CN111965167A - Method and device for predicting element composition and calorific value of solid waste - Google Patents
Method and device for predicting element composition and calorific value of solid waste Download PDFInfo
- Publication number
- CN111965167A CN111965167A CN202010840365.0A CN202010840365A CN111965167A CN 111965167 A CN111965167 A CN 111965167A CN 202010840365 A CN202010840365 A CN 202010840365A CN 111965167 A CN111965167 A CN 111965167A
- Authority
- CN
- China
- Prior art keywords
- sample
- classification
- detected
- spectrogram
- solid waste
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/71—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light thermally excited
- G01N21/718—Laser microanalysis, i.e. with formation of sample plasma
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Optics & Photonics (AREA)
- Plasma & Fusion (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A method and apparatus for predicting the element composition and heat value of solid waste includes obtaining the spectrum of the sample to be measured; extracting spectrogram information of the spectrogram; classifying the samples to be detected according to the spectrogram information; and if the classification result determines that the sample to be detected is solid waste, calculating the elemental composition and the heat value of the sample to be detected, wherein the calculation result is the predicted elemental composition and the heat value of the sample to be detected. The method can efficiently identify inorganic impurities in the solid waste, can predict the calorific value and the element content of organic components in the solid waste at high speed, and solves the problems of long time consumption, sample consumption, complex operation and the like of the traditional element analysis and calorific value test.
Description
Technical Field
The invention relates to the field of crossing energy and environment, in particular to a method and a device for predicting the element composition and the calorific value of solid waste.
Background
The accumulation of a large amount of solid waste brings many adverse effects to the environment, and the energy utilization of solid waste is a common solid waste treatment method, but the solid waste has diversified properties such as calorific value and elemental composition, and therefore needs to be utilized independently. Meanwhile, inorganic substances may be mixed in the solid waste, which affects the energy utilization thereof and requires the removal of inorganic components before use.
A variety of methods based on computer vision, spectroscopy, X-ray, sonar have been developed for classifying and identifying substances. These techniques, based on computer vision, X-ray, sonar, use cameras or sensors to obtain spatial and graphical features of the sample, which are analyzed to produce classification results. However, this technique has two significant disadvantages: it is difficult for spatial, graphical based classification algorithms to identify highly distorted or fragmented samples; samples of similar shape but made of completely different materials are easily mistaken for the same set. While the classification method based on spectroscopy can obtain the internal composition information of the sample, and solve the above problems to some extent, the sensitivity of the classification method is too strong, and instead, the classification method is more suitable for studying the composition of the sample rather than classifying the sample. In addition, the conventional methods for measuring the elemental composition and the calorific value are conventional analysis methods such as an elemental analyzer and a calorimeter, but the methods are long-lasting and are not suitable for automation technology. In addition to traditional classification methods, methods based on infrared spectroscopy combined with artificial intelligence have been developed for predicting elemental composition and calorific value. It is more efficient than the traditional method, but this technique has two distinct disadvantages: 1) the infrared spectrum of the black object cannot be collected. The infrared absorption spectrum of the article can be obtained by detecting the condition that infrared rays are absorbed according to the principle of the infrared technology that molecules can selectively absorb infrared rays with certain wavelengths to cause transition of energy levels in the molecules, and the black object can absorb all the light rays, so that the infrared spectrum cannot be collected; 2) the infrared spectrum is easily influenced by the moisture of a sample, and the existence of the water can cover peaks of some important components, so that the operation result of a model is influenced, and the optimal utilization of solid waste is adversely affected. Therefore, in view of the classification and energy utilization requirements of solid waste, a classification and characterization technology capable of adapting to the energy utilization method of solid waste is needed.
Disclosure of Invention
In view of the above, one of the main objectives of the present invention is to provide a method and an apparatus for predicting the elemental composition and calorific value of solid waste, so as to at least partially solve at least one of the above technical problems.
