CN114993982A - Method for calculating oil performance parameters and device for monitoring lubricating oil on line - Google Patents
Method for calculating oil performance parameters and device for monitoring lubricating oil on line Download PDFInfo
- Publication number
- CN114993982A CN114993982A CN202210624057.3A CN202210624057A CN114993982A CN 114993982 A CN114993982 A CN 114993982A CN 202210624057 A CN202210624057 A CN 202210624057A CN 114993982 A CN114993982 A CN 114993982A
- Authority
- CN
- China
- Prior art keywords
- data
- calculating
- oil
- matrix
- singular values
- 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 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 239000003921 oil Substances 0.000 title abstract description 36
- 239000010687 lubricating oil Substances 0.000 title abstract description 16
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 18
- 238000001228 spectrum Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 239000007788 liquid Substances 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 51
- 230000003595 spectral effect Effects 0.000 claims description 30
- 239000013598 vector Substances 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010183 spectrum analysis Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000012530 fluid Substances 0.000 claims 1
- 238000004611 spectroscopical analysis Methods 0.000 claims 1
- 239000003153 chemical reaction reagent Substances 0.000 abstract description 2
- 238000000354 decomposition reaction Methods 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- 238000002835 absorbance Methods 0.000 description 2
- 238000012569 chemometric method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004476 mid-IR spectroscopy Methods 0.000 description 2
- 229910052698 phosphorus Inorganic materials 0.000 description 2
- 239000011574 phosphorus Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization 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
- G01N21/359—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
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
Abstract
The invention belongs to the technical field of lubricating oil monitoring, and particularly discloses a method for calculating oil performance parameters and a device for monitoring lubricating oil on line. The method comprises the following steps: collecting near infrared spectrum data of the oil liquid, and calculating a singular value based on the spectrum data; selecting representative feature data based on the singular values; and establishing a model for calculating the oil performance parameters based on the singular values. The invention has the advantages of no damage to samples, no consumption of chemical reagents, simplicity, convenience, high efficiency, low cost, suitability for on-site rapid analysis and capability of providing experimental basis for nondestructive analysis.
Description
Technical Field
The invention relates to the technical field of lubricating oil monitoring, in particular to a method for calculating oil performance parameters and a device for monitoring lubricating oil on line.
Background
Lubricating oil can be called 'blood' of industrial equipment, and lubricating oil monitoring is the most effective method for realizing lubricating wear state monitoring and fault diagnosis of large mechanical equipment. The method has important significance for ensuring safe and reliable operation of mechanical equipment, avoiding unplanned shutdown, realizing energy conservation and efficiency improvement and the like.
The existing oil monitoring is mainly offline monitoring for many years, and the requirement of long-period continuous monitoring of modern equipment can not be met, so that the equipment online oil monitoring technology becomes one of the important development trends of the current equipment lubrication wear failure diagnosis technology. The lubricating oil on-line monitoring eliminates artificial uncertain factors, the sampling and the detection can be carried out simultaneously, and the problem of sampling representativeness can be basically solved as long as the installation position is properly selected.
With the development of the times, the demand of online monitoring of oil by using an infrared spectrum analysis technology is more and more urgent. In the field of on-line monitoring of lubricating oils, attempts have been made to perform on-line monitoring by means of spectral analysis using mid-infrared light. However, mid-infrared spectroscopy equipment is difficult to miniaturize and still requires sample preparation, making it difficult to fully achieve the goals of "on-line" monitoring.
Disclosure of Invention
In order to solve the defects and completely realize online monitoring, the invention firstly provides a method for calculating oil performance parameters, which comprises the following steps:
collecting near infrared spectrum data of the oil liquid, and calculating a singular value based on the spectrum data;
selecting representative feature data based on the singular values;
and establishing a model for calculating the oil performance parameters based on the singular values.
