CN112861412A - Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network - Google Patents
Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network Download PDFInfo
- Publication number
- CN112861412A CN112861412A CN201911181188.3A CN201911181188A CN112861412A CN 112861412 A CN112861412 A CN 112861412A CN 201911181188 A CN201911181188 A CN 201911181188A CN 112861412 A CN112861412 A CN 112861412A
- Authority
- CN
- China
- Prior art keywords
- data
- biomass
- neural network
- infrared spectrum
- content
- 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
- 239000002028 Biomass Substances 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 30
- 238000005259 measurement Methods 0.000 title claims abstract description 23
- 239000000523 sample Substances 0.000 claims abstract description 49
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 22
- 238000012795 verification Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 4
- 239000012472 biological sample Substances 0.000 claims description 3
- 239000002994 raw material Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000012847 principal component analysis method Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims 1
- 238000003672 processing method Methods 0.000 claims 1
- 239000000446 fuel Substances 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 3
- 239000007787 solid Substances 0.000 abstract description 3
- 238000004445 quantitative analysis Methods 0.000 abstract 1
- 230000003595 spectral effect Effects 0.000 abstract 1
- 239000011159 matrix material Substances 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 229910052573 porcelain Inorganic materials 0.000 description 1
- DPLVEEXVKBWGHE-UHFFFAOYSA-N potassium sulfide Chemical compound [S-2].[K+].[K+] DPLVEEXVKBWGHE-UHFFFAOYSA-N 0.000 description 1
- 229920002379 silicone rubber Polymers 0.000 description 1
- 239000004945 silicone rubber Substances 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G01N21/17—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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1296—Using chemometrical methods using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method for measuring and modeling the content of biomass volatile components based on near infrared spectrum main components and a neural network, which measures the content of the biomass volatile components by adopting a quantitative analysis method according to a standard (such as national standard GB/T28731 and 2012 'solid biomass fuel industry analysis method'), obtains a measurement value of the content of the biomass volatile components, and measures the near infrared spectrum of a biomass sample by adopting a near infrared spectrometer; measuring state parameters such as ambient temperature, ambient pressure, distance between an infrared sensor probe and a sample, ambient light intensity and the like during near-infrared data acquisition; preprocessing the obtained spectral data such as baseline drift, smooth denoising and the like; and (3) correlating the biomass near infrared spectrum and the environment-related state parameters with the measured value of the volatile content to construct a prediction model. The method has no damage to the biomass sample, fully considers the influence caused by the measurement environment, and can realize rapid detection and online measurement of the volatile content in the biomass.
Description
Technical Field
The invention belongs to the field of biomass big data analysis, and relates to a method for quickly and accurately measuring volatile components in biomass raw materials.
Background
The utilization of biomass belongs to waste utilization and is not limited in one aspect, the volatile content of biomass fuel plays a crucial role in the operation of a boiler, and the detection of the content of the volatile content of the biomass is realized by a standard method that a certain amount of solid biomass fuel sample is weighed and placed in a porcelain crucible with a cover, and the sample is heated for 7min in an isolated air mode at the temperature of 900 +/-10 ℃, so that the reduced mass accounts for the mass fraction of the mass of the sample, and the moisture content of the sample is subtracted to serve as the volatile content of the sample. The method is also adopted in the national standard GB/T28731-2012 'solid biomass fuel industry analysis method', and although the method is accurate, the required time is long, the process is complex, and real-time online measurement is difficult to realize.
Compared with a Gaussian mathematical model, the method has higher accuracy and precision, relatively small data calculation amount and is more suitable for the optimization and calculation of larger data, and meanwhile, the method does not consider the influence of the environment during real-time measurement.
In patent CN 107314989 a, a method for measuring the volatile content of room temperature potassium sulfide-based silicone rubber is provided, wherein second derivative is used to preprocess data, and partial least square method is used to model data, and the method does not consider the influence of environment during real-time measurement. The method adopts a Chauvenet test method which is a test method of a range taking normal distribution as a center, removes the steel, adopts a support vector machine model to predict the Gaussian element distribution characteristic of the biomass, and is relatively scientific and practical.
Disclosure of Invention
The biomass volatile component content measuring and modeling method based on the near infrared spectrum main component and the neural network provided by the invention provides a non-contact rapid measuring method which can realize online real-time measurement and fully considers the influence of the measuring environment.
To achieve the object, the invention comprises the following features:
the biomass volatile component content measurement and modeling based on the near infrared spectrum principal component and the neural network mainly comprises infrared spectrum measurement, biomass volatile component content measurement, state parameter measurement, principal component analysis and a support vector machine modeling method.
Mainly comprises the following steps:
(1) collecting biomass original data: measuring the volatile content of the biomass according to a standard (such as national standard GB/T28731-; measuring a biological sample by using a near infrared spectrum instrument (the wavelength range is 1200-3000 nm) to obtain infrared spectrum data of the sample; and measuring the ambient temperature, pressure, the distance between the infrared sensor probe and the sample, ambient light intensity and other state parameters during infrared data acquisition.
(2) Dividing a sample set: a random classification method is adopted, 30% -70% of samples are selected as a training sample set, and the rest of data are used as a verification sample set. The training sample set is used for training the neural network model, and the verification sample set is used for detecting whether the established neural network model is accurate or not.
(3) Removing abnormal data: in the invention, a Chauvenet inspection method is adopted to process abnormal data of the data, remove the abnormal data from the data set, remove gross errors of the data and enhance the accuracy of the subsequent data modeling.
(4) Preprocessing infrared spectrum data: the invention adopts a principal component analysis method to carry out principal component analysis on the measurement data of each wavelength of the infrared data to obtain a principal component expression and a principal component numerical value. After the dimensionality reduction is carried out on the preprocessed data by using the principal components, the components with the contribution rate of more than 80% are selected as the principal components, the repeatability and the collinearity of the data are removed, the data calculation amount is reduced, and the original characteristics of the data are ensured.
(5) Establishing a neural network model: and (3) taking the main component data and the state parameter data of the preprocessed infrared spectrum as input parameters of a neural network of a support vector machine, taking a measured value of the content of the volatile components of the biomass as output parameters of the neural network, training the established neural network by adopting a training sample set, and finishing an optimization training process when the error is less than 0.1% to obtain an optimal network structure and parameters.
(6) Verifying the accuracy of the model: and (5) adopting infrared spectrum data and state parameter data in the verification sample set as the input of the trained and converged support vector machine neural network in the step (5), and comparing the output value of the neural network with the measured value of the biomass volatile component in the verification sample set to verify the accuracy of the model.
The beneficial effects of the invention include: the method has the advantages that the method carries out volatile component measurement on the biomass fuel in different states, the variety of the biomass fuel is not limited, and the method for modeling the near infrared spectrum by using the PCA-SVM is used to obtain the method for detecting the volatile component accurately, quickly, conveniently and quickly.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed description of the preferred embodiments
The following detailed description of specific embodiments of the above steps, and the examples of the present invention include, but are not limited to, the present examples.
(1) Measurement of raw biomass data: selecting 100 groups of biomass samples, carrying out infrared data measurement on biomass raw materials in different states to obtain 40000 groups of infrared data, carrying out smooth denoising treatment on the data, recording state parameter data such as environmental temperature, pressure, distance between an infrared sensor and the sample, environmental light intensity and the like during near infrared spectrum data acquisition, and measuring the content of the volatile components of the biomass according to standards (such as national standard GB/T28731 one-year-old 2012).
(2) Dividing a sample set: 40000 groups of collected infrared data and corresponding state parameters are randomly classified into a training sample set and a verification sample set, wherein 20000 groups are used as the training sample set data, 20000 groups are used as the verification sample set data, the training sample set is used for training a neural network model, and the verification sample set is used for detecting whether the established neural network model is accurate or not.
(3) Removing abnormal data: and removing abnormal data by using a Chauvenet inspection method, removing the abnormal data from the data set, and removing gross errors of the data to obtain a training sample set S with the abnormal data removed to enhance the accuracy of the subsequent data modeling.
(4) Preprocessing infrared spectrum data: analyzing S as input data of principal component analysis, solving a correlation matrix C of the S, solving a characteristic value of the correlation matrix C, obtaining an accumulated contribution rate, selecting a component with the accumulated contribution rate more than 80% as a principal component to obtain a principal component matrix F, reducing the dimension of data, removing the repeatability and the collinearity of the data, preventing the situations of excessive fitting and the like, reducing the data calculation amount and ensuring the original characteristics of the data.
(5) Establishing a neural network model: and (3) taking the preprocessed principal component matrix F of the infrared spectrum and the state parameter data as input parameters of a neural network of a support vector machine, taking a biomass volatile content measurement value Y as an output parameter of the neural network, training the established neural network by adopting a training sample set, and finishing an optimization training process when the error is less than 0.1% to obtain an optimal network structure and parameters.
(6) Verifying the accuracy of the model: and verifying the neural network model by using a verification set to obtain a volatile component calculation value Y, comparing the volatile component content measurement value with a predicted value Y of the neural network, and solving a correlation coefficient and a root mean square error between the predicted value and a true value to evaluate the accuracy of the rapid detection of the integral model.
The methods of the present invention include, but are not limited to, analytical measurement of biomass fuel components.
Claims (8)
1. The biomass volatile component content measurement and modeling method based on the near infrared spectrum main component and the neural network is characterized by comprising the following steps of:
(1) collecting biomass original data: measuring the volatile content of the biomass according to a standard (such as national standard GB/T28731-; measuring a biological sample by using a near infrared spectrum instrument (the wavelength range is 1200-3000 nm) to obtain infrared spectrum data of the sample; measuring state parameters such as ambient temperature, ambient pressure, distance between an infrared sensor probe and a sample, ambient light intensity and the like during infrared data acquisition;
(2) dividing a sample set: selecting 30-70% of data as a training sample set and the rest of data as a verification sample set by adopting a random classification method;
(3) removing abnormal data: in the invention, a Chauvenet inspection method is adopted to process abnormal data of data, useful data signals are extracted, and signals with low noise point ratio and relatively small background interference are obtained;
(4) preprocessing infrared spectrum data: the method adopts a principal component analysis method to separate noise from background, and carries out principal component analysis on the measurement data of each wavelength of infrared data to obtain a principal component expression and a principal component numerical value;
(5) establishing a neural network model: using the preprocessed principal component data of the infrared spectrum and the state parameter data as input parameters of a neural network of a support vector machine, using a measured value of the content of the volatile components of the biomass as output parameters of the neural network, and training the established neural network by adopting a training sample set to obtain an optimal network structure and parameters;
(6) verifying the accuracy of the model: and (5) adopting infrared spectrum data and state parameter data in the verification sample set as the input of the trained and converged support vector machine neural network in the step (5), and comparing the output value of the neural network with the measured value of the biomass volatile component in the verification sample set to verify the accuracy of the model.
2. The method for measuring and modeling the content of the biomass volatile components based on the near infrared spectrum main components and the neural network as claimed in claim 1, wherein: measuring a biological sample by using a near infrared spectrometer to obtain infrared spectrum data of the sample; and measuring the ambient temperature, pressure, the distance between the infrared sensor probe and the sample, ambient light intensity and other state parameters during infrared data acquisition.
3. The method for measuring and modeling the content of the biomass volatile components based on the near infrared spectrum main components and the neural network as claimed in claim 1, wherein: classifying the acquired data, selecting 30-70% of the data as a training sample set by adopting a random classification method, and taking the rest of the data as a verification sample set; the training sample set is used for establishing a neural network model, and the verification sample set is used for detecting whether the established neural network model is accurate or not.
4. The method for measuring and modeling the content of the biomass volatile components based on the near infrared spectrum main components and the neural network as claimed in claim 1, wherein: and (3) smoothing processing method, wherein a Chauvenet inspection method is adopted to remove abnormal data to enhance the accuracy of data modeling.
5. The method for measuring and modeling the content of the biomass volatile components based on the near infrared spectrum main components and the neural network as claimed in claim 1, wherein: and (4) carrying out principal component analysis on the measurement data of each wavelength of the infrared data, carrying out dimensionality reduction on the preprocessed data, selecting components with contribution rate more than 80% as principal components, obtaining a principal component expression and a principal component numerical value, removing repeatability and collinearity of the data, preventing the situations of overfitting and the like, reducing data calculation amount and ensuring original characteristics of the data.
6. The method for measuring and modeling the content of the biomass volatile components based on the near infrared spectrum main components and the neural network as claimed in claim 1, wherein: training and optimizing the neural network by using a support vector machine neural network method to training sample set data, wherein the input of the model is a principal component vector extracted after principal component analysis, and the output is a volatile component content value in the biomass raw material; the environment state parameters of the infrared analyzer are directly used as neural network input, the influence of environment change on measurement accuracy is fully considered, the result is more accurate and reliable, and the application range is wider.
7. The method for measuring and modeling the content of the biomass volatile components based on the near infrared spectrum main components and the neural network as claimed in claim 1, wherein: and (6) evaluating the accuracy of the rapid detection of the whole model by using the model to calculate the correlation coefficient and the root mean square error of the training sample set and the verification sample set.
8. The application of the biomass volatile component content measuring and modeling method based on near infrared spectrum main components and the neural network according to any one of claims 1 to 7 in the fields of biomass and big data analysis belongs to the protection scope of the patent claims.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911181188.3A CN112861412A (en) | 2019-11-27 | 2019-11-27 | Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911181188.3A CN112861412A (en) | 2019-11-27 | 2019-11-27 | Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112861412A true CN112861412A (en) | 2021-05-28 |
Family
ID=75985593
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911181188.3A Pending CN112861412A (en) | 2019-11-27 | 2019-11-27 | Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112861412A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115406793A (en) * | 2022-08-16 | 2022-11-29 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Establishment method and application of missible oil pesticide VOCs emission potential coefficient prediction model |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101520412A (en) * | 2009-03-23 | 2009-09-02 | 中国计量学院 | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network |
CN107677647A (en) * | 2017-09-25 | 2018-02-09 | 重庆邮电大学 | Chinese medicine place of production discrimination method based on principal component analysis and BP neural network |
US20180306711A1 (en) * | 2017-04-19 | 2018-10-25 | Bruker Daltonik Gmbh | Microbial test standard for use in infrared spectrometry |
CN109724941A (en) * | 2019-02-27 | 2019-05-07 | 大唐长山热电厂 | A kind of CO based on radial base neural net2High-temperature gas concentration detection method |
CN110308111A (en) * | 2019-06-14 | 2019-10-08 | 湖北省农业科学院果树茶叶研究所 | A method of using the near-infrared spectrum technique quick predict Yuanan yellow tea bored yellow time |
-
2019
- 2019-11-27 CN CN201911181188.3A patent/CN112861412A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101520412A (en) * | 2009-03-23 | 2009-09-02 | 中国计量学院 | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network |
US20180306711A1 (en) * | 2017-04-19 | 2018-10-25 | Bruker Daltonik Gmbh | Microbial test standard for use in infrared spectrometry |
CN107677647A (en) * | 2017-09-25 | 2018-02-09 | 重庆邮电大学 | Chinese medicine place of production discrimination method based on principal component analysis and BP neural network |
CN109724941A (en) * | 2019-02-27 | 2019-05-07 | 大唐长山热电厂 | A kind of CO based on radial base neural net2High-temperature gas concentration detection method |
CN110308111A (en) * | 2019-06-14 | 2019-10-08 | 湖北省农业科学院果树茶叶研究所 | A method of using the near-infrared spectrum technique quick predict Yuanan yellow tea bored yellow time |
Non-Patent Citations (3)
Title |
---|
张瑶: "基于光谱技术的农林环境关键参数信息获取研究", 《中国优秀博硕士学位论文全文数据库(博士) 农业科技辑》 * |
程旭云: "生物质秸秆热化工特性的NIRS分析方法与热值模型构建", 《中国优秀博硕士学位论文全文数据库(硕士) 农业科技辑》 * |
路文江: "基于光谱分析技术的农林生物质燃料特性的快速检测研究", 《红外》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115406793A (en) * | 2022-08-16 | 2022-11-29 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Establishment method and application of missible oil pesticide VOCs emission potential coefficient prediction model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
CN105300923A (en) | Correction method of measuring point free temperature compensation model during process of online application of near infrared spectrum analyzer | |
CN109085136B (en) | Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum | |
CN103175805B (en) | Method for determining indexes of COD and BOD5 in sewage through near infrared spectrometry | |
CN105486655A (en) | Rapid detection method for organic matters in soil based on infrared spectroscopic intelligent identification model | |
CN108760647A (en) | A kind of wheat content of molds line detecting method based on Vis/NIR technology | |
WO2020248961A1 (en) | Method for selecting spectral wavenumber without reference value | |
CN111999258A (en) | Spectral baseline correction-oriented weighting modeling local optimization method | |
CN114624142A (en) | Tobacco leaf total sugar and reducing sugar quantitative analysis method based on pyrolysis kinetic parameters | |
CN110567894A (en) | method and device for rapidly detecting pH value of aqueous solution | |
CN112485238B (en) | Method for identifying turmeric essential oil producing area based on Raman spectrum technology | |
CN111141809B (en) | Soil nutrient ion content detection method based on non-contact type conductivity signal | |
CN105954228A (en) | Method for measuring content of sodium metal in oil sand based on near infrared spectrum | |
CN111896497B (en) | Spectral data correction method based on predicted value | |
CN112861412A (en) | Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network | |
CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
CN105277531A (en) | Grading-based coal characteristic measurement method | |
CN112861415A (en) | Biomass ash content measurement and modeling method based on near infrared spectrum principal component and neural network | |
CN112861413A (en) | Biomass water content measurement and modeling method based on near infrared spectrum principal component and neural network | |
CN112858208A (en) | Biomass potassium content measurement and modeling method based on infrared spectrum principal component and neural network | |
CN111337452A (en) | Method for verifying feasibility of spectral data model transfer algorithm | |
CN104596978A (en) | Method for determining quantitative physical indexes of paper-making tobacco sheet by virtue of near-infrared reflectance spectroscopy | |
CN112861411A (en) | Biomass sodium content measurement and modeling method based on near infrared spectrum principal component and neural network | |
CN107884360B (en) | Cigarette paper combustion improver detection method | |
CN112861416A (en) | Biomass fixed carbon measurement and modeling method based on near infrared spectrum principal component and neural network |
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 |