A method and system for classifying and assessing the contamination level of lubricating oil, and a storage medium.

Abstract

This invention discloses a method and system for classifying and assessing lubricating oil contamination levels, as well as a storage medium. The method includes the following steps: acquiring lubricating oil samples from multiple operating machines; preprocessing the lubricating oil samples to obtain samples to be tested; extracting metal particles and colloids from the samples to construct a contamination feature dataset; analyzing the viscous substance content in the contamination feature dataset to obtain the comprehensive correlation between the flow rate, velocity, and pressure of the lubricating oil sample, as well as the clogging risk threshold value of the viscous substance content; calculating the clogging risk probability value for each operating machine using the comprehensive correlation and the clogging risk threshold value; and analyzing the contamination source classification results of metal particle clogging in the operating machines using the clogging risk probability value. By classifying the contamination sources of metal particles, more targeted lubricating oil detection can be performed on the machines, identifying lubricating oil anomalies.

Description

Technical Field

[0001] This invention relates to the field of lubricating oil residue testing and analysis, and in particular to a method and system for classifying and assessing the contamination level of lubricating oil, as well as a storage medium. Background Technology

[0002] With the increasing complexity and precision of machinery and industrial facilities, equipment reliability and operational efficiency have become crucial factors in the production process. Lubricating oil, as an indispensable component in the operation of machinery, directly affects the equipment's working condition, service life, and maintenance costs due to its quality and level of contamination. Especially under prolonged operation or high-load conditions, contaminants in the lubricating oil gradually increase. These contaminants not only affect the performance of the lubricating oil but may also cause equipment malfunctions or even serious mechanical damage.

[0003] Lubricating oil contaminants are diverse, primarily including metal particles and colloids. Metal particles typically originate from internal friction, wear, and corrosion processes within equipment, and are one of the main sources of contaminant damage and lubricating oil deterioration. Colloids mainly affect the viscosity and flowability of lubricating oil. Excessively high viscosity leads to poor lubricating oil flow, increasing internal resistance and causing problems such as system blockage, increased temperature, and component wear. Especially for high-precision equipment and high-speed machinery, the accumulation of contaminants in lubricating oil often exacerbates the risk of equipment failure, leading to increased maintenance frequency and decreased production efficiency.

[0004] Currently, the detection and assessment of lubricating oil contamination mainly rely on traditional laboratory analytical methods, such as spectral analysis, mass spectrometry, and microscopic observation. While these methods can effectively detect contaminants in lubricating oil, they suffer from drawbacks such as cumbersome sampling, long analysis cycles, and high equipment costs, and they cannot monitor the contamination status of lubricating oil in real time. Therefore, based on existing detection technologies, how to accurately assess the contamination level of lubricating oil in real time and predict the risk of equipment blockage through data analysis has become a pressing problem to be solved in the fields of lubricating oil management and equipment maintenance.

[0005] To address these challenges, recent years have seen numerous studies dedicated to developing novel methods for detecting lubricating oil contamination. These methods combine advanced data analysis techniques with physicochemical analysis to provide more accurate contamination assessments and risk predictions. They enable rapid pretreatment of lubricating oil samples, precise extraction of contaminant components, and comprehensive analysis of the impact of different contaminants on equipment performance, providing a reliable basis for monitoring equipment operating conditions. Furthermore, by constructing contamination feature datasets and integrating machine learning and artificial intelligence algorithms, real-time monitoring and early warning of equipment operating status can be achieved, reducing downtime and maintenance costs caused by equipment failures. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for classifying and assessing the contamination level of lubricating oil, as well as a storage medium, which solves the aforementioned technical problems pointed out in the prior art.

[0007] This invention provides a method for classifying and assessing the contamination level of lubricating oil, comprising the following steps:

[0008] Lubricating oil samples were obtained from multiple operating machines, and the lubricating oil samples were preprocessed to obtain samples to be tested.

[0009] Metal particles and colloids are extracted from the sample to be tested to construct a pollution feature dataset; the content of viscous substances in the pollution feature dataset is analyzed to obtain the comprehensive correlation between the flow rate and pressure of the lubricating oil sample and the clogging risk threshold value of the viscous substance content; the clogging risk probability value of each machine operating equipment is calculated using the comprehensive correlation and the clogging risk threshold value; the pollution source classification results of metal particle clogging in the machine operating equipment are analyzed using the clogging risk probability value.

[0010] Accordingly, the present invention also proposes a lubricating oil contamination level classification assessment and processing system, comprising: a data acquisition module; and an identification module;

[0011] The acquisition module is used to acquire lubricating oil samples from multiple machine operating devices, and to preprocess the lubricating oil samples to obtain samples to be tested.

[0012] The identification module is used to extract metal particles and colloids from the sample to be tested to construct a pollution feature dataset; analyze the viscous substance content of the pollution feature dataset to obtain the comprehensive correlation between the flow rate and pressure of the lubricating oil sample and the clogging risk threshold value of the viscous substance content; use the comprehensive correlation and clogging risk threshold value to calculate the clogging risk probability value of each machine operating equipment; and use the clogging risk probability value to analyze the pollution source classification results of metal particle clogging in the machine operating equipment.

[0013] Compared with the prior art, the embodiments of the present invention have at least the following technical advantages:

[0014] Analysis of the lubricating oil contamination level classification assessment and treatment method and system and storage medium provided by the present invention shows that, in specific applications, by comprehensively analyzing multiple key parameters such as metal particles, gum content, flow rate change rate and pressure difference in the lubricating oil, the contamination characteristics of the lubricating oil and the risk of equipment blockage can be accurately assessed. The solution uses a laser particle size analyzer to measure the particle size distribution and quantity of metal particles, and combines this with infrared spectroscopy to obtain the gum content, effectively quantifying the degree of lubricating oil contamination. Furthermore, by calculating particle dispersion, viscous substance adsorption amount, and total area of ​​particle splicing domains, the solution clearly demonstrates the relationship between metal particles and gum, and their impact on oil flowability and equipment performance.

