Lubricating oil conductivity temperature compensation method based on minimum distance discrimination method

Abstract

The lubricating oil conductivity temperature compensation method based on the minimum distance discrimination method comprises the following steps: S1, collecting and testing lubricating oil with different pollution degrees, and establishing a relationship between the temperature and the conductivity of the lubricating oil; s2, by taking the collected and tested lubricating oil as an object, establishing a relationship between conductivity and different temperatures, and establishing a database system; and S3, judging the pollution degree grade of the lubricating oil at different temperatures based on a minimum distance judgment method. According to the method, the temperature compensation of the conductivity of the lubricating oil is realized by collecting the detection test data of the temperatures and the conductivity of various lubricating oil and through a minimum distance discrimination algorithm of a supervision mode, so that the real monitoring and diagnosis of the oil product of the lubricating oil are realized.

Description

Technical Field

[0001] The invention relates to a lubricating oil quality detection technology, in particular to a lubricating oil conductivity temperature compensation method based on a minimum distance discrimination method. Background Art

[0002] The quality of lubricating oil directly determines whether the equipment can operate normally, so monitoring the characteristics of lubricating oil has become a critical process. Since lubricating oil has insulating properties, when the oil is new or clean, its insulation is good. As the lubricating oil runs in the moving equipment, the characteristics of the lubricating oil will change, especially when the lubricating oil is infiltrated with water, severely worn, aged, etc., the lubricating oil will be contaminated and deteriorated. At this time, the conductive properties of the lubricating oil will change significantly and dramatically. Therefore, using lubricating oil conductivity to monitor the quality of lubricating oil is becoming an important means of detecting lubricating oil.

[0003] However, the conductivity of lubricating oil is greatly affected by temperature. When the temperature rises, its conductivity will increase, and when the temperature drops, its conductivity will decrease. Therefore, when monitoring the lubricating oil, the change in temperature will affect the change in conductivity, which will affect the true judgment of the quality of the lubricating oil. Therefore, it is necessary to perform temperature compensation on the conductivity of the lubricating oil to eliminate the influence of temperature on the change in conductivity and realize the true monitoring and diagnosis of the lubricating oil.

[0004] In the prior art, the related patents and literature materials on monitoring lubricating oil by conductivity index focus on products that monitor lubricating oil quality by monitoring lubricating oil conductivity based on various principles and methods, but no better method has been formed for the problem of conductivity compensation. Summary of the invention

[0005] In view of the above-mentioned defects, the purpose of the present invention is to propose a lubricating oil conductivity temperature compensation method based on a minimum distance discrimination method in a supervisory mode. The method collects a variety of lubricating oil temperature and conductivity detection test data, and realizes temperature compensation of lubricating oil conductivity through a minimum distance discrimination algorithm in a supervisory mode, thereby realizing true monitoring and diagnosis of lubricating oil products.

[0006] To achieve this object, the present invention adopts the following technical solutions:

[0007] The lubricating oil conductivity temperature compensation method based on the minimum distance discrimination method includes the following steps:

[0008] S1. Collect and test lubricating oils with different contamination levels, and establish the relationship between lubricating oil temperature and conductivity;

[0009] S2. Taking the collected and tested lubricating oil as the object, establish the relationship between conductivity and different temperatures, and establish a database system;

[0010] S3. Determine the contamination level of lubricating oil at different temperatures based on the minimum distance discrimination method.

[0011] Furthermore, the step S1 is specifically as follows:

[0012] S11. Determine a representative type of lubricant, obtain lubricant samples of this type of lubricant under different degrees of contamination, and classify the lubricant samples with different degrees of contamination;

[0013] S12. Perform a temperature test on the lubricating oil samples, collect the conductivity values ​​of the lubricating oil samples of various pollution levels at different temperatures, and use the least squares method third-order polynomial to establish the relationship between temperature and conductivity.

[0014] Furthermore, the step S2 is specifically as follows:

[0015] S21. Assume that the relationship between the conductivity and temperature of the uncontaminated lubricating oil is G(X), and the third-order relationship between the conductivity and temperature of pollution level 1, pollution level 2 and pollution level N is F1(X), F2(X)...F N (X), according to the oil characteristics, the third-order polynomial relationship is a composite polynomial formed by superposition of pure oil and contaminants;

[0016] S22. Subtract the temperature and conductivity relationship G(X) of new oil (grade 0) from the third-order polynomial F(X) of the contaminated lubricating oil curve, that is, F(X)-G(X)=A(X). At this time, the third-order curves A1(X), A2(X)...A of different single-contaminated lubricating oils will be obtained. N (X);

[0017] S23. According to the experimental tests of different pollution levels in steps S12, S21 and S22, a database of the relationship between conductivity and temperature under different single pollution levels is established and used as a training set.