In the method, the collecting near infrared spectrum data of the oil liquid and calculating singular values based on the spectrum data comprises:
s1, collecting m groups of spectral data, wherein m is a positive integer, each group of spectral data is a group of n-dimensional vectors, and n is used for indicating the frequency point number of the near infrared light for spectral analysis;
s2, establishing an m X n X matrix, and calculating a singular value matrix of the X matrix.
In the above method, S2 further includes:
s21, calculating the central vector of each row of data in the X matrix;
s22, subtracting the central vector from each element in the X matrix according to rows to obtain
A matrix;
s23, in the
A matrix of singular values is calculated on the basis of the matrix.
In the above method, the central vector is an arithmetic average of the data of each row.
In the above method, the selecting representative feature data based on the singular value includes:
s3, calculating the ratio of each singular value in the singular value matrix to the sum of all singular values;
and S4, determining the spectral data corresponding to the k singular values with the maximum ratio as representative characteristic data.
In the above method, in S4, the k singular values are determined by the following method:
pre-specifying a value of k; or
And arranging the ratios in a descending order, accumulating the ratios one by one, and determining the number of the accumulated ratios as k when the accumulated value exceeds a preset value.
In the above method, the predetermined value is 0.8 to 0.95.
In the above method, the establishing a model for calculating the oil performance parameters based on the singular values includes:
s5, establishing a corrected model for calculating the performance parameters based on the k selected feature vectors.
In the above method, a model for calculating the performance parameter is established by using a least square method with a penalty term.
In the method, the oil performance parameters include: the viscosity, the service time, the acidity and the element content of the oil liquid.
In the above method, the spectral data includes one or more of transmission data, reflection data, and diffuse reflection data of near infrared light.
Based on the same invention concept, the invention also provides a device for monitoring the oil performance parameters on line, which comprises:
the near infrared spectrum analysis unit is used for acquiring the spectral data of the oil in a near infrared band;
a performance parameter calculation unit for implementing the calculation method according to any one of claims 1 to 11 based on the spectral data.
In the above device, the spectral data includes data related to viscosity, service time, acidity and element content of the oil.
The present invention also provides a computer-readable storage medium having at least one computer instruction stored therein, the at least one computer instruction being loaded and executed by a processor to implement the above method.
The invention also proposes a computer program product comprising computer instructions which, when executed, implement the method described above.
Compared with the prior art, the invention discloses a method for quantitatively analyzing the performance parameters (such as key physicochemical indexes of viscosity, acidity element content and the like) of the lubricating oil by firstly establishing a mathematical correction model (for example, establishing a corresponding relation between infrared spectrum absorbance and the performance parameters of the lubricating oil) and then utilizing a chemometric method (including spectrum pretreatment, wavelength variable selection, under-fitting/over-fitting judgment, abnormal sample elimination and the like). The method does not damage the sample, does not consume chemical reagents, is simple and convenient, has high efficiency and low cost, is very suitable for field rapid analysis, and provides experimental basis for nondestructive analysis.
Drawings
FIG. 1 is a flow chart provided according to some embodiments of the invention;
FIG. 2 is a histogram of feature values provided according to some embodiments of the invention;
FIG. 3 is a graph of a predictive fit to a time parameter provided in accordance with some embodiments of the invention;
FIG. 4 is a graph of a predictive fit to a viscosity parameter provided in accordance with some embodiments of the invention;
fig. 5 is a graph of a predictive fit to the phosphorus content provided in accordance with some embodiments of the invention.
Detailed Description
It should be noted at the outset that although the terms "first," "second," etc. may be used herein to describe various features, these features should not be limited by these terms. These terms are used merely for distinguishing and are not intended to indicate or imply relative importance or ordering. For example, a first feature may be termed a second feature, and, similarly, a second feature may be termed a first feature, without departing from the scope of example embodiments.
It should be further noted that, in the present invention, the steps in the method and the flow are numbered for convenience of reference, but not for limiting the sequence, and if there is a sequence between the steps, the text is taken as the standard.