[0015] Furthermore, the solution incorporates calculations of flow rate change rate and pressure difference change rate, utilizing the Pearson correlation coefficient method to assess the intrinsic relationship between viscous substance content and oil fluidity. This not only reveals the relationship between oil contamination and equipment condition but also provides a quantitative assessment of blockage risk. By combining historical blockage incident records with real-time monitoring of oil viscous substance content, the solution sets a critical value for blockage risk, enabling real-time prediction and prevention of equipment failures, thereby reducing maintenance costs and downtime. The comprehensive assessment of blockage risk probability helps identify which equipment has a higher risk of blockage, and adjusting operating parameters based on the risk value effectively avoids equipment blockage and premature wear. Attached Figure Description

[0016] Figure 1 This is a flowchart of the main process of a lubricating oil contamination level classification assessment and treatment method in Example 1;

[0017] Figure 2 This is a flowchart of a lubricating oil contamination level classification assessment and treatment method according to Example 1;

[0018] Figure 3 This is a flowchart illustrating a lubricating oil contamination level classification assessment and treatment method according to a blockage risk threshold, as described in Example 1.

[0019] Figure 4 This is a schematic diagram of the spliced ​​particle range of a lubricating oil contamination level classification assessment and treatment method in Example 1;

[0020] Figure 5 This is a flowchart illustrating a lubricating oil contamination level classification assessment and treatment method according to a separation efficiency assessment value, as described in Example 1.

[0021] Figure 6 This is a schematic diagram of the smoothed trend curve of a lubricating oil contamination level classification assessment and treatment method in Example 1;

[0022] Figure 7This is a flowchart illustrating the identification of metal types in a lubricating oil contamination level classification and assessment treatment method according to Example 1.

[0023] Figure 8 This is a flowchart of a lubricating oil contamination level classification assessment and treatment system according to Example 2;

[0024] Figure 9 This is a schematic diagram of a storage medium for applying the above-mentioned method for classifying and assessing the contamination level of lubricating oil.

[0025] Labels: Acquisition module 10; Identification module 20; Memory 1130; Communication interface 1120; Processor 1110; Computer storage medium 1140. Detailed Implementation

[0026] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings.

[0028] Example 1

[0029] like Figure 1 , 2 As shown in the figure, this embodiment of the invention provides a method for classifying and assessing the contamination level of lubricating oil, including the following steps:

[0030] S1: Obtain lubricating oil samples from multiple machine operating devices, pre-process the lubricating oil samples to obtain the sample to be tested (i.e., the lubricating oil sample is pre-treated by concentration or dispersion to make the particles that may exist in the sample evenly distributed to prevent clogging of the instrument measurement channel).

[0031] It should be noted that particles in lubricating oil samples may be unevenly distributed due to their physical properties (such as size and density). Pretreatment, through concentration or dispersion, helps to disperse these particles, ensuring that they do not concentrate in a particular area and affect measurement accuracy during analysis. In subsequent detection, larger particles in the sample may clog the instrument's measurement channels, affecting the accuracy of the results. Pretreatment, especially particle dispersion, effectively avoids this problem, ensuring the instrument can accurately read the sample's characteristic data. The pretreatment step is crucial for the smooth progress of subsequent analysis; it ensures the consistency and operability of the lubricating oil sample, avoids the impact of large particulate contaminants on the detection instrument, guarantees sample homogeneity and repeatability, and provides a foundation for accurate analysis of contaminant components.

[0032] S2: Extract metal particles and colloids from the sample to be tested to construct a pollution feature dataset; analyze the viscous substance content of the pollution feature dataset to obtain the comprehensive correlation between the flow rate and pressure of the lubricating oil sample and the clogging risk threshold value of the viscous substance content; use the comprehensive correlation and clogging risk threshold value to calculate the clogging risk probability value of each machine operating equipment; use the clogging risk probability value to analyze the pollution source classification results of metal particle clogging in the machine operating equipment.

[0033] It should be noted that lubricating oil may contain metal particles (such as iron, chromium, etc.), colloids, and other contaminants. By extracting these components, a contamination feature dataset can be constructed. This dataset contains the concentration, type, and other characteristics of all contaminants in the lubricating oil, helping the embodiments of this invention to understand the compositional characteristics of the contaminants. Among the aforementioned components, viscous substances (i.e., viscous substances include colloids and a small amount of asphaltenes, etc.; in this application embodiment, viscous substances specifically refer to colloids) are key contaminants in lubricating oil, affecting its fluidity, flow rate, and pressure. Analyzing the relationship between the content of viscous substances and the flow rate, velocity, and pressure of the equipment is used to illustrate the flow of lubricating oil within the equipment.

[0034] Therefore, calculating the comprehensive correlation can help predict changes in flowability caused by contaminants. Based on the content of viscous substances and their impact on equipment flowability, a "clogging risk threshold" is calculated. This represents a threshold value; when the content of viscous substances exceeds this threshold, it may obstruct lubricant flow, increasing the risk of equipment clogging. Using the comprehensive correlation and the clogging risk threshold, the clogging risk probability value for each machine is calculated. This probability value, derived from a mathematical model that quantifies the equipment's operating state and contaminant concentration, represents the likelihood of clogging under current operating conditions. By calculating the clogging risk probability value, the types of contamination sources in the equipment can be further analyzed, particularly contamination caused by metal particles. These metal particles are often generated by internal friction and wear. Identifying the contamination source helps pinpoint the source of the fault, allowing for timely repairs or lubricant replacement to prevent equipment damage.

[0035] Specifically, such as Figure 3 As shown, in step S2, metal particles and colloids are extracted from the sample to be tested to construct a pollution feature dataset; the content of viscous substances in the pollution feature dataset is analyzed to obtain the comprehensive correlation between the flow rate and pressure of the lubricating oil sample and the critical value of the clogging risk of the viscous substance content; the comprehensive correlation and the critical value of the clogging risk are used to calculate the clogging risk probability value of each machine operating equipment; the clogging risk probability value is used to analyze the pollution source classification results of metal particle clogging in the machine operating equipment. The specific operation steps are as follows:

[0036] S21: The sample to be tested is tested by a laser particle size analyzer to identify the particle size distribution and number of metal particles, and the particle dispersion is calculated.