[0018] Furthermore, the step S3 is specifically as follows:

[0019] S31. When the sensor tests the value F(t1) of the lubricating oil at a certain temperature t1, the contamination value A(t1) at a certain temperature t1 can be obtained by subtracting the pure oil value G(t1) at the temperature from F(t1), that is, F(t1)-G(t1)=A(t1), which is recorded as the coordinate (t1, A(t1));

[0020] S32, Substitute t1 into A1(X), A2(X)...A N (X) The third-order polynomial is used to calculate and obtain the conductivity values ​​of the single pollution degree at this temperature A1(t1), A2(t1)...A N(t1), and the coordinates are recorded as (t1, A1(t1)), (t1, A2(t1))...(t1, A N (t1));

[0021] S33, using the minimum distance discrimination method, using the Euclidean distance as a classifier, respectively calculating the coordinates (t1, A(t1)) to the coordinates (t1, A1(t1)), (t1, A2(t1)) ... (t1, A N (t1)); the Euclidean distance between any two points a(x1,y1) and b(x2,y2) is calculated as follows:

[0022]

[0023] Taking the coordinates (t1, A(t1)) as the point to be measured, the calculated distances are:

[0024] d t1A1(t1) d t1A2(t1) ……d t1AN(t1)

[0025] S34, select the minimum distance value d t1AN(t1)min , that is, to select this equation as the third-order curve A(X) of single-contaminated lubricating oil;

[0026] S35. According to the contamination curve A(X) obtained in, convert the value at temperature t1 to the value A(25℃) at 25°, and finally add the value G(25℃) of the new lubricating oil at room temperature to obtain the value F(25℃) of the pure oil at 25℃ and the contaminated oil at temperature t1, that is, A(25℃)+G(25℃)=F(25℃).

[0027] One of the above technical solutions includes the following beneficial effects: Since conductivity is greatly affected by temperature, temperature compensation is inevitable in the process of using lubricating oil conductivity indicators to monitor lubricating oil quality. The temperature compensation method in the present invention can quickly realize the temperature compensation of the conductivity indicator of lubricating oil under any temperature and any oil condition, so as to achieve the purpose of quickly identifying the degree of lubricating oil contamination. The method is applicable to all kinds of lubricating oils, and has no requirements or restrictions on the characteristics and state of the lubricating oil itself. Compared with other methods, the present invention is based on the lubricating oil database system, which can more truly reflect the state scenario of the oil in the on-site working condition. At the same time, the method of unsupervised minimum distance discrimination is applied. The present invention can be automatically realized without manual operation, which is easy to operate. Compared with other methods, the present invention can realize rapid detection of lubricating oil conductivity, rapid detection of oil contamination, fast detection speed, high efficiency, can improve the oil diagnosis efficiency of equipment, effectively ensure the safety of equipment, and reduce the operating costs of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic diagram of a method flow of an embodiment of the present invention;

[0029] Figure 2 is a schematic diagram of establishing a database of the relationship between conductivity and temperature under different single pollution levels according to an embodiment of the present invention;

[0030] Figure 3 is a schematic diagram of determining oil quality in a database based on a minimum distance discrimination method according to an embodiment of the present invention;

[0031] Figure 4 It is a schematic diagram of experimental sampling data of an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0033] like Figure 1 As shown, the lubricating oil conductivity temperature compensation method based on the minimum distance discrimination method includes the following steps:

[0034] S1. Collect and test lubricating oils with different contamination levels, and establish the relationship between lubricating oil temperature and conductivity;

[0035] S2. Taking the collected and tested lubricating oil as the object, establish the relationship between conductivity and different temperatures, and establish a database system;

[0036] S3. Determine the contamination level of lubricating oil at different temperatures based on the minimum distance discrimination method.

[0037] Since conductivity is greatly affected by temperature, temperature compensation is inevitable in the process of using lubricating oil conductivity indicators to monitor lubricating oil quality. The temperature compensation method in the present invention can quickly realize temperature compensation of the conductivity indicator of lubricating oil under any temperature and any oil condition, so as to achieve the purpose of quickly identifying the degree of lubricating oil contamination. This method is applicable to all kinds of lubricating oils, and has no requirements or restrictions on the characteristics and state of the lubricating oil itself. Compared with other methods, the present invention is based on a lubricating oil database system, which can more truly reflect the state scenario of the oil in the on-site working conditions. At the same time, the unsupervised minimum distance discrimination method is applied. The present invention can be automatically realized without manual operation, which is easy to operate. Compared with other methods, the present invention can realize rapid detection of lubricating oil conductivity and oil contamination degree, with fast detection speed and high efficiency, which can improve the oil diagnosis efficiency of the equipment, effectively ensure the safety of the equipment, and reduce the operating costs of the enterprise.

[0038] Wherein, the step S1 is specifically as follows:

[0039] S11. Determine a representative type of lubricant, obtain lubricant samples of this type of lubricant under different degrees of contamination, and classify the lubricant samples with different degrees of contamination;

[0040] S12. Perform a temperature test on the lubricating oil samples, collect the conductivity values ​​of the lubricating oil samples of various pollution levels at different temperatures, and use the least squares method third-order polynomial to establish the relationship between temperature and conductivity.

[0041] The key to this step is to collect lubricating oil samples with different pollution levels. Through this step, a sample library with different pollution levels can be established. At the same time, the conductivity of the lubricating oil at different temperatures is detected by the heating method, and a functional relationship is established, thereby enriching the basic data of the sample library.

[0042] Wherein, the step S2 is specifically as follows:

[0043] S21. Assume that the relationship between the conductivity and temperature of the uncontaminated lubricating oil is G(X), and the third-order relationship between the conductivity and temperature of pollution level 1, pollution level 2 and pollution level N is F1(X), F2(X)...F N (X), according to the oil characteristics, the third-order polynomial relationship is a composite polynomial formed by superposition of pure oil and contaminants;

[0044] S22. Subtract the temperature and conductivity relationship G(X) of new oil (grade 0) from the third-order polynomial F(X) of the contaminated lubricating oil curve, that is, F(X)-G(X)=A(X). At this time, the third-order curves A1(X), A2(X)...A of different single-contaminated lubricating oils will be obtained. N (X);

[0045] S23, according to the experimental tests of different pollution levels in steps S12, S21 and S22, a database of the relationship between conductivity and temperature under different single pollution levels is established and used as a training set. Figure 2 shown.

[0046] This step can derive the numerical relationship between the single contamination degree and the temperature based on the basic database. Through this relationship, a database of the single contamination degree of lubricating oil can be established to provide training data and a data basis for minimum distance determination. The method has high operational feasibility.

[0047] Wherein, the step S3 is specifically as follows:

[0048] S31. When the sensor tests the value F(t1) of the lubricating oil at a certain temperature t1, the contamination value A(t1) at a certain temperature t1 can be obtained by subtracting the pure oil value G(t1) at the temperature from F(t1), that is, F(t1)-G(t1)=A(t1), which is recorded as the coordinate (t1, A(t1));

[0049] S32, Substitute t1 into A1(X), A2(X)...A N (X) The third-order polynomial is used to calculate and obtain the conductivity values ​​of the single pollution degree at this temperature A1(t1), A2(t1)...A N (t1), and the coordinates are recorded as (t1, A1(t1)), (t1, A2(t1))...(t1, A N (t1));

[0050] S33, using the minimum distance discrimination method, using the Euclidean distance as a classifier, respectively calculating the coordinates (t1, A(t1)) to the coordinates (t1, A1(t1)), (t1, A2(t1)) ... (t1, A N (t1)); the Euclidean distance between any two points a(x1,y1) and b(x2,y2) is calculated as follows:

[0051]

[0052] Taking the coordinates (t1, A(t1)) as the point to be measured, the calculated distances are:

[0053] d t1A1(t1) ,d t1A2(t1) ……d t1AN(t1) ,

[0054] S34, select the minimum distance value d t1AN(t1)min , that is, to select this equation as the third-order curve A(X) of single-contaminated lubricating oil;

[0055] S35. According to the contamination curve A(X) obtained in, convert the value at temperature t1 to the value A(25℃) at 25°, and finally add the value G(25℃) of the new lubricating oil at room temperature to obtain the value F(25℃) of the pure oil at 25℃ and the contaminated oil at temperature t1, that is, A(25℃)+G(25℃)=F(25℃).

[0056] The above realizes the conversion of the conductivity value of oil with any pollution level at any temperature into the conductivity at room temperature of 25℃. Figure 3 shown.

[0057] The minimum distance method in this step can achieve the regression compensation value of the conductivity index of the lubricating oil at different temperatures at room temperature (25°C). This value truly reflects the actual contamination status of the oil and realizes real-time monitoring of the oil contamination status. The minimum distance method has a simple algorithm implementation and can achieve a good compensation effect.