As described in the background, mid-infrared spectroscopy has been attempted for on-line monitoring of lubricating oils. There are two main reasons why NIR analysis has not been applied to on-line monitoring of lubricating oils for some time: 1) the near infrared spectrum is easily influenced by temperature and hydrogen bonds, and the molecular structure cannot be identified by adopting the traditional spectral analysis method; 2) the near infrared spectrum contains a large number of overlapping broad bands (meaning that there is little "fingerprint"), i.e., the interference between the near infrared bands overlaps, and the oil cannot be quantitatively analyzed based on the lambert-beer law for a single wavelength.
The technical idea of the invention is as follows: the oil to be detected is irradiated by near infrared light, and the oil has physical phenomena of reflection, transmission, diffuse reflection and the like on the infrared light. And performing spectrum analysis on the reflected, transmitted and diffused near infrared light, and establishing a relation function between the spectrum and the oil performance (such as viscosity, acidity and the like), so that the oil performance parameters can be calculated quantitatively.
In order to make the objects, embodiments and advantages of the present invention clearer, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
When near-infrared light is adopted to analyze oil, the dimensionality of data is large. The near infrared spectrum is now defined to be in the range 780nm-2526 nm. If the spectral analysis is performed in units of 1nm wavelength intervals, a set of near infrared spectral data may reach 1747 dimensions. Even with computer-aided computation, it is difficult to extract key and effective information directly from the feature vectors. And for spectrum detection, the interval period of data collection is not very short, so that the data quantity is far smaller than the characteristic quantity. Therefore, in order to effectively utilize the near infrared spectrum data of the oil, a dimension reduction method can be adopted to select a plurality of spectrum data which can represent all data most from a plurality of data, that is, the spectrum data which bears the most performance (parameter) information is selected as an object to be focused by a calculation model.
According to the invention, on the basis of collecting near infrared spectrum data of oil as much as possible, singular values are firstly calculated based on the spectrum data, for example, a Singular Value Decomposition (SVD) method can be adopted to calculate the singular values of a two-dimensional matrix. Then, representative characteristic data are selected based on the singular values, and a model for calculating the oil performance parameters is established.
In particular, FIG. 1 illustrates a flow chart for calculating performance parameters, according to some embodiments of the invention.
In S1, m sets of the spectral data are collected first, where m is a positive integer. It can also be understood how many times the spectral data has been co-acquired. In practical applications, since the oil is contaminated or deteriorated in use as a long-term process, the oil is not sampled very frequently, that is, m is usually a small number, for example, a single digit. Wherein each set of the spectral data is a set of n-dimensional vectors, n is used to indicate the frequency point number of the near-infrared light for spectral analysis, n may be a value of thousands, and the n-dimensional spectral data is reduced to single digits in step S2.
In S2, an m × n X matrix is created, and a singular value matrix of the X matrix is calculated. In particular, a further six accounts of singular values are obtained using the SVD method.
And S21, calculating the central vector of each row of data in the X matrix. The center vector refers to an arithmetic average of the each line of data.
S22, subtracting the central vector from each element in the X matrix according to rows to obtain
And (4) matrix. Because the near infrared spectrum data of the oil liquid has relatively small fluctuation in the whole life cycle of the oil liquid, the difference of the light absorption rate on the corresponding wavelength length is very small, if the original data is directly used for modeling the tiny measurement error, the great influence of the prediction result can be caused, the difference between each element in the X matrix and the average value is analyzed, and convenience is brought to people when a data chart is drawn in the later period.
S23, in the
A matrix of singular values is calculated on the basis of the matrix.
In S3, calculating a ratio of each singular value in the singular value matrix to a sum of all singular values; the higher the proportion of the single singular value to the sum of the singular values, the more spectral information is carried by the corresponding spectral data.
In S4, the spectral data corresponding to the k singular values (k < n) having the largest ratio is determined as representative feature data. In order to reduce the dimension of the data, the data must be rounded. By calculating the proportion of singular values in the sum of all singular values, spectral data which can represent most information in the spectral data is selected, thereby realizing the effect of data dimension reduction.
Specifically, the k singular values may be predetermined to be the first k larger singular values, or may be determined by the following method:
and arranging the ratios in a descending order, accumulating the ratios one by one, and determining the number of the accumulated ratios as k when the accumulated value exceeds a preset value. The predetermined value is used to indicate that the spectrum data corresponding to the singular value can already represent (or already include) most information in all spectrum data, and may generally be 0.8 to 0.95.
The following describes the data selection process by way of example.
For example, assume that singular values (sorted in descending order) obtained by the SVD method are (5,1,0.1,0.1,0.01), where the ratio of the first eigenvalue (5) to the total number of all eigenvalues (singular values) is: 5/(5+1+0.1+0.1+0.01) ═ 0.805; the first characteristic value (5) and the second characteristic value (1) are added together, and the ratio is as follows: (5+1)/(5+1+0.1+0.1+0.01) ═ 0.966. If the preset value is 0.95, the spectral data corresponding to the first and second characteristic values is taken as the dimension reduction result (principal component). That is, after the previous 5-dimensional data is selected, only 2-dimensional data that can represent the main information is retained.
The cumulative contribution rate of the first 2 principal components in the above example is 96.6%, that is, 96.6% of the spectrum information included in the original spectrum data is concentrated into the first 2 principal components, and the remaining 3 spectrum data can be discarded in exchange for a compact data dimension (for convenience of calculation).
In S5, a corrected model for calculating the performance parameter is created based on the k feature vectors selected. For example, a least squares method with a penalty term may be used to model the performance parameters. According to the model, when the oil performance is monitored, more accurate parameters can be calculated.
The following m pieces of near infrared spectrum data X ═ X related to the oil viscosity are collected 1 ,x 2 ,…,x i …,x m The above method will be described in full by way of example.
Spectral data X ═ X 1 ,x 2 ,…,x i …,x m Any one element x in i Is n, i.e., x i ＝[x i1 ,x i2 ,…,x in ]. In other words, for the oil viscosity, sampling is performed on n frequency points in total on the near infrared spectrum, and m times are sampled in total. Thus, X is an m n matrix.
Firstly, calculating the central vector of each row of data in the X matrix, and subtracting the central vector from each row of data to obtain
Matrix:
to which
Matrix, using Singular Value Decomposition (SVD) method, for
Performing singular value decomposition on the matrix:
SVD(X)＝UΣV H
where U is an orthogonal matrix of m x m, V is an orthogonal matrix of n x n, and Σ is a matrix of singular values where only the main diagonal contains non-zero values. The eigenvalues and singular values are squared.
And then selecting the characteristic dimension k after dimensionality reduction according to the proportion of the characteristic value to the sum of all the characteristic values, wherein k is less than n. For a specific example, reference may be made to the above description of S4, which is not repeated herein.
Finally, for each set of collected or new spectral data X, the central vector is subtracted and the matrix is multiplied by v 1 ,v 2 ,…,v k ]Namely the characteristic information after dimension reduction. For the reduced-dimension features, a least squares with penalty term can be used for the calculation.
For example, let the raw spectral data be:
x 1 ＝[1.1,1.2,2.3,2.6,1.9]
x 2 ＝[1.0,1.1,2.3,2.7,2.1]
x 3 ＝[1.2,1.2,2.4,2.5,2.0]
the original data x is processed 1 ～x 3 Merging into an original data matrix X:
then, the center vector of each row of data for X is:
mixing X with X mean Is reduced to
Matrix:
formula SVD (X) U Σ V based on singular value decomposition method H Then, the sigma matrix sum V is obtained H Matrix:
from V above H Selecting singular value with ratio of more than 95%, i.e. 0.95 x 0.95 ═ 90.25% of characteristic value, i.e. first two rows, from matrix, then transposing to obtain reduced-dimension V trancated Matrix:
further, after dimensionality reduction
The matrix is:
in the case where a plurality of performance parameters need to be calculated, for example viscosity, age, metal content, simultaneously, these properties can also be used to establish a matrix Y ═ Y 1 ,y 2 ,…,y p ] T Where p indicates the sequence number of the performance parameter that needs to be predicted, for example, p is 3 in this embodiment. Only by using the Principal Component Analysis (PCA) method to find a low-dimensional singular value matrix which can maximally contain information in the X matrix, a fitting algorithm, such as Ridge Regression, is used to build a model.
Want to pass through
To find the correlation with the performance parameter matrix Y, the weight can be calculated using the least square method
Make it
With minimum error from y. The constant terms are combined into a matrix to yield:
according to the formula of the least square method,
w′＝(X′ T X′) -1 X′ T Y
for data stabilization, a least square with a penalty term is used, for example, λ is set to 0.001, and values of different λ may be tried over a wide range to make y est And Y error is minimal.
Formula w ' ═ X ' according to least squares method ' T X′+λI) -1 X′ T Y, wherein the parameter matrix takes the value of Y H ＝[1,2,3]It is possible to obtain:
calculating to obtain a predicted value of the viscosity of the oil liquid:
fig. 2 is a histogram of feature values provided according to some embodiments of the invention. The sizes of the first 20 eigenvalues are sorted from large to small for the eigenvalues after PCA decomposition. Since the eigenvalue magnitudes differ considerably, logarithmic coordinates are shown here. As can be seen from the figure, in this embodiment, the top 2 feature data can cover more than 90% of the information amount of all the spectrum data. That is, in the embodiment shown in FIG. 2, the data dimension may be reduced from 20 dimensions to 2 dimensions.
Of fig. 3-5, fig. 3 is a graph of predictive fit over time parameters provided according to some embodiments of the invention. FIG. 4 is a graph of a predictive fit to a viscosity parameter provided in accordance with some embodiments of the invention. Fig. 5 is a graph of a predictive fit to the phosphorus content provided in accordance with some embodiments of the invention. In the figure, the solid line is a linear function curve of y ═ x, and the dots represent training data used for training the computational model. The x symbol is test data used to test whether the model is accurate. As can be seen from the figure, the fitting effect of the data is good,
the invention further provides a computer-readable storage medium, in which at least one computer instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the monitoring method.
The present invention also proposes a computer program product comprising computer instructions which, when executed, implement the monitoring method described above.
Generally speaking, the present invention performs pca (principal Component analysis), i.e. principal Component analysis method principal Component analysis, on a sample, reduces the dimension of data, and converts original variables, so that a few new variables express data characteristics of the original variables as much as possible without losing information. And then establishing a model of relevant performance parameters and near infrared spectrum absorbance of the lubricating oil by a partial least square method. With the miniaturization of spectral instruments, the increasingly perfect measurement accessories, the continuous innovation of experimental techniques and the development and the popularization of chemometric methods, the near infrared spectrum analysis technique will play an increasingly important role in the aspects of lubricating oil analysis and monitoring.
Numerous specific details are set forth in this specification. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
Claims (15)
1. A method for calculating oil performance parameters is characterized by comprising the following steps:
collecting near infrared spectrum data of the oil liquid, and calculating a singular value based on the spectrum data;
selecting representative feature data based on the singular values;
and establishing a model for calculating the oil performance parameters based on the singular values.
2. The method of claim 1, wherein the collecting near infrared spectral data of the oil and calculating singular values based on the spectral data comprises:
s1, collecting m groups of spectral data, wherein m is a positive integer, each group of spectral data is a group of n-dimensional vectors, and n is used for indicating the frequency point number of the near infrared light for spectral analysis;
s2, establishing an m X n X matrix, and calculating a singular value matrix of the X matrix.
3. The computing method of claim 2, wherein S2 further includes:
s21, calculating the central vector of each row of data in the X matrix;
s22, subtracting the central vector from each element in the X matrix according to rows to obtain
A matrix;
s23, in the
A matrix of singular values is calculated on the basis of the matrix.
4. The computing method of claim 3, wherein the center vector is an arithmetic mean of each row of data.
5. The computing method of claim 1, wherein said selecting representative feature data based on said singular values comprises:
s3, calculating the ratio of each singular value in the singular value matrix to the sum of all singular values;
and S4, determining the spectral data corresponding to the k singular values with the maximum ratio as representative characteristic data.
6. The computing method of claim 4, wherein in S4, the k singular values are determined by:
pre-specifying a value of k; or
And arranging the ratios in a descending order, accumulating the ratios one by one, and determining the number of the accumulated ratios as k when the accumulated value exceeds a preset value.
7. The calculation method according to claim 6, wherein the predetermined value is 0.8 to 0.95.
8. The method according to claim 1, wherein the modeling the oil performance parameters based on the singular values comprises:
s5, establishing a corrected model for calculating the performance parameters based on the k selected feature vectors.
9. The method of claim 8, wherein the model for calculating the performance parameter is created using a least squares method with a penalty term.
10. The method of calculating according to any one of claims 1 to 9, wherein the oil property parameters include: the viscosity, the service time, the acidity and the element content of the oil liquid.
11. The computing method of any one of claims 1 to 9, wherein the spectral data includes one or more of transmission data, reflection data, and diffuse reflection data of near infrared light.
12. The utility model provides a device of on-line monitoring fluid performance parameter which characterized in that includes:
the near infrared spectrum analysis unit is used for acquiring the spectral data of the oil in a near infrared band;
a performance parameter calculation unit for implementing the calculation method according to any one of claims 1 to 11 based on the spectral data.
13. The apparatus of claim 12, wherein said spectroscopic data comprises data relating to viscosity, age, acidity, elemental content of said oil.
14. A computer-readable storage medium having stored therein at least one computer instruction, the at least one instruction being loaded and executed by a processor to implement the method of any one of claims 1-11.
15. A computer program product, characterized in that the computer program product comprises computer instructions which, when executed, implement the method according to any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210624057.3A CN114993982A (en) | 2022-06-02 | 2022-06-02 | Method for calculating oil performance parameters and device for monitoring lubricating oil on line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210624057.3A CN114993982A (en) | 2022-06-02 | 2022-06-02 | Method for calculating oil performance parameters and device for monitoring lubricating oil on line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114993982A true CN114993982A (en) | 2022-09-02 |
Family
ID=83031804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210624057.3A Pending CN114993982A (en) | 2022-06-02 | 2022-06-02 | Method for calculating oil performance parameters and device for monitoring lubricating oil on line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114993982A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5121337A (en) * | 1990-10-15 | 1992-06-09 | Exxon Research And Engineering Company | Method for correcting spectral data for data due to the spectral measurement process itself and estimating unknown property and/or composition data of a sample using such method |
| US20030023148A1 (en) * | 1999-07-22 | 2003-01-30 | Lorenz Alexander D. | Targeted interference subtraction applied to near-infrared measurement of analytes |
| CN103134763A (en) * | 2011-11-23 | 2013-06-05 | 中国石油化工股份有限公司 | Method for predicting crude oil density by infrared spectroscopy |
| WO2021073908A1 (en) * | 2019-10-17 | 2021-04-22 | Evonik Operations Gmbh | Method for predicting a property value of interest of a material |
| CN112801172A (en) * | 2021-01-25 | 2021-05-14 | 江苏大学 | Chinese cabbage pesticide residue qualitative analysis method based on fuzzy pattern recognition |
| CN113762208A (en) * | 2021-09-22 | 2021-12-07 | 山东大学 | Map conversion method for near infrared spectrum and characteristic map and application thereof |
-
2022
- 2022-06-02 CN CN202210624057.3A patent/CN114993982A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5121337A (en) * | 1990-10-15 | 1992-06-09 | Exxon Research And Engineering Company | Method for correcting spectral data for data due to the spectral measurement process itself and estimating unknown property and/or composition data of a sample using such method |
| US20030023148A1 (en) * | 1999-07-22 | 2003-01-30 | Lorenz Alexander D. | Targeted interference subtraction applied to near-infrared measurement of analytes |
| CN103134763A (en) * | 2011-11-23 | 2013-06-05 | 中国石油化工股份有限公司 | Method for predicting crude oil density by infrared spectroscopy |
| WO2021073908A1 (en) * | 2019-10-17 | 2021-04-22 | Evonik Operations Gmbh | Method for predicting a property value of interest of a material |
| CN112801172A (en) * | 2021-01-25 | 2021-05-14 | 江苏大学 | Chinese cabbage pesticide residue qualitative analysis method based on fuzzy pattern recognition |
| CN113762208A (en) * | 2021-09-22 | 2021-12-07 | 山东大学 | Map conversion method for near infrared spectrum and characteristic map and application thereof |
Non-Patent Citations (2)
| Title |
|---|
| 王凯等: "矩阵的奇异值分解在红外光谱预处理中的应用", 海军航空工程学院学报, vol. 32, no. 3, 30 June 2017 (2017-06-30), pages 270 - 274 * |
| 蔡剑华;肖永良;黎小琴;: "基于广义S变换和奇异值分解的近红外光谱去噪", 光学学报, no. 04, 8 December 2017 (2017-12-08), pages 390 - 399 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109493287B (en) | Deep learning-based quantitative spectral data analysis processing method | |
| CN109324013B (en) | Near-infrared rapid analysis method for constructing crude oil property by using Gaussian process regression model | |
| CN102830087A (en) | Method for quickly identifying food waste oils based on near infrared spectroscopy | |
| CN109187392B (en) | Zinc liquid trace metal ion concentration prediction method based on partition modeling | |
| Thygesen et al. | NIR measurement of moisture content in wood under unstable temperature conditions. Part 2. Handling temperature fluctuations | |
| CN111537845A (en) | Method for identifying aging state of oil paper insulation equipment based on Raman spectrum cluster analysis | |
| CN116935384A (en) | Intelligent detection method for cell abnormality sample | |
| CN110887798B (en) | Nonlinear full-spectrum water turbidity quantitative analysis method based on extreme random tree | |
| CN113076692B (en) | Method for inverting nitrogen content of leaf | |
| CN114993982A (en) | Method for calculating oil performance parameters and device for monitoring lubricating oil on line | |
| Huang et al. | Optimal wavelength selection for hyperspectral scattering prediction of apple firmness and soluble solids content | |
| CN113295673B (en) | Laser-induced breakdown spectroscopy weak supervision feature extraction method | |
| CN107462564B (en) | Quick label-free detection method for aflatoxin B1 based on silver nanocrystals | |
| CN113496218B (en) | Evaluation method and system for hyperspectral remote sensing sensitive wave band selection mode | |
| CN115420726A (en) | Method for rapidly identifying target object by using reconstructed SERS spectrum | |
| CN113029993A (en) | Ultraviolet spectrum rapid total nitrogen online detection method based on attention mechanism | |
| CN112326619A (en) | Micro-fluidic pesticide residue detection method based on double-spectrum technology | |
| CN111562226B (en) | Method and system for analyzing total nitrogen and total phosphorus in seawater based on characteristic peak area of absorption spectrum | |
| Artime et al. | On-line estimation of fresh milk composition by means of VIS-NIR spectrometry and partial least squares method (PLS) | |
| CN113686823B (en) | Water nitrite content estimation method based on transmission spectrum and PLS-Elman neural network | |
| Dan | NIR spectroscopy fruit quality detection algorithm based on the least angle regression model | |
| CN117169166A (en) | TOC rapid detection algorithm combining spectral technology and deep learning technology | |
| No et al. | Multivariate statistics in the analytical laboratory (1): an introduction | |
| CN117929356A (en) | LIBS quantitative analysis method based on Gaussian process regression | |
| Wu et al. | Classification and Quantitative Modeling Analysis of Groundwater Hardness based on Ultraviolet Absorption Spectrum |
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 |