CN112198136A - Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum - Google Patents
Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum Download PDFInfo
- Publication number
- CN112198136A CN112198136A CN202011270488.1A CN202011270488A CN112198136A CN 112198136 A CN112198136 A CN 112198136A CN 202011270488 A CN202011270488 A CN 202011270488A CN 112198136 A CN112198136 A CN 112198136A
- Authority
- CN
- China
- Prior art keywords
- acid value
- infrared spectrum
- turbine oil
- mid
- oil
- 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
- 239000002253 acid Substances 0.000 title claims abstract description 67
- 239000010723 turbine oil Substances 0.000 title claims abstract description 37
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 48
- 239000003921 oil Substances 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 238000010521 absorption reaction Methods 0.000 claims abstract description 14
- 239000010736 steam turbine oil Substances 0.000 claims abstract description 12
- 238000009659 non-destructive testing Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims abstract description 4
- 238000012937 correction Methods 0.000 claims description 11
- 230000032683 aging Effects 0.000 claims description 9
- 239000003209 petroleum derivative Substances 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000012569 chemometric method Methods 0.000 claims description 4
- 238000010977 unit operation Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000001066 destructive effect Effects 0.000 claims 1
- 238000001228 spectrum Methods 0.000 description 7
- 238000010200 validation analysis Methods 0.000 description 7
- 238000012795 verification Methods 0.000 description 6
- RTZKZFJDLAIYFH-UHFFFAOYSA-N Diethyl ether Chemical compound CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 description 4
- 239000010687 lubricating oil Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 239000002199 base oil Substances 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005461 lubrication Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- WRIDQFICGBMAFQ-UHFFFAOYSA-N (E)-8-Octadecenoic acid Natural products CCCCCCCCCC=CCCCCCCC(O)=O WRIDQFICGBMAFQ-UHFFFAOYSA-N 0.000 description 1
- LQJBNNIYVWPHFW-UHFFFAOYSA-N 20:1omega9c fatty acid Natural products CCCCCCCCCCC=CCCCCCCCC(O)=O LQJBNNIYVWPHFW-UHFFFAOYSA-N 0.000 description 1
- QSBYPNXLFMSGKH-UHFFFAOYSA-N 9-Heptadecensaeure Natural products CCCCCCCC=CCCCCCCCC(O)=O QSBYPNXLFMSGKH-UHFFFAOYSA-N 0.000 description 1
- ZQPPMHVWECSIRJ-UHFFFAOYSA-N Oleic acid Natural products CCCCCCCCC=CCCCCCCCC(O)=O ZQPPMHVWECSIRJ-UHFFFAOYSA-N 0.000 description 1
- 239000005642 Oleic acid Substances 0.000 description 1
- 235000013405 beer Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009835 boiling Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- QXJSBBXBKPUZAA-UHFFFAOYSA-N isooleic acid Natural products CCCCCCCC=CCCCCCCCCC(O)=O QXJSBBXBKPUZAA-UHFFFAOYSA-N 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- ZQPPMHVWECSIRJ-KTKRTIGZSA-N oleic acid Chemical compound CCCCCCCC\C=C/CCCCCCCC(O)=O ZQPPMHVWECSIRJ-KTKRTIGZSA-N 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer 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
- G01N2021/3595—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using FTIR
-
- 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 nondestructive testing method for a turbine oil acid value based on mid-infrared spectrum, which comprises the steps of collecting infrared spectrum and acid value data of a turbine oil sample, preprocessing the collected infrared spectrum by a chemometrics method, establishing a model of the relation between an absorption waveband and the acid value in a sample spectrogram by adopting a partial least square-artificial neural network method, finally introducing an infrared spectrogram of turbine oil to be tested into the model, and obtaining the acid value of the turbine oil to be tested by model analysis. The detection method can obtain the detection report of the oil acid value of the steam turbine under the condition of not damaging the sample, and guides the oil change of the steam turbine oil and the fault analysis of equipment.
Description
Technical Field
The invention belongs to the technical field of lubricating oil detection, and relates to a nondestructive detection method for an oil acid value of a steam turbine based on a mid-infrared spectrum.