In order to achieve the above object, as one aspect of the present invention, there is provided a method of predicting an elemental composition and a calorific value of solid waste, comprising:
acquiring a spectrum of a sample to be detected;
extracting spectrogram information of the spectrogram;
classifying the samples to be detected according to the spectrogram information;
and if the classification result determines that the sample to be detected is solid waste, calculating the elemental composition and the heat value of the sample to be detected, wherein the calculation result is the predicted elemental composition and the heat value of the sample to be detected.
As another aspect of the present invention, there is also provided an apparatus for predicting the elemental composition and calorific value of solid waste, for performing the method as described above, including:
the data acquisition module is used for acquiring a spectral spectrogram of a sample to be detected;
the information extraction module is used for extracting spectrogram information of the spectrogram;
the classification module is used for classifying the samples to be detected according to the spectrogram information; and
and the regression module is used for calculating the element composition and the heat value of the sample to be detected if the classification result determines that the sample to be detected is solid waste.
As still another aspect of the present invention, there is also provided an electronic apparatus including:
one or more processors;
a memory to store one or more instructions;
wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method as described above.
As a further aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to implement the method as described above.
Based on the technical scheme, compared with the prior art, the invention has at least one of the following advantages:
1. the invention provides a method for predicting the element composition and the heat value of solid waste by adopting laser spectrum, which can efficiently identify inorganic impurities in the solid waste, and can predict the heat value and the element content of organic components in the solid waste at high speed, thereby solving the problems of long time consumption, sample consumption, complex operation and the like of the traditional element analysis and heat value test;
2. compared with the traditional analysis and classification method, the method has higher analysis efficiency and higher classification accuracy;
3. compared with other spectrum technologies, the method has wider application range and can be used for predicting the calorific value and the element content of black solid waste;
4. the method can be applied to the fields of automatic classification of solid wastes, fuel utilization research and the like, and improves the production efficiency and the energy utilization efficiency.
Drawings
FIG. 1 is a flow chart of a method for predicting the elemental composition and calorific value of solid waste by using laser spectroscopy according to an embodiment of the present invention.
Detailed Description
In order that the objects, technical solutions and advantages of the present invention will become more apparent, the present invention will be further described in detail with reference to the accompanying drawings in conjunction with the following specific embodiments.
The invention discloses a method for predicting the element composition and the calorific value of solid waste, which comprises the following steps:
acquiring a spectrum of a sample to be detected;
extracting spectrogram information of the spectrogram;
classifying the samples to be detected according to the spectrogram information;
and if the classification result determines that the sample to be detected is solid waste, calculating the elemental composition and the heat value of the sample to be detected, wherein the calculation result is the predicted elemental composition and the heat value of the sample to be detected.
In some embodiments of the present invention, the acquiring step of acquiring the spectral data of the sample to be tested includes a laser spectroscopy.
In some embodiments of the present invention, the extracting step in the extracting step of the spectrogram information of the spectrogram comprises at least one of signal noise reduction and data dimension reduction;
in some embodiments of the present invention, the extracting method in the step of extracting the spectrogram information of the spectrogram comprises at least one of principal component analysis, local linear embedding and laplace feature mapping.
In some embodiments of the present invention, the classification method adopted in the classification step includes at least one of support vector classification, artificial neural network, and decision tree;
in some embodiments of the present invention, the training method of the classification algorithm model includes:
establishing an initial classification algorithm model;
optimizing parameters of an initial classification algorithm model according to classification evaluation indexes according to sample data of known samples to obtain the classification algorithm model;
in some embodiments of the invention, the categorical assessment indicators include accuracy rate, recall rate, prequalification rate, and F1 score.
In some embodiments of the invention, the method employed in the calculating step comprises a regression module model;
in some embodiments of the invention, the method of obtaining the regression model comprises at least one of support vector regression, artificial neural network, random forest;
in some embodiments of the invention, the training method of the regression module model comprises:
establishing an initial regression module model;
and optimizing the parameters of the initial regression model according to the sample data of the known samples by average relative error to obtain the regression model.
