CN110987858A - Method for rapidly detecting oil product by using neural network data model - Google Patents
Method for rapidly detecting oil product by using neural network data model Download PDFInfo
- Publication number
- CN110987858A CN110987858A CN201911207981.6A CN201911207981A CN110987858A CN 110987858 A CN110987858 A CN 110987858A CN 201911207981 A CN201911207981 A CN 201911207981A CN 110987858 A CN110987858 A CN 110987858A
- Authority
- CN
- China
- Prior art keywords
- oil
- model
- oil product
- neural network
- infrared spectrum
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 14
- 238000013499 data model Methods 0.000 title claims abstract description 13
- 239000003921 oil Substances 0.000 claims abstract description 48
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 11
- 239000010687 lubricating oil Substances 0.000 claims abstract description 8
- 238000012937 correction Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 9
- 239000010779 crude oil Substances 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 239000004215 Carbon black (E152) Substances 0.000 abstract description 4
- 239000003963 antioxidant agent Substances 0.000 abstract description 4
- 230000003078 antioxidant effect Effects 0.000 abstract description 4
- 238000004817 gas chromatography Methods 0.000 abstract description 4
- 229930195733 hydrocarbon Natural products 0.000 abstract description 4
- 150000002430 hydrocarbons Chemical class 0.000 abstract description 4
- 239000002199 base oil Substances 0.000 abstract description 2
- 230000008859 change Effects 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000003908 quality control method Methods 0.000 abstract description 2
- 238000007670 refining Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract 2
- 238000011160 research Methods 0.000 abstract 1
- 230000002596 correlated effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010249 in-situ analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 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
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
-
- 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
- G01N21/3554—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for determining moisture content
-
- 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
- G01N2201/127—Calibration; base line adjustment; drift compensation
- G01N2201/12746—Calibration values determination
- G01N2201/12761—Precalibration, e.g. for a given series of reagents
-
- 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
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method for quickly detecting oil products by utilizing a neural network data model, which is used for monitoring key quality of products such as hydrocarbon composition, viscosity, density, antioxidant content and the like in real time usually in the oil refining and oil product production processes, and monitoring water content in oil during operation. At present, the indexes of oil products are mainly determined by a single instrument or a Gas Chromatography (GC) method at home and abroad, so that the determination cost is higher, the measurement time lag is large, the method is not suitable for real-time quality control analysis, and the efficiency is lower. The method is based on near infrared spectrum analysis, a data model is established by using a back propagation artificial neural network method (BP-ANN), so that the method not only can analyze indexes which change linearly, such as viscosity, antioxidant content, hydrocarbon content and the like of an oil product, but also can be used as a data analysis means for processing a nonlinear problem, and can better quantitatively research the relationship between near infrared spectrum information and lubricating oil base oil.
Description
Technical Field
The invention relates to the technical field of oil product analysis, in particular to a method for quickly detecting oil products by using a neural network data model.
Background
In the oil refining and oil product production process, the key quality of the product, such as hydrocarbon composition, viscosity, density, antioxidant content and the like, is usually monitored in real time, and the oil in operation needs to be monitored for water content. At present, the indexes of oil products are mainly determined by a single instrument or a Gas Chromatography (GC) method at home and abroad, so that the determination cost is higher, the measurement time lag is large, the method is not suitable for real-time quality control analysis, and the efficiency is lower.