Background
The turbine oil, also called turbine oil, is an important industrial lubricating oil, which mainly plays roles of lubrication, heat dissipation, sealing and the like in the operation of a turbine, and the quality of the turbine oil directly affects the economy and safety of a power plant generator set. The detection of the acid value is of great significance in the aspects of new oil acceptance and operation oil supervision. For acceptance detection of new oil, the refining level of the base oil of the lubricating oil can be reflected, and the lower the acid value, the higher the refining level of the base oil is represented, and the better the quality is. On the other hand, in the case of a lubricating oil of a working oil, the acid value indicates the degree of oxidation of the working oil and is an important index for judging the lubrication state of equipment.
The method for detecting the acid value of the steam turbine oil mainly adopts single physicochemical monitoring, and along with the development of industrialization, the complicated detection program of the traditional detection means has serious hysteresis, and the requirements of complicated and continuous development of large-scale mechanical equipment can not be met, so that new testing technologies are developed. The infrared spectrum technology is widely applied to the rapid detection of oil products due to the characteristics of no need of sample pretreatment, no damage to samples, rapid detection and the like. However, the overlapping of the infrared spectrum peaks is a main reason for influencing the accuracy of the detection result, and the quantitative analysis of the sample needs to be realized by combining a chemometrics related method.
The relatively mature regression modeling method includes Partial Least Squares (PLS) and the like, and when a multivariate calibration method such as the PLS method is applied, the researched spectroscopic systems are considered to have linear additivity, namely completely or substantially follow the lambert beer law. In some data analysis, however, there is some non-linearity between the spectral factor and the desired property. In addition, the sample itself has complex and varied components, and influences each other, and in addition, the noise and baseline drift of the device cause nonlinearity. Although Partial Least Squares (PLS) based on factor analysis can correct partial non-linearity under certain circumstances, if non-linearity is clearly present, a correction model with high predictive power cannot be fitted.
An artificial neural network is a highly interconnected and complex nonlinear system. The neural network system is formed by a large number of simple neuron interconnections, and simultaneously, the signal receiving and processing are completed. The artificial neural network mainly comprises five parts of input, network weight and threshold, a summation unit, a transfer function and output. The function of step-by-step storage and parallel data processing can realize very good nonlinear expression, make up for the defects of the partial least square method, and better establish a model.
In experiments, the change of the acid value of the turbine oil in the operation process is also nonlinear, and compared with the standard of operation maintenance of other industrial oils, the turbine oil has the characteristic properties and lower acid value requirement (the operation oleic acid value is generally required to be not more than 0.3mgKOH/g), so that the detection of the acid value of the turbine oil is an important part of the nondestructive detection of the acid value of an oil product.
Disclosure of Invention
The invention aims to solve the problems and aims to provide a nondestructive testing method for the oil acid value of a steam turbine based on mid-infrared spectrum.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a nondestructive detection method for the acid value of turbine oil based on mid-infrared spectrum includes collecting the infrared spectrum and acid value data of a turbine oil sample, preprocessing the collected infrared spectrum by chemometrics method, establishing a model of the relation between absorption wave band and acid value in a sample spectrogram by partial least square-artificial neural network method, introducing the infrared spectrogram of the turbine oil to be detected into the model, and analyzing the model to obtain the acid value of the turbine oil to be detected.
The invention has the further improvement that the steam turbine oil sample comprises two parts, wherein one part is a power plant unit operation oil sample; the other part was samples obtained by aging the same grade of oil for different time intervals according to the DL/T429.6 electric oil open cup aging method.
The invention is further improved in that the aging time is 12h, 24h and 72 h.
A further improvement of the invention is that the acid number data are determined by national standard petroleum products acid number determination GB/T264, GB/T7304, GB/T28552 or GB/T258.
The further improvement of the invention is that the specific process for collecting the infrared spectrum of the steam turbine oil sample comprises the following steps: collecting a Fourier transform mid-infrared spectrum of a steam turbine oil sample, wherein the spectral scanning range is 650cm-1～4000cm-1Resolution of 4cm-1The number of scans was 32.