[0058] Applying this temperature compensation method, the oil with a conductivity value of 370pS / m was tested at elevated temperature. The results are as follows: Figure 4 As shown. The results show that the conductivity value of the contaminated oil gradually increases as the temperature increases. After applying the fuzzy array-based temperature compensation method, the conductivity value of the contaminated oil is still about 372pS / m when the temperature rises to about 48°C. Since the contamination value of the oil is actually 460pS / m, it can be seen that the temperature compensation method can be regressed to the properties of the oil itself, proving the correctness and accuracy of the test.

[0059] The technical principle of the present invention is described above in conjunction with specific embodiments. These descriptions are only for explaining the principle of the present invention and cannot be interpreted as limiting the scope of protection of the present invention in any way. Based on the explanations herein, those skilled in the art can associate other specific implementations of the present invention without paying creative labor, and these methods will fall within the scope of protection of the present invention.

Claims

1. A lubricating oil conductivity temperature compensation method based on a minimum distance discrimination method, characterized in that: The following steps are included: S1. Collect and test lubricating oils with different contamination levels, and establish the relationship between lubricating oil temperature and conductivity; S2. Taking the collected and tested lubricating oil as the object, establish the relationship between conductivity and different temperatures, and establish a database system; S3. Determine the contamination level of lubricating oil at different temperatures based on the minimum distance discrimination method.

2. The lubricating oil conductivity temperature compensation method based on the minimum distance judgment method according to claim 1 is characterized in that: The step S1 is specifically as follows: S11. Determine a representative type of lubricant, obtain lubricant samples of this type of lubricant under different degrees of contamination, and classify the lubricant samples with different degrees of contamination; S12. Perform a temperature test on the lubricating oil samples, collect the conductivity values ​​of the lubricating oil samples of various pollution levels at different temperatures, and use the least squares method third-order polynomial to establish the relationship between temperature and conductivity.

3. The lubricating oil conductivity temperature compensation method based on the minimum distance judgment method according to claim 2 is characterized in that: The step S2 is specifically as follows: S21. Assume that the relationship between the conductivity and temperature of the uncontaminated lubricating oil is G(X), and the third-order relationship between the conductivity and temperature of pollution level 1, pollution level 2 and pollution level N is F1(X), F2(X)...F N (X), according to the oil characteristics, the third-order polynomial relationship is a composite polynomial formed by superposition of pure oil and contaminants; S22. Subtract the temperature and conductivity relationship G(X) of new oil (grade 0) from the third-order polynomial F(X) of the contaminated lubricating oil curve, that is, F(X)-G(X)=A(X). At this time, the third-order curves A1(X), A2(X)...A of different single-contaminated lubricating oils will be obtained. N (X); S23. According to the experimental tests of different pollution levels in steps S12, S21 and S22, a database of the relationship between conductivity and temperature under different single pollution levels is established and used as a training set.

4. The lubricating oil conductivity temperature compensation method based on the minimum distance judgment method according to claim 3 is characterized in that: The step S3 is specifically as follows: S31. When the sensor tests the value F(t1) of the lubricating oil at a certain temperature t1, the contamination value A(t1) at a certain temperature t1 can be obtained by subtracting the pure oil value G(t1) at the temperature from F(t1), that is, F(t1)-G(t1)=A(t1), which is recorded as the coordinate (t1, A(t1)); S32, Substitute t1 into A1(X), A2(X)...A N (X) The third-order polynomial is used to calculate and obtain the conductivity values ​​of the single pollution degree at this temperature A1(t1), A2(t1)...A N (t1), and the coordinates are recorded as (t1, A1(t1)), (t1, A2(t1))...(t1, A N (t1)); S33, using the minimum distance discrimination method, using the Euclidean distance as a classifier, respectively calculating the coordinates (t1, A(t1)) to the coordinates (t1, A1(t1)), (t1, A2(t1)) ... (t1, A N (t1)); the Euclidean distance between any two points a(x1,y1) and b(x2,y2) is calculated as follows: Taking the coordinates (t1, A(t1)) as the point to be measured, the calculated distances are: d t1A1(t1) 、d t1A2(t1) ……d t1AN(t1) S34, select the minimum distance value d t1AN(t1)min , that is, to select this equation as the third-order curve A(X) of single-contaminated lubricating oil; S35. According to the contamination curve A(X) obtained in, convert the value at temperature t1 to the value A(25℃) at 25°, and finally add the value G(25℃) of the new lubricating oil at room temperature to obtain the value F(25℃) of the pure oil at 25℃ and the contaminated oil at temperature t1, that is, A(25℃)+G(25℃)=F(25℃).

Images