In some embodiments of the present invention, the number of the regression module models is at least one, and each regression module model tests a performance index;
in some embodiments of the present invention, the performance index includes a heating value, a carbon element content, or a hydrogen element content of the sample to be tested.
In some embodiments of the invention, the analysis is ended if the classification result of the first data in the classification step is inorganic.
The invention also discloses a device for predicting the element composition and the calorific value of the solid waste, which is used for executing the method, and comprises the following steps:
the data acquisition module is used for acquiring a spectral spectrogram of a sample to be detected;
the information extraction module is used for extracting spectrogram information of the spectrogram;
the classification module is used for classifying the samples to be detected according to the spectrogram information; and
and the regression module is used for calculating the element composition and the heat value of the sample to be detected if the classification result determines that the sample to be detected is solid waste.
The invention also discloses an electronic device, comprising:
one or more processors;
a memory to store one or more instructions;
wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method as described above.
The invention also discloses a computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to implement the method as described above.
In one exemplary embodiment, the device for predicting the elemental composition and the calorific value of the solid waste by using the laser spectrum comprises a data acquisition module, an information extraction module, a classification module and a regression module.
The data acquisition module is used for generating a sample spectrum, the method adopts laser spectrum, and the spectrum generation method comprises but is not limited to a spectrometer and a spectrum camera.
The information extraction module is used for extracting effective information from the spectrum, the specific information extraction process includes but is not limited to signal noise reduction and data dimension reduction, and the adopted information extraction algorithm includes but is not limited to principal component analysis, local linear embedding, Laplace feature mapping and the like.
The classification module is used for identifying inorganic impurities, the classification algorithm model adopted by the module comprises but is not limited to support vector classification, artificial neural network and decision tree, and parameters of the related algorithm model are obtained by training a large amount of known sample data.
The regression module is used for generating results of the heat value and the element content, the regression algorithm model adopted by the module comprises but is not limited to support vector regression, an artificial neural network and a random forest, and parameters of the relevant algorithm model are obtained by training a large amount of known sample data.
As shown in fig. 1, the method for predicting the elemental composition and the calorific value of the solid waste by using the laser spectrum is realized by the following technical scheme:
step 1, collecting a large number of samples of solid waste and inorganic matters from various regions, classifying the samples, storing the samples under specific conditions, and simultaneously obtaining data such as heat values, element contents and the like of the samples in advance.
And 2, processing the sample to different degrees according to the use requirement of the machine, and acquiring the spectral data of the sample by a data acquisition module consisting of a spectrometer or a spectral camera.
And 3, constructing an information processing module model based on algorithms such as principal component analysis or local linear embedding. And (3) inputting the spectral data obtained in the step (2) into the model, and performing noise reduction, dimension reduction and other processing on the data to obtain processed sample data.
And 4, training a classification module model based on support vector classification, neural networks and the like by using the processed sample data obtained in the step 3, optimizing an objective function by using accuracy, recall rate or other parameter indexes to obtain the optimal parameter condition of the module model, and generating the optimal classification module model.
And 5, training a regression module model based on support vector regression, random forests and the like by adopting the processed sample data obtained in the step 3, and taking the average relative error or other parameter indexes as an optimization objective function to obtain the optimal parameter condition of the module model so as to generate an optimal regression module model. Each regression model is only used for one test item, such as low calorific value, carbon element content or hydrogen element content. If different items are to be analyzed, multiple different regression models are trained.
Step 6, for new unknown samples, acquiring the spectral data of the new unknown samples through the data acquisition module in the step 2, acquiring the processed data through the information extraction module in the step 3, classifying the data by using the classification module model in the step 4, and finishing the analysis if the obtained classification result is inorganic; if the solid waste is classified, the process proceeds to step 7.