A further improvement of the invention is that the chemometric method is one or more of normalisation, derivative, smoothing and signal correction.
A further development of the invention consists in that the absorption band is determined by the correlation coefficient method.
The invention has the further improvement that when a model of the relation between the absorption wave band and the acid value in a sample spectrogram is established by adopting a partial least square-artificial neural network method, the number of network main factors of the partial least square-artificial neural network is 10, the number of nodes of a hidden layer is 10, and the initial learning rate is 0.1.
Compared with the prior art, the invention has the following beneficial effects: the method comprises the steps of analyzing according to an absorption peak of the turbine oil reflected in a specific waveband of a mid-infrared spectrum, establishing a quantitative analysis model by using an infrared spectrogram and an oil acid value, and accurately obtaining performance information of an unknown sample. And (3) introducing the infrared spectrogram of the turbine oil to be detected into a model, and analyzing by using the detection model to obtain the acid value of the turbine oil to be detected. The invention can truly realize the nondestructive monitoring of the oil acid value of the steam turbine and overcome the complex procedures of the traditional detection of the oil acid value of the steam turbine and the destructiveness of the oil.
Drawings
FIG. 1 is an infrared spectrum of a representative sample.
Fig. 2 is an enlarged view of fig. 1 at block.
FIG. 3 is a graph showing the relationship between the measured value and the true value of the acid value model established by the partial least squares-artificial neural network regression method for the nondestructive detection of the oil acid value of the steam turbine based on the mid-infrared spectrum.
Detailed Description
For a better understanding of the method, the method is described in further detail below with reference to specific examples, but the scope of the invention is not limited to the examples shown.
The detection method is based on the combination of the infrared spectrum information of the steam turbine oil molecules and a chemometrics method, and comprises the following specific processes: collecting a steam turbine oil sample, collecting infrared spectrum and acid value data, preprocessing the collected infrared spectrum by a chemometrics method, establishing a model of the relation between an absorption waveband in a sample spectrogram and the acid value by adopting a partial least square-artificial neural network method, finally guiding an infrared spectrogram of the steam turbine oil to be detected into the model, and obtaining the acid value of the steam turbine oil to be detected by model analysis.
The specific process is as follows:
1) preparing an experimental sample, wherein the turbine oil acid value sample needs to comprise two parts, and one part is a power plant unit operation oil sample; the other part is a sample obtained by sampling the new oil with the same grade at different time intervals of 12h, 24h, 72h and the like according to the DL/T429.6 electric oil open cup aging method. Compared with the prepared acid value sample, the sample obtained by sampling the open cup at different time intervals of aging for 12h, 24h, 72h and the like and the power plant unit operation oil sample can represent the real component after the radical change of the oil liquid after operation.
2) And measuring acid value data by using national standard petroleum product acid value measurement methods GB/T264, GB/T7304, GB/T28552 or GB/T258 to serve as a true value of the acid value of the sample.
3) Collecting a mid-infrared spectrogram of a steam turbine oil sample: collecting Fourier transform mid-infrared spectrum (FTIR) of steam turbine oil sample under the same environmental condition, wherein the spectrum scanning range is 650cm-1～4000cm-1Resolution of 4cm-1The number of scans is 32, and may be a single measurement or an average of multiple measurements.
4) And the obtained spectrogram of the intermediate infrared sample is processed by adopting a chemometric method (one or more methods in standardization, derivative, smoothing and signal correction), so that the signal-to-noise ratio is improved, and the deviation of a model caused by the flattening and scattering of the sample spectrum due to environmental difference and the influence of an instrument per se is reduced.
5) Correction set and verification set
All turbine oil samples were classified into correction and validation sets using the Kennard-Stone (K-S) classification based on Mahalanobis distance between variables, making both sets of data samples representative. The samples are classified according to the proportion of 80 percent of the samples in the correction set.
