spectrum of the iron ore to be tested.

5. The method for online detection of solid waste in iron ore according to claim 1, characterized in that: The method also includes: selecting a near-infrared spectrum with the highest similarity and a similarity greater than a preset value, and obtaining a sample ore corresponding to the near-infrared spectrum, and obtaining a corresponding country of origin and brand based on a constructed sample ore database.

6. The on-line detection method for solid waste in iron ore according to claim 1, characterized in that: The method further includes: selecting a near infrared spectrum with the highest similarity and a similarity greater than a preset value, acquiring a sample ore corresponding to the near infrared spectrum, and obtaining corresponding component detection data based on a constructed sample ore database.

7. The method for online detection of solid waste in iron ore according to claim 1, characterized in that: The method further comprises: issuing an early warning when it is detected that the iron ore to be tested currently contains solid waste.

8. An online detection system for solid waste in iron ore, characterized in that: include: Module M1: Establish a near-infrared spectral database of sample iron ore that meets preset requirements; Module M2: using a near-infrared spectrum detection device to obtain a near-infrared reflection spectrum of the iron ore to be tested, and preprocessing the obtained near-infrared reflection spectrum of the iron ore to be tested; Module M3: Calculate the similarity between the near-infrared reflectance spectrum of the iron ore to be tested and the spectrum in the near-infrared spectrum database. When the similarity is less than a preset value, it is considered that the current iron ore to be tested contains solid waste; when the similarity is greater than the preset value, it is considered that the current iron ore to be tested does not contain solid waste.

9. The on-line detection system for solid waste in iron ore according to claim 8, characterized in that: The module M2 includes: performing denoising and normalization processing on the acquired near-infrared reflection spectrum of the iron ore to be tested, so as to obtain the processed near-infrared reflection spectrum of the iron ore to be tested.

10. The on-line detection system for solid waste in iron ore according to claim 8, characterized in that: The system further includes: selecting a near infrared spectrum with the highest similarity and a similarity greater than a preset value, obtaining a sample ore corresponding to the near infrared spectrum, and obtaining a corresponding country of origin and brand based on a constructed sample ore database; Select the near-infrared spectrum with the highest similarity and a similarity greater than a preset value, obtain the sample ore corresponding to the near-infrared spectrum, and obtain the corresponding component detection data based on the constructed sample ore database; When it is detected that the iron ore to be tested contains solid waste, an early warning is issued.

Citation Information

Cited By

  • Solid waste classification method based on spectrograph

    CN119702490A

  • Online identification method, device and equipment for iron-containing solid waste of iron ore and storage medium

    CN119985451A