And 7, inputting the sample data classified into the solid waste obtained in the step 6 into the regression module model obtained in the step 5, and performing regression calculation to obtain results such as the heat value, the element composition and the like of the sample.
The technical solution of the present invention is further illustrated by the following specific embodiments in conjunction with the accompanying drawings. It should be noted that the following specific examples are given by way of illustration only and the scope of the present invention is not limited thereto.
In order to fully illustrate the effectiveness of the method for predicting the elemental composition and calorific value of solid waste by using laser spectroscopy, in conjunction with fig. 1, the present invention provides an example for predicting the calorific value and elemental content of solid waste. The specific calculation steps and results are as follows:
and S1, collecting a large number of solid waste and inorganic substance samples in various regions, classifying the samples, storing the samples under specific conditions, and simultaneously obtaining the heat value, the carbon element content and the hydrogen element content data of the samples in advance.
In this example, 21 solid wastes and 3 inorganic materials were selected as spectroscopic materials from southern China. Storing in sealed bag under drying condition at room temperature. 10 samples were taken for each spectroscopic material for spectroscopic testing. The data of the low calorific value, the carbon element content and the hydrogen element content of the sample are obtained in advance through experiments or database retrieval, and are shown in table 1.
TABLE 1 Low calorific value, carbon element content and hydrogen element content of the samples
And S2, processing the sample to different degrees according to the use requirement of the machine, and acquiring the spectrum data of the sample in a data acquisition module consisting of a spectrometer or a spectrum camera.
In this embodiment, a Laser Induced Breakdown Spectroscopy (LIBS) spectrometer is used to collect a Laser Induced Breakdown Spectroscopy (LIBS) spectrum of a sample, the wavelength of the laser is 1064nm, a laser with energy of 10MJ and frequency of 10Hz is used, the delay time of the instrument is set to 2.6us to avoid bremsstrahlung, and the wave number range of the LIBS spectrum is 200-1000 cm--1LIBS spectrogram data of 2064 wavenumbers are obtained. An air background spectrum was collected before the sample spectrum was collected. Each test sample was scanned 32 times and the results averaged for subsequent analysis. During the experiment, the sample is not specially pretreated, and a large sample can be directly placed on a sample box of a spectrometer for measurement.
And S3, constructing an information extraction module model by using a principal component analysis algorithm. And (3) inputting the spectral data obtained in the step (2) into the program, performing noise reduction, dimension reduction and other processing on the data to obtain a plurality of mutually unrelated principal components containing original data information, and extracting the first 20 principal components for subsequent analysis and calculation.
And S4, training a support vector classification model by using the data obtained in the step 3, optimizing a target function by using parameter indexes such as accuracy, recall rate, prejudgment success rate and F1 score (F1 score), optimizing parameters such as the number of principal components of the information processing module, a kernel function of the support vector classification model and the like, obtaining the optimal parameter condition of the model, and generating the optimal classification module model.
The result shows that when the number of the principal components of the information processing module is 4-10 and the kernel function of the support vector classification model is linear, the classification effect of the classification module model is optimal, so that the kernel function of the support vector classification model of the classification module adopts the linear kernel function, and the number of the principal components of the information processing module is selected to be 8.
S5, respectively training 2 support vector regression models, 1 artificial neural network regression model and 1 random forest regression model by adopting the data obtained in the step 3, respectively obtaining the optimal parameter conditions of 4 module models by taking the average relative error as an optimization objective function, and generating the optimal regression module model for predicting the low-order calorific value, the carbon element content and the hydrogen element content.
The result shows that when the random forest regression model is selected and the number of the main components of the information processing module is about 8, the lower calorific value prediction accuracy is highest. Therefore, the regression model for predicting the lower calorific value is selected as the random forest regression model, and the information module (the number of principal components is 8) used for the classification module can be used for the regression model as well.