6) Establishment of sample model
Before the model is built, an infrared spectrogram absorption wave band needs to be screened, a correlation coefficient method is adopted for selecting the absorption wave band, and absorption wave points with high correlation with an acid value are screened to participate in the model building. The larger the absolute value of the correlation coefficient is, the more the information of the wavelength is, the data correlation of the threshold value between 0.8 and 1 is generally considered to be strong, and the wavelength with the correlation coefficient of the wavelength and the basic data larger than the threshold value is selected to participate in model establishment during calculation or different threshold value models are selected for comparison.
The spectrum and acid value data are processed by adopting an Artificial Neural Network (ANN), the data are decomposed by combining a Partial Least Squares (PLS) method before the artificial neural network is used, the number of network main factors is 10, the number of nodes of a hidden layer is 10, the initial learning rate is 0.1, and a model is established.
And inputting the infrared spectrogram of the verification set sample into the model to feed back the acid value data of the verification set sample. Finally to correct the set correlation coefficient (R)C) Standard Error of Calibration (SEC) and validation set correlation coefficient (R)P) And a Standard Error of Prediction (SEP) evaluation model. The closer the correlation coefficient is to 1, the better the regression effect of the model is, and the smaller the standard deviation is, the stronger the prediction capability of the model is.
The following are specific examples of the present invention.
1) Preparing experimental samples and determining acid value data of the samples
The sample comprises 5 running oil 32# of turbine oil (with an acid value of 0.034 mgKOH/g-0.150 mgKOH/g) and 27 new oil 32# of turbine oil (with an acid value of 0.120mgKOH/g) which is aged by an open cup aging method (with an acid value of 0.061-0.293 mgKOH/g) at different time intervals, the total number is 32, and the sample has an acid collection value range of 0.034-0.293 mgKOH/g and has gradient property. The acid value of the petroleum product is determined by adopting the national standard GB/T264.
2) Spectrum collection
Referring to fig. 1 and 2, the infrared spectrum of the sample is statically collected at room temperature in an environment of 25 ℃, the atmospheric environment is used as a background, and the spectrum collection range is 650-4000 cm-1Data interval 0.482cm-1Resolution of 4cm-1The number of scans was 32.After the sample is collected, analytically pure petroleum ether with the boiling range of 60-90 ℃ is used for cleaning until the surface of the sampling crystal is free from stains and particles, and redundant petroleum ether is volatilized through illumination of a lamp to dry the surface of the sampling crystal. The acquired spectral peaks are overlapped seriously, and the relationship between the spectrogram information and the oil product property is strengthened by a chemometric method for quantitative analysis.
3) Spectral preprocessing
And (3) adopting a spectrum pretreatment method of first-order difference derivation for the collected infrared spectrum in the turbine oil.
4) Correction set and verification set
The samples were classified into a calibration set and a validation set using Kennard-Stone (K-S) classification based on Mahalanobis distance between variables, making both sets of data samples representative. The samples are classified according to the proportion of 80 percent of the samples in the correction set.
5) Establishment of sample model
Before the model is established, spectrogram absorption wave bands need to be screened, a correlation coefficient method is adopted to be 0.8, and 132 absorption wave points are screened in total to participate in calculation. And (3) processing the spectrum and acid value data by adopting an Artificial Neural Network (ANN), decomposing the data by adopting a Partial Least Squares (PLS) method by adopting the artificial neural network before calculation, wherein the number of network main factors is 10, the number of nodes of a hidden layer is 10, the initial learning rate is 0.1, and establishing a model.
And (4) introducing the infrared spectrum of the turbine oil to be detected into the model, and analyzing to obtain the acid value of the sample to be detected.
And inputting the infrared spectrogram of the verification set sample into the model and simultaneously feeding back the acid value data of the verification set sample. Correlation coefficient (R) of model correction setC) 0.986, standard deviation of correction Set (SEC) 0.022, and correlation coefficient of validation set (R)P) 0.825 and the standard deviation (SEP) of the validation set is 0.024, and the comparison result of the measured value of the validation set and the true value is shown in the table 1 and the figure 3, and the relative error of the measurement is less than 14 percent, which shows that the correlation between the acid value data and the sample signal is better.