[0037] The sample to be tested is scanned using an infrared spectroscopy device with pre-set characteristic bands for the gel, and the absorption spectral data of each band (i.e., the characteristic bands of the gel) in the sample to be tested is obtained (i.e., the values ​​of the gel in each band); the absorption spectral data is then converted into the values ​​of the gel.

[0038] It should be noted that in the above steps, the laser particle size analyzer detects the particle size distribution and quantity of metal particles, identifies and classifies the characteristics of metal particles in the lubricating oil. The size and quantity of metal particles directly affect the lubrication performance of the lubricating oil and the wear of the equipment. The particle dispersion is calculated by the particle size distribution and quantity. Particle dispersion refers to the number of the most representative (i.e., the majority of the particle size) metal particles in each grid within the scanning area of ​​the sample to be tested.

[0039] For example, the scanning area of ​​the current sample to be tested is divided into a 128x128 grid. Within each grid, metal particles of different sizes can be detected using a laser particle size analyzer. Simultaneously, the particle size range (the range of the majority of metal particles in the current grid) is determined and recorded as the particle dispersion of that grid. For instance, a particle dispersion of 100 in a unit grid indicates a grid range of large metal particles, while a particle dispersion of 60 indicates a grid range of medium-sized metal particles. Particle dispersion can identify the wear caused by different types of metal particles on various parts of machinery and equipment. This helps determine the degree of lubricant contamination and its wear risk to the equipment. Particle dispersion also reflects the dispersion of various types of metal particles. The aforementioned gum is a viscous substance in lubricating oil that can affect the fluidity, lubrication effect, and clogging risk of the oil. This step, by identifying specific wavelength absorption spectral data, can quantify the gum content in the oil, accurately measure the amount of gum, and assess the fluidity and potential clogging risk of the oil.

[0040] The above analysis shows that temperature and pressure are key factors in the performance of lubricating oil. Changes in these parameters directly affect the fluidity of the oil and the operating status of the equipment. More importantly, they are used to detect the characteristic performance of the lubricating oil under corresponding temperature and pressure. By using machine operating environment data, we can help establish the correlation between contamination characteristics and equipment status.

[0041] S22: The metal particles in the sample to be tested are uniformly divided into particle intervals. Adjacent grids belonging to the same particle dispersion range are merged to form particle intervals. The total area of ​​the particle splicing domain is calculated for each particle interval (i.e., the total area of ​​the particle splicing domain is calculated for each particle interval (i.e., the splicing of adjacent grids). For example, the current grid is searched in an 8-neighborhood, and then grids belonging to the same large metal particle range are spliced ​​and merged to form the spliced ​​particle intervals. Figure 4 As shown;

[0042] The percentage of viscous material adsorbed in each particle interval is calculated based on the total area of ​​the particle splicing domain and the value of the adhesive material. This percentage is expressed as the ratio of the mass of viscous material adsorbed in that interval to the total mass of the adhesive material, which is the proportion of viscous material and adhesive material adsorbed on the metal particles. The viscous material content is then extracted based on this percentage, and a viscous material content distribution map is constructed. (The extracted viscous material content can be calculated by multiplying the adhesive material value by the percentage of viscous material adsorbed in each particle interval; the viscous material content distribution map includes this percentage.)

[0043] The pollution feature dataset is constructed by combining the values ​​of the colloid, the total area of ​​the particle splicing domain in each particle interval, and the distribution map of the viscous substance content.

[0044] It should be noted that the above-mentioned division of metal particle intervals and calculation of the total area of ​​particle splicing domains are used to help quantify the degree of particle contamination on lubricating oil. The total area of ​​particle splicing domains is closely related to the amount of viscous substances adsorbed in the oil. The larger the total area of ​​particle splicing domains, the more viscous substances are adsorbed, indicating that the viscous substances are also more viscous, and the higher the potential risk of clogging (in this case, if the entire scanning area has a large number of particle intervals belonging to the same grid range of large metal particles, and the total area of ​​particle splicing domains is very large). The above steps assess the impact of particles on oil flowability and lubricity by analyzing the amount of viscous substances adsorbed in different particle intervals. Higher adsorption amounts mean higher clogging risk, and it is possible to determine which particle intervals affect the oil flowability and lubricity. Flowability and equipment performance have the greatest impact, thus helping to predict the risk of equipment blockage. Meanwhile, if the number of particle intervals belonging to the same grid range of large metal particles is large, but the total area of ​​the particle splicing domain is not large, it indicates that the viscosity of the gum produced after the current lubricating oil load is relatively low, and the affected area is small. Conversely, if the number of particle intervals belonging to the same grid range of large metal particles is large, but the total area of ​​the particle splicing domain is large, it indicates that the gum produced after the current lubricating oil load is dispersed, so its viscosity is relatively low. However, the large total area of ​​the particle splicing domain indicates that a large amount of low-viscosity gum has been generated, which also affects the quality of lubricating oil use.

[0045] The above steps integrate all key features (such as metal particles, colloid content, etc., where temperature and pressure sensors are used to collect continuous time-period operating parameters of the sample to be tested (i.e., operating parameters include operating temperature and pressure parameters, that is, the temperature and pressure generated when the sample is running in the machine)) into a dataset for subsequent analysis and calculation. By integrating different data sources, a comprehensive contamination feature dataset is established, which helps to more accurately assess oil quality and equipment operating status.

[0046] This indicates that lubricating oil produces both low-viscosity and high-viscosity gums after prolonged operation. Therefore, simply analyzing the area and quantity of particles within a particle range is insufficient to accurately reflect the viscosity of the gums. It is also necessary to analyze the flow rate change rate of the sample to help understand the properties of the generated gums. Specifically, execute S23: obtain the flow rate change rate and pressure difference change rate of the sample to be tested for each particle range (i.e., the flow rate change rate is calculated by comparing the current lubricating oil flow rate of the sample to be tested with the reference flow rate in the machine operating equipment; simultaneously, the pressure difference change rate is calculated by comparing the current pressure difference between the inlet and outlet of the machine operating equipment with the reference pressure difference).