When the random forest regression model is selected and the number of the main components of the information processing module is about 15, the carbon element content prediction accuracy is highest. Therefore, the regression model is selected as a random forest regression model when the carbon element content is predicted, and the information module (the number of principal components is 8) used for the classification module can also be used for the regression model.
When the random forest regression model and the information processing module are selected, the main component number is about 8, and the hydrogen element content prediction accuracy is highest. Therefore, the regression model is selected as a random forest regression model when predicting the hydrogen content, and the information module (the number of principal components is 8) used for the classification module can also be used for the regression model.
S6, selecting 24 unknown samples of different types, obtaining spectral data of the unknown samples through the data acquisition module in the step 2, obtaining processed data through the information extraction module in the step 3, classifying the data by using the classification module model in the step 4, and finishing analysis if the obtained classification result is an inorganic matter; if the solid waste is classified, the process proceeds to step 7.
And S7, inputting the sample extraction data classified into the solid waste obtained in the step 6 into the regression module model in the step 5, and performing regression calculation to obtain results of heat value, element analysis and the like of the sample. Through actual analysis and calculation, the method is adopted to carry out prediction calculation on the calorific value of an unknown sample, and the prediction relative error is about 4%.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of predicting the elemental composition and calorific value of solid waste comprising:
acquiring a spectrum of a sample to be detected;
extracting spectrogram information of the spectrogram;
classifying the samples to be detected according to the spectrogram information;
and if the classification result determines that the sample to be detected is solid waste, calculating the elemental composition and the heat value of the sample to be detected, wherein the calculation result is the predicted elemental composition and the heat value of the sample to be detected.
2. The method of claim 1,
the acquisition method adopted in the step of acquiring the spectral data of the sample to be detected comprises a laser spectroscopy.
3. The method of claim 1,
the extraction step in the step of extracting spectrogram information of the spectrogram comprises at least one of signal noise reduction and data dimension reduction;
the extraction method in the step of extracting the spectrogram information of the spectrogram comprises at least one of principal component analysis, local linear embedding and Laplace characteristic mapping.
4. The method of claim 1,
the classification method adopted in the classification step comprises at least one of support vector classification, an artificial neural network and a decision tree;
the training method of the classification algorithm model comprises the following steps:
establishing an initial classification algorithm model;
optimizing parameters of an initial classification algorithm model according to classification evaluation indexes according to sample data of known samples to obtain the classification algorithm model;
the classification evaluation indexes comprise accuracy, recall rate, prejudgment success rate and F1 scores.
5. The method of claim 1,
the method adopted in the calculating step comprises a regression module model;
the method for obtaining the regression module model comprises at least one of support vector regression, an artificial neural network and a random forest;
the training method of the regression module model comprises the following steps:
establishing an initial regression module model;
and optimizing the parameters of the initial regression model according to the sample data of the known samples by average relative error to obtain the regression model.
6. The method of claim 5,
the number of the regression module models is at least one, and each regression module model tests one performance index;
the performance index comprises the heat value, the carbon element content or the hydrogen element content of the sample to be detected.
7. The method of claim 1,
and if the classification result of the first data in the classification step is inorganic matter, the analysis is finished.
8. An apparatus for predicting the elemental composition and calorific value of solid waste for carrying out the method of claims 1-7, comprising:
the data acquisition module is used for acquiring a spectral spectrogram of a sample to be detected;
the information extraction module is used for extracting spectrogram information of the spectrogram;
the classification module is used for classifying the samples to be detected according to the spectrogram information; and
and the regression module is used for calculating the element composition and the heat value of the sample to be detected if the classification result determines that the sample to be detected is solid waste.