Disclosure of Invention
Aiming at the defects or the improvement requirements of the prior art, the invention provides a method for quickly detecting oil products by using a neural network data model, and the technical scheme adopted by the invention for solving the technical problems is as follows:
a method for carrying out oil product rapid detection by utilizing a neural network data model comprises the following steps:
step (1): collecting oil products;
step (2): measuring the near infrared spectrum of the oil product obtained in the step (1), performing spectrogram processing on measured spectrum data, and simultaneously measuring the conventional index of the oil product obtained in the step (1), wherein in the step (2), quantitative detection is realized by adopting multiple linear regression and combining with SIMCA (simple in-situ analysis and analysis), classification is performed by utilizing the SIMCA method, the oil content is divided into a plurality of families, and then quantitative calculation is performed on the families by using multiple correction; firstly, 10 samples of new oil to completely aged lubricating oil are taken, the infrared spectrum of the 10 oil samples is scanned, the water content result in the oil samples is obtained through a Karl Fischer potentiometric titrator, the obtained infrared spectrum is correlated with the water content result, and a curve of the water content and the absorbed light in the lubricating oil is obtained through multiple linear regression calculation. (ii) a
And (3): correlating the spectrogram processing data obtained in the step (2) with the conventional indexes of the oil product, and establishing a correction model, wherein the correction model is established by adopting a partial least square method;
and (4): carrying out model verification on the correction model obtained in the step (3), and enabling the verified model to become a final model;
and (5): and obtaining accurate analysis structure and unknown sample determination data through the final model.
Furthermore, the method for establishing the partial least square method comprises the following steps:selecting 120 crude oils to form a correction set sample, taking 120 crude oils as a verification set sample, performing first order differential processing on a spectrogram to eliminate the influence of factors such as sample color and baseline drift, and selecting a spectral interval of 4000-6000cm from a near infrared spectrum-property correlation coefficient diagram-1And (3) participating in the establishment of a model, determining the spectrum optimal main factor number by predicting the square sum of residual errors by adopting an interactive verification method, and judging the adaptability of the model to an unknown crude oil sample by adopting three indexes of the Mahalanobis distance, the spectrum residual errors and the nearest neighbor distance.
Has the advantages that:
the method is mainly based on the near infrared spectrum analysis, a data model is established by using a back propagation artificial neural network method (BP-ANN), so that not only can the indexes of the oil product, such as viscosity, antioxidant content and hydrocarbon content, which change linearly be analyzed, but also the method can be used as a data analysis means for processing the nonlinear problem, and the relationship between the near infrared spectrum information and the lubricating oil base oil can be well and quantitatively researched. The artificial neural network has outstanding nonlinear mapping capability, establishes a nonlinear correction model aiming at the specific nonlinear characteristics of an analysis system, corrects oil near infrared spectrum data models with different distillation ranges, predicts related indexes of oil products, and considers that the neural network technology has better accuracy and anti-interference performance.
Drawings
FIG. 1 is a flow chart of a method for oil rapid testing using a neural network data model;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
As shown in FIG. 1, the invention provides a method for oil product rapid detection by using a neural network data model, comprising the following steps:
step (1): collecting oil products;
step (2): measuring the near infrared spectrum of the oil product obtained in the step (1), performing spectrogram processing on measured spectrum data, and simultaneously measuring the conventional index of the oil product obtained in the step (1), wherein in the step (2), quantitative detection is realized by adopting multiple linear regression and combining with SIMCA (simple in-situ analysis and analysis), classification is performed by utilizing the SIMCA method, the oil content is divided into a plurality of families, and then quantitative calculation is performed on the families by using multiple correction; firstly, 10 samples of new oil to completely aged lubricating oil are taken, the infrared spectrum of the 10 oil samples is scanned, the water content result in the oil samples is obtained through a Karl Fischer potentiometric titrator, the obtained infrared spectrum is correlated with the water content result, and a curve of the water content and the absorbed light in the lubricating oil is obtained through multiple linear regression calculation. (ii) a
And (3): correlating the spectrogram processing data obtained in the step (2) with the conventional indexes of the oil product, and establishing a correction model, wherein the correction model is established by adopting a partial least square method;
and (4): carrying out model verification on the correction model obtained in the step (3), and enabling the verified model to become a final model;
and (5): and obtaining accurate analysis structure and unknown sample determination data through the final model.