[0047] Calculate the rate of change of average flow rate and the rate of change of average pressure difference for all particle ranges;

[0048] The first Pearson correlation coefficient is calculated using the Pearson correlation coefficient method to calculate the change rate of the viscous substance content with the average flow rate; the second Pearson correlation coefficient is calculated using the Pearson correlation coefficient method to calculate the change rate of the viscous substance content with the average pressure difference.

[0049] The average value of the first Pearson correlation coefficient and the second Pearson correlation coefficient is used as the comprehensive correlation degree.

[0050] It should be noted that the flow rate change rate and pressure difference change rate mentioned above reflect the fluidity of the lubricating oil and the load conditions of the machine operating equipment, which can provide a practical basis for calculating the blockage risk. These two parameters can help quantify the oil flow under different operating conditions of the machine operating equipment, further illustrate the impact of fluidity changes on blockage risk, and accurately assess the viscosity properties of gum substances. The above steps use Pearson correlation coefficients to assess the correlation between the content of viscous substances and the flow rate change rate and pressure difference change rate, which helps to illustrate the intrinsic relationship between oil contamination characteristics and equipment operating conditions. The average value of the first Pearson correlation coefficient and the second Pearson correlation coefficient is used as the comprehensive correlation degree to assess the comprehensive impact between oil contamination characteristics and equipment blockage risk, comprehensively assess the relationship between different factors, and improve the accuracy and reliability of prediction.

[0051] S24: Obtain the content value of viscous substances (i.e., gum) in the lubricating oil sample corresponding to the blockage incident in the historical record, sort the viscous substance content values ​​in the historical record in descending order, and calculate the first quartile as the critical value for blockage risk;

[0052] It should be noted that the above steps assess the content of viscous substances in the oil when blockages occurred in the past by reviewing historical records. This establishes a critical value (i.e., the maximum value of the viscous substance content; therefore, the first quartile is calculated using the quartile method based on the maximum viscous substance content value, which best reflects the boundary when the historical viscous substance content was at its highest, indicating the possibility of blockage). This critical value serves as an early warning indicator for blockages. It helps to determine the boundary between normal and abnormal operations and provides a reference standard for real-time monitoring.

[0053] S25: Collect the content value of viscous substances in the lubricating oil in real time, adjust the actual fluctuation range of the machine operating equipment, and calculate the blockage risk probability value of each machine operating equipment by using the actual fluctuation range, the blockage risk threshold value, and the comprehensive correlation. Calculate the separation efficiency evaluation value of the blocked machine operating equipment based on the blockage risk probability value of each machine operating equipment. Analyze the metal particle contamination source classification results of the lubricating oil sample using the separation efficiency evaluation value.

[0054] It should be noted that the above process combines real-time and historical data to assess the clogging risk of each machine and adjust the operating parameters of the equipment in real time to avoid clogging. Through real-time monitoring and risk assessment, equipment failures can be accurately predicted and prevented in advance, reducing maintenance costs and downtime. The above steps, through clogging risk assessment, further analyze the metal particle contamination sources of lubricating oil samples, helping to find the root cause of the contamination and optimize the machine's maintenance and cleaning plan. This helps to control oil contamination at the source, reduce equipment wear, and extend the service life of the equipment.

[0055] Specifically, such as Figure 5 As shown, in step S25, the content value of viscous substances in the lubricating oil in real time is collected to adjust the actual fluctuation range of the machine operating equipment. The actual fluctuation range is then used to calculate the blockage risk probability value for each machine operating device based on the blockage risk probability value of each machine operating device. The separation efficiency evaluation value of the blocked machine operating device is then calculated based on the blockage risk probability value of each machine operating device. Finally, the separation efficiency evaluation value is used to analyze the metal particle contamination source classification results of the lubricating oil sample. The specific operation steps are as follows:

[0056] S251: Collect the content value of viscous substances in the lubricating oil in real time; determine whether the content value of viscous substances in the lubricating oil in real time is greater than the critical value for blockage risk;

[0057] If so, calculate the excess ratio of the viscous substance content in the real-time lubricating oil (i.e., subtract the blockage risk threshold from the viscous substance content in the real-time lubricating oil and then divide by the blockage risk threshold to obtain the excess ratio).

[0058] A preset piecewise function is used to calculate the temperature increase based on the excess ratio (e.g., if the excess ratio < 0.1, the temperature increase is +2℃; if 0.1 ≤ excess ratio < 0.3, the temperature increase is +4℃; if the excess ratio ≥ 0.3, the temperature increase is +6℃).

[0059] A pressure adjustment coefficient is introduced, and the pressure increment is calculated by using the introduced pressure adjustment coefficient and the excess ratio. This means that by increasing the pressure, the machine operating equipment improves the transmission of oil between pipes or components, ensuring that the lubricating oil can flow to the key parts in a timely manner.

[0060] By using a preset benchmark flow rate to reduce the flow rate change rate, the residence time of the lubricating oil is extended (i.e., reducing the flow rate of the machine operating equipment can extend the residence time of the lubricating oil inside the equipment, improve its lubrication effect, and thus compensate for the adverse effects caused by the decline in quality).

[0061] It should be noted that the above-mentioned method of collecting the content of viscous substances in lubricating oil and determining whether it exceeds a critical value allows for real-time identification of changes in lubricating oil quality. When the viscous substance content exceeds the standard, it usually means that the fluidity of the lubricating oil has weakened, which may lead to blockage or excessive wear of machine parts. The calculation of the excess ratio mentioned above, if the viscous substance content exceeds the critical value, reflects the severity of the impact of contaminants on equipment operation. Adjusting the temperature, pressure, and flow rate according to the excess ratio helps to mitigate the impact of contaminants. For example, increasing the temperature helps to reduce the viscosity of the oil, and reducing the flow rate helps to prolong the contact time between the lubricating oil and the equipment, improving its lubrication effect. Through these measures, the negative impact of contaminants on the equipment can be controlled when there is too much contaminant, reducing the risk of blockage.