9. An electronic device, comprising:
one or more processors;
a memory to store one or more instructions;
wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010840365.0A CN111965167A (en) | 2020-08-20 | 2020-08-20 | Method and device for predicting element composition and calorific value of solid waste |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010840365.0A CN111965167A (en) | 2020-08-20 | 2020-08-20 | Method and device for predicting element composition and calorific value of solid waste |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111965167A true CN111965167A (en) | 2020-11-20 |
Family
ID=73388540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010840365.0A Pending CN111965167A (en) | 2020-08-20 | 2020-08-20 | Method and device for predicting element composition and calorific value of solid waste |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111965167A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077006A (en) * | 2021-04-15 | 2021-07-06 | 天津大学 | Model training method and analysis method for analyzing quality of bio-oil |
| CN113327300A (en) * | 2021-06-01 | 2021-08-31 | 浙江大学 | Real-time measuring and calculating method for heat value of garbage entering furnace of garbage incinerator based on thermal imaging graph |
| CN117454327A (en) * | 2023-12-26 | 2024-01-26 | 山东建筑大学 | Polynomial regression-based organic waste pyrolysis gas component prediction method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2938066A1 (en) * | 2008-11-06 | 2010-05-07 | Centre Nat Rech Scient | SYSTEM AND METHOD FOR QUANTITATIVE ANALYSIS OF THE ELEMENTARY COMPOSITION OF LASER-INDUCED PLASMA SPECTROSCOPY MATERIAL (LIBS) |
| CN103499552A (en) * | 2013-10-23 | 2014-01-08 | 天津工业大学 | Fast and intelligent waste plastic sorting method |
| CN104697965A (en) * | 2015-03-10 | 2015-06-10 | 西北大学 | Method for recognizing slag variety by combining with laser-induced breakdown spectroscopy based on least squares support vector machine |
| US20160349174A1 (en) * | 2015-06-01 | 2016-12-01 | Ingrain, Inc. | Combined Vibrational Spectroscopy And Laser Induced Breakdown Spectroscopy For Improved Mineralogical And Geochemical Characterization Of Petroleum Source Or Reservoir Rocks |
| CN106404748A (en) * | 2016-09-05 | 2017-02-15 | 华中科技大学 | Multispectral combined laser induced breakdown spectroscopy cereal crop producing area identification method |
| CN108627500A (en) * | 2018-04-16 | 2018-10-09 | 华南理工大学 | A kind of solid fuel measurement of caloric value method |
| CN110161013A (en) * | 2019-05-14 | 2019-08-23 | 上海交通大学 | Laser induced breakdown spectroscopy data processing method and system based on machine learning |
-
2020
- 2020-08-20 CN CN202010840365.0A patent/CN111965167A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2938066A1 (en) * | 2008-11-06 | 2010-05-07 | Centre Nat Rech Scient | SYSTEM AND METHOD FOR QUANTITATIVE ANALYSIS OF THE ELEMENTARY COMPOSITION OF LASER-INDUCED PLASMA SPECTROSCOPY MATERIAL (LIBS) |
| CN103499552A (en) * | 2013-10-23 | 2014-01-08 | 天津工业大学 | Fast and intelligent waste plastic sorting method |
| CN104697965A (en) * | 2015-03-10 | 2015-06-10 | 西北大学 | Method for recognizing slag variety by combining with laser-induced breakdown spectroscopy based on least squares support vector machine |
| US20160349174A1 (en) * | 2015-06-01 | 2016-12-01 | Ingrain, Inc. | Combined Vibrational Spectroscopy And Laser Induced Breakdown Spectroscopy For Improved Mineralogical And Geochemical Characterization Of Petroleum Source Or Reservoir Rocks |
| CN106404748A (en) * | 2016-09-05 | 2017-02-15 | 华中科技大学 | Multispectral combined laser induced breakdown spectroscopy cereal crop producing area identification method |
| CN108627500A (en) * | 2018-04-16 | 2018-10-09 | 华南理工大学 | A kind of solid fuel measurement of caloric value method |
| CN110161013A (en) * | 2019-05-14 | 2019-08-23 | 上海交通大学 | Laser induced breakdown spectroscopy data processing method and system based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 刘可;邱春玲;田地;杨光;李颖超;韩旭;: "一种基于激光诱导击穿光谱的塑料分类方法" * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077006A (en) * | 2021-04-15 | 2021-07-06 | 天津大学 | Model training method and analysis method for analyzing quality of bio-oil |