Table 1 validation set measurement error
Acid value obtained by national standard petroleum product acid value determination method GB/T264.
Claims (8)
1. A turbine oil acid value nondestructive testing method based on mid-infrared spectrum is characterized by collecting infrared spectrum and acid value data of a turbine oil sample, preprocessing the collected infrared spectrum by a chemometrics method, establishing a model of the relation between an absorption waveband and the acid value in a sample spectrogram by adopting a partial least square-artificial neural network method, finally introducing an infrared spectrogram of turbine oil to be tested into the model, and obtaining the acid value of the turbine oil to be tested by model analysis.
2. The nondestructive testing method for the turbine oil acid value based on the mid-infrared spectrum is characterized in that the turbine oil sample comprises two parts, wherein one part is a power plant unit operation oil sample; the other part was samples obtained by aging the same grade of oil for different time intervals according to the DL/T429.6 electric oil open cup aging method.
3. The nondestructive testing method for the turbine oil acid value based on the mid-infrared spectrum is characterized in that the aging time is 12 hours, 24 hours and 72 hours.
4. The nondestructive testing method for the turbine oil acid value based on the mid-infrared spectrum is characterized in that the acid value data is measured by national standard petroleum product acid value measurement methods GB/T264, GB/T7304, GB/T28552 or GB/T258.
5. The nondestructive testing method for the turbine oil acid value based on the mid-infrared spectrum of claim 1, characterized in that the specific process of collecting the infrared spectrum of the turbine oil sample is as follows: collecting a Fourier transform mid-infrared spectrum of a steam turbine oil sample, wherein the spectral scanning range is 650cm-1～4000cm-1Resolution of 4cm-1The number of scans was 32.
6. The mid-infrared spectrum-based non-destructive detection method for turbine oil acid numbers according to claim 1, wherein the chemometric method is one or more of normalization, derivative, smoothing, and signal correction.
7. The nondestructive testing method for the turbine oil acid value based on the mid-infrared spectrum of claim 1, characterized in that the absorption band is determined by a correlation coefficient method.
8. The nondestructive testing method for the oil acid value of the turbine based on the mid-infrared spectrum of claim 1, characterized in that when a partial least squares-artificial neural network method is adopted to establish a model of the relationship between the absorption waveband and the acid value in a sample spectrogram, the number of network main factors of the partial least squares-artificial neural network is 10, the number of nodes of a hidden layer is 10, and the initial learning rate is 0.1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011270488.1A CN112198136A (en) | 2020-11-13 | 2020-11-13 | Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011270488.1A CN112198136A (en) | 2020-11-13 | 2020-11-13 | Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112198136A true CN112198136A (en) | 2021-01-08 |
Family
ID=74034373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011270488.1A Pending CN112198136A (en) | 2020-11-13 | 2020-11-13 | Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112198136A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113484275A (en) * | 2021-07-08 | 2021-10-08 | 云南中烟工业有限责任公司 | Method for rapidly predicting oil content in fresh tobacco leaves by adopting peak separation analysis technology based on mid-infrared spectrum |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5420041A (en) * | 1992-09-28 | 1995-05-30 | Kurashiki Boseki Kabushiki Kaisha | Method of acid value determination by infrared absorption |
| CN102954945A (en) * | 2011-08-25 | 2013-03-06 | 中国石油化工股份有限公司 | Method for determining crude oil acid value by infrared spectroscopy |
| CN106645012A (en) * | 2016-12-19 | 2017-05-10 | 中国石油化工股份有限公司 | Method for carrying out rapid quantitative analysis on ester compounds in finished product gasoline and diesel |
| CN106841083A (en) * | 2016-11-02 | 2017-06-13 | 北京工商大学 | Sesame oil quality detecting method based on near-infrared spectrum technique |
| CN110987858A (en) * | 2019-11-30 | 2020-04-10 | 江苏万标检测有限公司 | Method for rapidly detecting oil product by using neural network data model |
-
2020
- 2020-11-13 CN CN202011270488.1A patent/CN112198136A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5420041A (en) * | 1992-09-28 | 1995-05-30 | Kurashiki Boseki Kabushiki Kaisha | Method of acid value determination by infrared absorption |
| CN102954945A (en) * | 2011-08-25 | 2013-03-06 | 中国石油化工股份有限公司 | Method for determining crude oil acid value by infrared spectroscopy |
| CN106841083A (en) * | 2016-11-02 | 2017-06-13 | 北京工商大学 | Sesame oil quality detecting method based on near-infrared spectrum technique |
| CN106645012A (en) * | 2016-12-19 | 2017-05-10 | 中国石油化工股份有限公司 | Method for carrying out rapid quantitative analysis on ester compounds in finished product gasoline and diesel |
| CN110987858A (en) * | 2019-11-30 | 2020-04-10 | 江苏万标检测有限公司 | Method for rapidly detecting oil product by using neural network data model |
Non-Patent Citations (3)
| Title |
|---|
| 史令飞等: "最小二乘支持向量机结合红外光谱法测定润滑油酸值", 《理化检验-化学分册》 * |
| 宋庆媛等: "采用红外光谱和化学计量学结合方法测定汽轮机油中水分含量", 《汽轮机技术》 * |
| 韩晓等: "基于ＢＰ－神经网络的航空煤油总酸值近红外光谱快速检测", 《分析科学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113484275A (en) * | 2021-07-08 | 2021-10-08 | 云南中烟工业有限责任公司 | Method for rapidly predicting oil content in fresh tobacco leaves by adopting peak separation analysis technology based on mid-infrared spectrum |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101893561B (en) | Near infrared spectrum quick test method of new oil quality of lubricating oil | |
| CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
| CN109324013B (en) | Near-infrared rapid analysis method for constructing crude oil property by using Gaussian process regression model | |
| CN109324014B (en) | Self-adaptive near-infrared rapid prediction method for crude oil properties | |
| CN112557834B (en) | Aging diagnosis method for oiled paper insulation equipment based on Raman spectrum | |
| CN101915744A (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
| CN102636454A (en) | Method for quickly measuring content of low carbon number fatty acid in edible oil by near infrared spectrum | |
| CN104749132A (en) | Method for measuring content of azodicarbonamide in flour | |
| CN111537845A (en) | Method for identifying aging state of oil paper insulation equipment based on Raman spectrum cluster analysis | |
| CN102841069B (en) | Method for rapidly identifying types of crude oil by using mid-infrared spectrum | |
| CN105784628A (en) | Method for detecting chemical composition of soil organic matter with mid-infrared spectra | |
| CN111537469A (en) | Apple quality rapid nondestructive testing method based on near-infrared technology | |
| CN102954946B (en) | By the method for infrared spectrum measurement sulfur content in crude oil | |
| Li et al. | Aging assessment of oil-impregnated-paper electrical equipment via near infrared spectroscopy powered by improved PCA-RBF-NN: Modelling and field practices | |
| CN112198136A (en) | Nondestructive detection method for turbine oil acid value based on mid-infrared spectrum | |
| CN105954228A (en) | Method for measuring content of sodium metal in oil sand based on near infrared spectrum | |
| CN112858208A (en) | Biomass potassium content measurement and modeling method based on infrared spectrum principal component and neural network | |
| CN110567385A (en) | Hyperspectral technology-based construction thickness detection method for building reflective insulation coating | |
| CN114414524A (en) | Method for rapidly detecting properties of aviation kerosene | |
| CN115236024A (en) | Training method, determination method and device for model for determining content of total acids and total esters in wine | |
| Cheng et al. | Recognition of MIR Data of Semen Armeniacae Amarum and Semen Persicae Using Discrete Wavelet Transformation and BP‐Artificial Neural Network | |
| CN103134762B (en) | The method of crude oil nitrogen content is predicted by infrared spectrum | |
| CN112861411A (en) | Biomass sodium content measurement and modeling method based on near infrared spectrum principal component and neural network | |
| WO2024011687A1 (en) | Method and apparatus for establishing oil product physical property fast evaluation model | |
| CN112861412A (en) | Biomass volatile component content 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210108 |