[0062] S252: The temperature increase, pressure increase, and flow rate reduction are used as actual adjustment values ​​to adjust the machine operation equipment; the actual fluctuation range is calculated using the machine operation equipment's setpoints and the actual adjustment values; research has found that when the viscous content in the lubricating oil exceeds the standard in real-time monitoring, it usually means that the oil's fluidity has decreased. By adjusting the temperature, pressure, and flow rate, the equipment can maintain a safer and more stable operating range under unfavorable oil conditions (i.e., oil quality). If no adjustment is made, when the viscous content exceeds the standard, the equipment may experience excessive wear due to insufficient lubrication or shutdown due to blockage. By calculating the maximum fluctuation range using the actual adjustment values ​​of the machine operation equipment, the system can monitor changes in equipment parameters in real time. If the actual fluctuation range is too large after adjustment, the subsequent safety margin indicators decrease, thereby calculating the probability value of subsequent blockage risk.

[0063] Record the maximum actual fluctuation range, and calculate the upper limit of the safe fluctuation range using the set value of the machine operating equipment and the maximum actual fluctuation range;

[0064] The safety margin index is obtained by calculating the ratio of the difference between the actual adjustment value and the upper limit of the safety fluctuation range to the upper limit of the safety fluctuation range.

[0065] The probability value of blockage risk (i.e., the safety margin index divided by the blockage risk threshold) is calculated based on the safety margin index and the blockage risk threshold and the comprehensive correlation.

[0066] ;

[0067] In the formula, Norm[.] represents the normalization function, which is used to map the entire risk index to a predetermined range (usually 0 to 1).

[0068] In some parts Together with the internal arcsine function Used to The output value (usually in) (between) is further mapped to a standardized interval;

[0069] This is expressed as the degree of temperature increase. This indicates the preset temperature adjustment amount based on exceeding the critical value; its value is determined by a piecewise function.

[0070] This is expressed as exceeding the proportion, defined as: ;in This represents the current real-time concentration of viscous substances. It represents the critical value for clogging risk; it reflects the degree of deviation of the current content of chemical substances from the critical value and is an indicator for measuring the severity of pollution.

[0071] It is expressed as a pressure adjustment coefficient, which is a pre-set empirical coefficient used to adjust the effect of exceeding the ratio on the pressure increment;

[0072] Expressed as a flow rate adjustment factor, it is the ratio of the baseline flow rate to the adjusted flow rate: This reflects the impact of flow rate adjustments on the risk of blockage;

[0073] It is expressed as the comprehensive correlation degree, which is used to comprehensively consider the interaction between various adjustment measures (temperature, pressure, flow rate) and their overall correlation with the safety of equipment operation;

[0074] This is expressed as a safety margin indicator, measuring the difference between the current operating state and the safe operating state of the equipment. If the actual fluctuation is close to or exceeds the safe range, then... Smaller; conversely, larger margin Larger;

[0075] It should be noted that the above steps, by adjusting the actual operating parameters of the equipment, such as temperature, pressure, and flow rate, prevent the equipment from operating under poor lubricant quality conditions. Simultaneously, a "safety margin" is calculated to ensure safe operation under various operating conditions. The above steps, by calculating the adjusted fluctuation range, ensure the equipment does not operate within excessively high or low parameter ranges, thus preventing excessive wear or blockage. The difference between the actual fluctuation range and the set value is compared with the safe fluctuation range to assess the safety of equipment operation. This ensures the equipment always operates within a safe range, maintaining stability even when the lubricant is heavily contaminated, by adjusting operating parameters. In fact, step S22 evaluates the number of particle intervals and the total area of ​​particle splicing domains in the entire scanning area and grid range. Step S251 further determines the comprehensive correlation by considering the influence of flow rate change rate and pressure difference change rate on high and low viscosity colloids. Step S252 further considers safety margin indicators (equipment factors) and blockage risk thresholds to assess the probability of blockage risk, further evaluating the quality of lubricant usage.

[0076] S253: Sort the blockage risk probability values ​​of each machine's operating equipment in descending order, and select the highest blockage risk probability value to collect vibration frequency (i.e., collect vibration signal data output by the equipment's vibration sensor and record the time-domain waveform of the vibration signal), operating temperature fluctuation amplitude (i.e., the temperature fluctuation amplitude over a continuous time period), and fluid velocity and pressure drop over a continuous time period.

[0077] The vibration frequency is converted into a frequency domain signal using Fourier transform based on the moving average method. The frequency component with the largest amplitude is calculated from the frequency domain signal and used as the dominant vibration frequency component.

[0078] Linear regression was used to calculate the slope of the pressure drop over a continuous time period.

[0079] A sliding window is used to calculate the mean and standard deviation of the operating temperature fluctuation amplitude in each window.

[0080] The average flow rate and standard deviation of the flow rate are calculated for the fluid velocity over the continuous time period; the flow rate fluctuation coefficient is calculated using the average flow rate and standard deviation of the flow rate.

[0081] The moving average method is used to generate a smooth trend curve by combining the dominant vibration frequency component, the slope of pressure drop over time, the standard deviation of temperature fluctuation, and the flow rate fluctuation coefficient. (The moving average method involves setting a moving window for the collected vibration, pressure drop, temperature, and flow rates over a fixed time period, averaging the data within the window, and then sliding the moving window along the time series to continuously generate new averages; resulting in a smooth trend curve that reflects the overall trend of the parameters over time.) Figure 6 (as shown)

[0082] It should be noted that the above-mentioned methods, by monitoring parameters such as vibration frequency, temperature fluctuations, flow rate, and pressure changes of the equipment, establish trend curves for the equipment's operating status. This data can help identify whether there is an impending blockage or other potential fault. By using the Fourier transform of the vibration signal, frequency components can be identified and compared with a reference frequency to determine whether there is abnormal vibration. The moving average method is used to smooth parameter fluctuations and extract trends, which helps to discover potential fault signals. These monitoring indicators and trend analyses help to monitor the health status of the equipment in real time, detect abnormalities in a timely manner, and take preventive measures to reduce sudden failures.