| CN113327300A (en) * | 2021-06-01 | 2021-08-31 | 浙江大学 | Real-time measuring and calculating method for heat value of garbage entering furnace of garbage incinerator based on thermal imaging graph |
| CN113327300B (en) * | 2021-06-01 | 2022-04-19 | 浙江大学 | Real-time measuring and calculating method for heat value of garbage entering furnace of garbage incinerator based on thermal imaging graph |
| CN117454327A (en) * | 2023-12-26 | 2024-01-26 | 山东建筑大学 | Polynomial regression-based organic waste pyrolysis gas component prediction method and system |
| CN117454327B (en) * | 2023-12-26 | 2024-03-15 | 山东建筑大学 | Polynomial regression-based organic waste pyrolysis gas component prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111965167A (en) | Method and device for predicting element composition and calorific value of solid waste | |
| Feng et al. | Rapid and non-destructive measurement of biofuel pellet quality indices based on two-dimensional near infrared spectroscopic imaging | |
| Wang et al. | Rapid quantitative analysis of the acidity of iron ore by the laser-induced breakdown spectroscopy (LIBS) technique coupled with variable importance measures-random forests (VIM-RF) | |
| CN115905881B (en) | Yellow pearl classification method and device, electronic equipment and storage medium | |
| CN105486655A (en) | Rapid detection method for organic matters in soil based on infrared spectroscopic intelligent identification model | |
| CN102841063B (en) | Method for tracing and identifying charcoal based on spectrum technology | |
| CN105092579A (en) | Mango quality non-destructive testing device | |
| Pan et al. | Identification of complex mixtures for Raman spectroscopy using a novel scheme based on a new multi-label deep neural network | |
| Chen et al. | Correction of moisture interference in laser-induced breakdown spectroscopy detection of coal by combining neural networks and random spectral attenuation | |
| Ruan et al. | A modified backward elimination approach for the rapid classification of Chinese ceramics using laser-induced breakdown spectroscopy and chemometrics | |
| CN112750507B (en) | Method for simultaneously detecting nitrate and nitrite contents in water based on hybrid machine learning model | |
| CN110887798B (en) | Nonlinear full-spectrum water turbidity quantitative analysis method based on extreme random tree | |
| CN117491293A (en) | High-steep bank slope carbonate rock corrosion rapid evaluation method based on hyperspectrum | |
| Li et al. | Origin traceability and adulteration detection of soybean using near infrared hyperspectral imaging | |
| CN113740294B (en) | Near infrared modeling-based gasoline/diesel oil detection and analysis method and device | |
| Ding et al. | Determination of soil source using laser induced breakdown spectroscopy combined with feature selection | |
| CN113791062A (en) | Method for judging fixed substance type based on Raman spectrum | |
| CN112861413A (en) | Biomass water content measurement and modeling method based on near infrared spectrum principal component and neural network | |
| CN112861415A (en) | Biomass ash content measurement and modeling method based on near infrared spectrum principal component and neural network | |
| Li et al. | SVM-based apple classification of soluble solids content by near-infrared spectroscopy | |
| CN112861412A (en) | Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network | |
| CN111693484A (en) | Sesame oil variety identification method based on terahertz time-domain spectroscopy | |
| Dou et al. | Quantitative analysis of coal industrial index based on data set partitioning method | |
| Yan et al. | Prediction Analysis of Soluble Solids Content in Apples Based on Wavelet Packet Analysis and BP Neural Network | |
| CN111504981B (en) | Method for determining chemical components and moisture content in powder material |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |