Quick identification method of engine lubricating oil types
An identification method and lubricating oil technology, applied in special data processing applications, instruments, electrical digital data processing, etc., to achieve the effect of avoiding losses
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0044] Example 1: Evaluation of identification variable identification ability
[0045] 1) Collect new oil samples
[0046] Collected 83 internal combustion engine oils with clear type identification, 40 diesel engine oils, 12 gasoline engine oils, and 31 general-purpose internal combustion engine oils. Its manufacturers include Shell, ESSO, Mobil, MOBIL, Great Wall and Kunlun, etc.
[0047] 2) Determination of quality indicators
[0048] Determination of saturated hydrocarbons, aromatics, colloids, total base number, total acid number, pour point, flash point, viscosity at 100°C, viscosity at 40°C, viscosity index, C content, H content, C / H ratio of engine oil using standard methods , S content, N content, Ca content, Mg content, Zn content, P content and other 19 indicators. Table 1 lists the units and standard methods for each quality parameter. The measurement results of various quality indicators of various lubricating oils are shown in Table 2 (due to the huge data, on...
example 2
[0061] Example 2: Determining the number of recognition features and establishing a recognition model
[0062] In the process of pattern recognition, the larger the number of samples / features, the better the robustness of the model, so it is required to reduce the number of features as much as possible without reducing the recognition performance.
[0063] According to the evaluation results of the recognition ability of Example 1 ( figure 1 ), select the top m features with the strongest recognition ability in turn, use the BAYES discriminant method to build a model, and then identify the samples in the training set for inspection, and draw the relationship between the correct recognition rate and the number of recognized features. The results are shown in figure 2 . It can be seen from the figure that when m=9, the recognition rate is the highest, so 9 parameters such as saturated hydrocarbon, aromatic hydrocarbon, total base number, Zn, P, pour point, flash point, viscosi...
example 3
[0067] Example 3 Identification of Unknown Diesel Engine Oil Samples
[0068] Select 1 diesel engine oil as target identification lubricating oil, adopt the method of the present invention to carry out identification verification, identification steps are as follows:
[0069] (1) Determination of its physical and chemical indicators, the results are shown in Table 5 (in actual operation, only 9 indicators such as saturated hydrocarbons, aromatic hydrocarbons, total base number, Zn, P, pour point, flash point, viscosity index and 40 °C viscosity index were measured. on the line).
[0070] table 5
[0071] Viscosity at 40°C
/ mm 2 / s
Viscosity at 100°C
/ mm 2 / s
viscosity
index
saturated
Hydrocarbons / %
Aromatics
/ %
colloid
/ %
total base number
/ mgKOH /
g
Flash point
/ °C
pour point
/ ℃
total acid value
/ mgKOH /
g
138.7
13.99 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 