[0083] S254: Calculate the vibration difference (i.e., the degree of deviation) between the main vibration frequency component and the reference operating frequency of the machine operating equipment.

[0084] A preset deviation threshold is established; it is then determined whether the vibration difference exceeds the deviation threshold.

[0085] If so, it is determined that the machine's operating equipment is vibrating abnormally and there is a blockage.

[0086] If not, then identify whether the slope of the pressure drop over time increases (i.e., the degree of deviation) based on the smoothed trend curve.

[0087] If so, it is determined that the machine's operating equipment is experiencing a trend of increasing congestion;

[0088] Record the abnormal duration of the blockage; weight the vibration difference with the slope of the increase in pressure drop over time and the abnormal duration to obtain the separation efficiency evaluation value;

[0089] It should be noted that the above-mentioned monitoring of changes in equipment vibration frequency and the slope of pressure drop over time further analyzes whether the equipment is blocked or the trend of blockage worsening; then, by using the vibration difference and the set deviation threshold, it can be determined whether the equipment is blocked; the above steps, by monitoring changes in pressure drop, determine whether there is a worsening trend and detect blockage problems in advance; if abnormal vibration difference or pressure change is found, measures can be taken immediately to prevent the problem from worsening.

[0090] S255: Using the separation efficiency evaluation value, re-collect the lubricating oil sample to identify the particle size distribution and gum content (i.e., viscous substances include gum) of this type of metal particles, and generate trend data; use the trend data to analyze the main contamination factors of the lubricating oil sample; classify the contamination sources of the metal particles in the lubricating oil sample according to the main contamination factors.

[0091] It should be noted that the above steps, by analyzing the metal particles and gum components in lubricating oil samples, identify contamination sources and further assess the impact of contaminants, providing a basis for further contamination source classification. Then, by comparing historical data and trends, the source of contaminants is analyzed, and metal particles that may cause blockages are identified. Based on the type of contamination source, more targeted cleaning or replacement measures can be developed to improve lubricating oil quality and extend equipment lifespan. These steps, by accurately identifying contamination sources, enable targeted measures to reduce contamination risks, further optimize lubricating oil management, and thereby improve equipment reliability and efficiency.

[0092] The above steps utilize the separation efficiency assessment value to re-collect lubricating oil samples to identify the particle size distribution and gum content of this type of metal particles because the operating status of the equipment and the deterioration of the oil are a dynamic process. The previously constructed contamination feature dataset can be used as a "historical state," while the abnormal separation efficiency assessment value represents "a potential crisis for the current equipment due to the lubricating oil." There may be a time lag between the two, during which the nature of the contaminants may have undergone a qualitative change.

[0093] Specifically, such as Figure 7 As shown, in step S255, the particle size distribution and gum content of the metal particles in the lubricating oil sample are re-acquired using the separation efficiency evaluation value to generate trend data; the main contamination factors of the lubricating oil sample are analyzed using the trend data; and the contamination sources of the metal particles in the lubricating oil sample are classified according to the main contaminant factors. The specific operation steps are as follows:

[0094] S2551: Extract separation efficiency indicators from the separation efficiency evaluation value; preset a separation threshold;

[0095] Determine whether the separation efficiency index is less than the separation threshold;

[0096] If so, the separation efficiency evaluation value is determined to be abnormal, and a new lubricating oil sample is collected from the machine operating equipment. The lubricating oil sample is then pre-processed to collect the particle size distribution of the metal particles.

[0097] The gum content was determined by solvent extraction of newly collected lubricating oil samples (i.e., taking an appropriate amount of sample from the same lubricating oil sample, adding an appropriate amount of suitable solvent (e.g., dichloromethane or other specified solvent) for extraction; after stirring, ultrasonic treatment or other processes, the gum components were fully dissolved in the solvent; after filtration, concentration and other steps, the gum content was quantitatively determined using instruments such as ultraviolet-visible spectrophotometer or infrared spectrometer, and the measured value was recorded).

[0098] It should be noted that the separation efficiency index described above is used to determine whether the equipment is operating normally and to ensure that the equipment is running in optimal condition. If the separation efficiency index is lower than the preset threshold, it indicates that the equipment's lubricating oil separation efficiency has decreased, which may indicate the risk of contaminant accumulation or system blockage. In this case, it is necessary to collect lubricating oil samples again for further analysis of their composition. The decrease in separation efficiency mentioned above may be related to the aggregation of metal particles and colloids. After collecting and processing the samples, solvent extraction is used to detect the colloid content, which helps to accurately understand the type and concentration of contaminants.

[0099] The colloid content value obtained in this step is a verification value for a specific trend analysis, and is an accurate value for the content present on the metal particles; while the colloid value in step S2 above represents a basic measurement value, which is directly converted by scanning the characteristic band of an infrared spectroscopy device, and the two are represented differently.

[0100] S2552: Convert the particle size distribution of the re-collected metal particles into a particle size distribution curve; identify each peak of the particle size distribution curve, and select the largest peak as the main peak (i.e., the position with the most particles or the highest area ratio).

[0101] Preset baseline data values ​​(i.e., the basic peak value of metal particles and the initial colloidal content value); use the baseline data values, colloidal content value and the maximum peak value to calculate the particle size offset and colloidal growth rate.

[0102] The particle size offset and the gel growth rate are sorted in chronological order to form trend data;

[0103] It should be noted that the above-mentioned method uses the particle size distribution of metal particles to further understand the nature of lubricating oil contamination and identify the sources of contaminants (such as mechanical wear); then, the main peak is identified through the particle size distribution curve, and the particle size shift and gum growth rate are calculated by combining the baseline data values, thereby obtaining the dynamic trend of contamination; the shift in particle size distribution and the rate of change of gum reflect the accumulation of contaminants over time, and the trend data can be used to track the generation and accumulation process of contaminants;

[0104] S2553: Preset offset threshold and gel growth rate threshold based on the aforementioned trend data;

[0105] Determine whether the particle size offset is greater than the offset threshold;

[0106] If so, then the shift in the particle size distribution of the metal particles is determined to be the main factor affecting pollution.