The method for establishing the partial least square method comprises the following steps: selecting 120 crude oils to form a correction set sample, taking 120 crude oils as a verification set sample, performing first order differential processing on a spectrogram to eliminate the influence of factors such as sample color and baseline drift, and selecting a spectral interval of 4000-6000cm from a near infrared spectrum-property correlation coefficient diagram-1And (3) participating in the establishment of a model, determining the spectrum optimal main factor number by predicting the square sum of residual errors by adopting an interactive verification method, and judging the adaptability of the model to an unknown crude oil sample by adopting three indexes of the Mahalanobis distance, the spectrum residual errors and the nearest neighbor distance.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (2)
1. A method for rapidly detecting oil products by utilizing a neural network data model is characterized by comprising the following steps: the method comprises the following steps:
step (1): collecting oil products;
step (2): measuring the near infrared spectrum of the oil product obtained in the step (1), performing spectrogram processing on measured spectral data, and simultaneously measuring the conventional index of the oil product obtained in the step (1), wherein in the step, multivariate linear regression is adopted to combine with SIMCA to realize quantitative detection, and the SIMCA method is utilized to classify the oil product, so that the oil product is divided into a plurality of families, and then the families are subjected to quantitative calculation by multivariate correction; firstly, taking 10 samples of new oil to completely aged lubricating oil, scanning the infrared spectrum of the 10 oil samples, obtaining a water content result in the oil samples through a Karl Fischer potentiometric titrator, correlating the obtained infrared spectrum with the water content result, and calculating through multiple linear regression to obtain a curve of water content and absorbed light in the lubricating oil;
and (3): correlating the spectrogram processing data obtained in the step (2) with the conventional indexes of the oil product, and establishing a correction model, wherein the correction model is established by adopting a partial least square method;
and (4): carrying out model verification on the correction model obtained in the step (3), and enabling the verified model to become a final model;
and (5): and obtaining accurate analysis structure and unknown sample determination data through the final model.
2. The method for oil product rapid detection by using the neural network data model as claimed in claim 1, wherein the method for establishing the partial least squares method comprises: selecting 120 crude oils to form a calibration set sample, taking 120 crude oils as a verification set sample, performing first order differential processing on a spectrogram to eliminate the influence of sample color and baseline drift, and selecting a spectral interval of 4000--1The method is characterized in that a participation model is established, the optimal main factor number of the spectrum is determined by predicting the square sum of residual errors by adopting an interactive verification method, and the unknown source is judged by adopting three indexes of the Mahalanobis distance, the spectrum residual errors and the nearest neighbor distance to judge a modelSuitability of oil samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911207981.6A CN110987858A (en) | 2019-11-30 | 2019-11-30 | Method for rapidly detecting oil product by using neural network data model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911207981.6A CN110987858A (en) | 2019-11-30 | 2019-11-30 | Method for rapidly detecting oil product by using neural network data model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110987858A true CN110987858A (en) | 2020-04-10 |
Family
ID=70088959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911207981.6A Pending CN110987858A (en) | 2019-11-30 | 2019-11-30 | Method for rapidly detecting oil product by using neural network data model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110987858A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112129729A (en) * | 2020-10-22 | 2020-12-25 | 济南弗莱德科学仪器有限公司 | Method for rapidly analyzing content of hydrocarbons and dimethyl ether in liquefied petroleum gas |
| CN112198136A (en) * | 2020-11-13 | 2021-01-08 | 西安热工研究院有限公司 | Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum |
| CN114088927A (en) * | 2021-12-02 | 2022-02-25 | 绍兴淼汇能源科技有限公司 | Online health monitoring method for lubricating oil |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102374975A (en) * | 2010-08-19 | 2012-03-14 | 中国石油化工股份有限公司 | Method for predicting physical property data of oil product by using near infrared spectrum |
| CN107478598A (en) * | 2017-09-01 | 2017-12-15 | 广东省智能制造研究所 | A kind of near-infrared spectral analytical method based on one-dimensional convolutional neural networks |
| CN107976419A (en) * | 2016-10-21 | 2018-05-01 | 中国石油化工股份有限公司 | A kind of method that its property is predicted by oil product near infrared spectrum |
-
2019
- 2019-11-30 CN CN201911207981.6A patent/CN110987858A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102374975A (en) * | 2010-08-19 | 2012-03-14 | 中国石油化工股份有限公司 | Method for predicting physical property data of oil product by using near infrared spectrum |
| CN107976419A (en) * | 2016-10-21 | 2018-05-01 | 中国石油化工股份有限公司 | A kind of method that its property is predicted by oil product near infrared spectrum |
| CN107478598A (en) * | 2017-09-01 | 2017-12-15 | 广东省智能制造研究所 | A kind of near-infrared spectral analytical method based on one-dimensional convolutional neural networks |
Non-Patent Citations (3)
| Title |
|---|
| 周孟然 等: "《煤矿突水水源的激光光谱检测技术研究》", 31 March 2017 * |
| 焦昭杰 等: "近红外光谱法快速测定油品中的水分", 《光谱实验室》 * |
| 王艳斌: "人工神经网络在近红外分析方法中的应用及深色油品的分析", 《中国优秀博硕士学位论文全文数据库（博士）工程科技Ⅰ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112129729A (en) * | 2020-10-22 | 2020-12-25 | 济南弗莱德科学仪器有限公司 | Method for rapidly analyzing content of hydrocarbons and dimethyl ether in liquefied petroleum gas |
| CN112198136A (en) * | 2020-11-13 | 2021-01-08 | 西安热工研究院有限公司 | Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum |
| CN114088927A (en) * | 2021-12-02 | 2022-02-25 | 绍兴淼汇能源科技有限公司 | Online health monitoring method for lubricating oil |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110987858A (en) | Method for rapidly detecting oil product by using neural network data model | |
| CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
| CN101995389B (en) | Method for fast recognition of crude oil variety through near infrared spectrum | |
| CA2652336A1 (en) | Methods and apparatus for analysis of downhole asphaltene gradients and applications thereof | |
| CN112525879B (en) | In-situ identification and rapid quantification method for coal rock micro-components | |
| CN101726451A (en) | Method for measuring viscosity index of internal combustion engine oil | |
| CN110702663A (en) | Nondestructive rapid detection method for storage time of frozen meat | |
| CN114252430B (en) | Online pulp grade detection method based on laser-induced breakdown spectroscopy technology | |
| CN104297200A (en) | Method for identifying asphalt brands through infrared spectrum combined with high-temperature simulation and distillation technology | |
| CN109615145A (en) | A kind of method of the physical property of quick predict difference degree of aging matrix pitch | |
| CN106525755A (en) | Oil-sand pH value testing method based on near infrared spectroscopy technology | |
| CN105223140A (en) | The method for quickly identifying of homology material | |
| CN105954228A (en) | Method for measuring content of sodium metal in oil sand based on near infrared spectrum | |
| CN108663334B (en) | Method for searching spectral characteristic wavelength of soil nutrient based on multi-classifier fusion | |
| CN104237159A (en) | Method for analyzing content of dibutyl phthalate in mixed material through near infrared spectrum | |
| CN109668856B (en) | Method and apparatus for predicting hydrocarbon group composition of LCO hydrogenation feedstock and product | |
| CN112485238B (en) | Method for identifying turmeric essential oil producing area based on Raman spectrum technology | |
| CN109709060B (en) | Method for measuring asphalt softening point, penetration degree and mass loss | |
| CN103134764B (en) | The method of prediction true boiling point curve of crude oil is composed by transmitted infrared light | |
| CN107688007A (en) | A kind of detection method of the heat conduction oil quality based on near-infrared spectral analysis technology | |
| CN111337452A (en) | Method for verifying feasibility of spectral data model transfer algorithm | |
| CN115236024A (en) | Training method, determination method and device for model for determining content of total acids and total esters in wine | |
| CN113916817B (en) | Spectrum method chromaticity online measurement method for urban living drinking water | |
| CN104181125A (en) | Method for rapidly determining Kol-bach value of beer malt | |
| CN105866065B (en) | Methenamine content analysis method in a kind of methenamine-acetum |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200410 |