[0107] If not, then determine whether the gel growth rate is greater than the gel growth rate threshold;

[0108] If so, then the abnormal increase in colloid content is determined to be the main factor causing the pollution change;

[0109] Furthermore, the second derivative of the gel growth rate is calculated according to the time change to determine the gel polymerization value; if the gel polymerization value is positive, it is determined that the gel is polymerizing.

[0110] It should be noted that, based on time series data, the main factors of pollution change are identified, and the risks that the equipment may face are identified. In the above, the particle size shift and the growth rate of colloids are judged by preset thresholds to determine whether they exceed the set thresholds, and the impact of pollution on the equipment is further assessed. The changing trend of pollutants helps to predict whether the equipment will be blocked or other malfunctions. If an abnormal increase of a certain pollutant such as colloids is found, measures are taken in time to prevent equipment problems.

[0111] After identifying the abnormal growth of gum as the main factor causing pollution changes in the above steps, the gum polymerization value is calculated based on the second derivative of the gum growth rate to determine whether polymerization occurs after the abnormal growth of gum. Simultaneously, research has found that lubricating oil undergoes a complex oxidation and degradation process during use, leading to gum polymerization. Under the influence of high temperature, oxygen, and metal catalysts (such as iron and copper wear particles), lubricating oil base oil and additives undergo oxidation reactions, generating initial peroxides and free radicals. Polymerization reactions occur between free radicals or between molecules containing unsaturated bonds, connecting them through covalent bonds and causing a sharp increase in molecular weight.

[0112] The above calculation of the second derivative by monitoring the growth rate of gum content is essentially monitoring the rate of the above-mentioned oxidative polymerization reaction. A rapidly increasing gum content means that the oil is deteriorating rapidly and the polymerization reaction is accelerating.

[0113] S2554: Based on the main changing factors of pollution, re-extract the viscous substance content distribution map from the re-collected lubricating oil sample; calculate the surface area of ​​the viscous substance content distribution map;

[0114] The overall adsorption value is calculated using the surface area of ​​the viscous substance content distribution map and the polymerization value of the gel.

[0115] ;

[0116] In the formula, Expressed as the overall adsorption value;

[0117] The surface area of ​​the viscous substance content distribution map obtained by re-extraction from the current data;

[0118] The reference surface area value is collected or preset during the initial operation of the equipment;

[0119] For at any time The polymer value of the gel was obtained by calculating the second derivative;

[0120] This represents the baseline gel polymerization value at the corresponding time point;

[0121] This represents the total number of time points involved in the calculation.

[0122] The reference weights for adsorption evaluation;

[0123] Norm[.] is a normalization function that ensures that the final calculation result falls within a predetermined range (e.g., between 0 and 1).

[0124] Determine whether the overall adsorption value is less than the critical value for clogging risk;

[0125] If so, it is determined that the adsorption characteristics of the viscous substance have changed (i.e., the degree of polymerization has increased or the adsorption capacity has been enhanced).

[0126] It should be noted that the above steps analyze changes in the adsorption characteristics of lubricating oil by calculating the surface area of ​​the viscous substance content distribution map and the gum polymerization value, thereby predicting the potential risk of equipment blockage. Based on the surface area of ​​the resampled viscous substance content distribution map, combined with the gum polymerization value, the overall adsorption value is calculated. If this value is less than the critical value for blockage risk, it indicates that the adsorption characteristics of the viscous substances in the lubricating oil have changed, with increased polymerization or enhanced adsorption capacity. Changes in viscous substances in the above steps may directly lead to poor fluid flow and increase the risk of blockage. By analyzing changes in the overall adsorption value, risks can be identified early, and necessary preventive measures can be taken.

[0127] S2555: Obtain particle images of metal particles from the lubricating oil sample with altered adsorption properties.

[0128] The particle image is used to identify the particle size distribution, particle outline, and surface texture image of the metal particles.

[0129] The metal particles are identified by metal instruments to determine their metal element type (i.e., iron, chromium, nickel, etc.).

[0130] It should be noted that obtaining the type of pollution source, especially through image analysis of metal particles, helps determine whether the pollutants originate from mechanical wear. The process involves acquiring particle images of the metal particles, then analyzing their size distribution, outline, and surface texture using particle image recognition technology, combined with metal element detection using metal instruments (such as iron, chromium, nickel, etc.). The morphology and composition of the metal particles can provide clues to the pollution source, especially since metal particles caused by mechanical wear have unique surface characteristics. By identifying these characteristics, the above steps can further confirm the wear condition of the equipment and classify the pollution source.

[0131] S2556: Calculate the proportion of each metal element (i.e., iron, chromium, nickel, etc.) in the metal particles;

[0132] Preset threshold values ​​for each ratio; determine whether the ratio of each metal is greater than each threshold value;

[0133] If so, the metal elements corresponding to the metal ratio are labeled as mechanical wear types by combining the particle outline and surface texture images, and pollution source classification results are generated.

[0134] It should be noted that analyzing the type and proportion of metal particles in the lubricating oil further confirms the source of contamination. The above steps involve calculating the proportion of each metal element in the particles and determining whether it exceeds a set threshold. If it does, the metal element is labeled as a type of mechanical wear. Different metal elements have different sources and effects. For example, elements such as iron, chromium, and nickel may be caused by mechanical wear. By accurately analyzing the metal proportions in the above steps, the type of contamination source can be determined, allowing for targeted measures to reduce equipment damage.

[0135] Example 2

[0136] like Figure 8 As shown, the present invention also provides a lubricating oil contamination level classification assessment and processing system, including: a data acquisition module 10; and an identification module 20.

[0137] The acquisition module 10 is used to acquire lubricating oil samples from multiple machine operating devices, and preprocess the lubricating oil samples to obtain samples to be tested.

[0138] The identification module 20 is used to extract metal particles and colloids from the sample to be tested to construct a pollution feature dataset; analyze the viscous substance content of the pollution feature dataset to obtain the comprehensive correlation between the flow rate and pressure of the lubricating oil sample and the clogging risk threshold value of the viscous substance content; calculate the clogging risk probability value of each machine operating equipment using the comprehensive correlation and the clogging risk threshold value; and analyze the pollution source classification results of metal particle clogging in the machine operating equipment using the clogging risk probability value.

[0139] This invention discloses a lubricating oil contamination level classification and assessment system. During execution, the system first acquires lubricating oil samples from multiple operating machines, preprocesses these samples to obtain samples to be tested, extracts metal particles and colloids from the samples to construct a contamination feature dataset, analyzes the viscous substance content of the contamination feature dataset to obtain the comprehensive correlation between flow rate and pressure in the lubricating oil sample and the clogging risk threshold value of the viscous substance content, calculates the clogging risk probability value for each operating machine using the comprehensive correlation and clogging risk threshold value, and analyzes the contamination source classification results of metal particle clogging in the operating machines using the clogging risk probability value. By classifying the contamination sources of metal particles, the system enables more targeted lubricating oil detection in machinery and equipment, identifying lubricating oil anomalies.

[0140] Example 3

[0141] On the other hand, this third embodiment, based on the lubricating oil contamination level classification and assessment method provided in the first embodiment of the invention, also provides a computer storage medium 1140 (hereinafter referred to as the storage medium). For example... Figure 9 The diagram shown is a schematic of a computer storage medium structure framework provided in Embodiment 3 of the present invention, which includes:

[0142] Memory 1130 is used to store computer programs;

[0143] The communication interface 1120 is used to connect the memory 1130 to the processor 1110;

[0144] Processor 1110 is configured to execute a computer program to implement a method for classifying and assessing the contamination level of a lubricating oil, as disclosed in an embodiment of any combination of the above-described embodiments.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; those skilled in the art can modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for classifying and assessing the contamination level of lubricating oil, characterized in that, The following steps are included: Lubricating oil samples were obtained from multiple operating machines, and the lubricating oil samples were preprocessed to obtain samples to be tested. The sample to be tested was used to extract metal particles and colloids to construct a pollution feature dataset. Obtain the rate of change of flow rate and the rate of change of pressure difference for the sample under test in each particle range; Calculate the rate of change of average flow rate and the rate of change of average pressure difference for all particle ranges; The first Pearson correlation coefficient was calculated using the Pearson correlation coefficient method to determine the relationship between viscous substance content and average flow rate. The Pearson correlation coefficient method is used to calculate the second Pearson correlation coefficient based on the rate of change of the viscous substance content with the average pressure difference; the average value of the first and second Pearson correlation coefficients is calculated as the comprehensive correlation degree. Obtain the viscous substance content value in the lubricating oil sample corresponding to the blockage incident in the historical record, sort the viscous substance content values ​​in the historical record in descending order, and calculate the first quartile as the blockage risk threshold. Collect the content value of viscous substances in the lubricating oil in real time; determine whether the content value of viscous substances in the lubricating oil in real time is greater than the critical value for blockage risk; If so, calculate the excess ratio of the viscous substance content in the real-time lubricating oil. A preset piecewise function is used to calculate the temperature increase based on the excess ratio; A pressure adjustment coefficient is introduced, and the pressure increment is calculated by using the introduced pressure adjustment coefficient and the excess ratio. By using a preset benchmark flow rate, the flow rate change rate is reduced to decrease the flow rate and extend the residence time of the lubricating oil. The machine operation equipment is adjusted using the increase in pressure and decrease in flow rate as actual adjustment values; the actual fluctuation range is calculated using the set values ​​of the machine operation equipment and the actual adjustment values. Record the maximum actual fluctuation range, and calculate the upper limit of the safe fluctuation range using the set value of the machine operating equipment and the maximum actual fluctuation range; The safety margin index is obtained by calculating the ratio of the difference between the actual adjustment value and the upper limit of the safety fluctuation range to the upper limit of the safety fluctuation range. The probability value of blockage risk is calculated based on the safety margin index, the critical value of blockage risk, and the comprehensive correlation. The separation efficiency evaluation value of the blocked machine operating equipment is calculated based on the blockage risk probability value of each machine operating equipment. The separation efficiency evaluation value was used to analyze the source classification results of metal particle contamination in the lubricating oil sample.

2. The method for classifying and assessing the contamination level of lubricating oil according to claim 1, characterized in that, The sample to be tested is used to extract metal particles and colloids to construct a pollution feature dataset. The specific operation steps are as follows: The sample to be tested is analyzed by a laser particle size analyzer to identify the particle size distribution and number of metal particles, and the particle dispersion is calculated. The sample to be tested is scanned using an infrared spectroscopy device with pre-set characteristic bands for the gel, and the absorption spectral data of each band in the sample to be tested is obtained; the absorption spectral data is then converted into numerical values ​​for the gel. The metal particles in the sample to be tested are uniformly divided into particle intervals, wherein adjacent grids belonging to the same particle dispersion range are merged to obtain particle intervals; the total area of ​​the particle splicing domain is calculated for each particle interval. The proportion of viscous substance adsorption in each particle interval is calculated based on the total area of ​​the particle splicing domain and the value of the colloid. The content of viscous substance is extracted by analyzing the proportion of viscous substance adsorption in each particle interval, and a distribution map of viscous substance content is constructed. The pollution feature dataset is constructed by combining the numerical values ​​of the colloid, the total area of ​​the particle splicing domain in each particle interval, and the distribution map of the viscous substance content.

3. The method for classifying and assessing the contamination level of lubricating oil according to claim 2, characterized in that, The separation efficiency evaluation value of the blocked machine is calculated based on the blockage risk probability value of each machine operating device. The specific operation steps are as follows: The blockage risk probability values ​​of each machine operating equipment are sorted in descending order, and the highest blockage risk probability value is selected for collecting vibration frequency, operating temperature fluctuation amplitude, fluid flow rate and pressure drop over a continuous time period. The vibration frequency is converted into a frequency domain signal using Fourier transform according to the moving average method, and the frequency component with the largest amplitude is calculated from the frequency domain signal as the main vibration frequency component. Linear regression was used to calculate the slope of the pressure drop over a continuous time period. A sliding window is used to calculate the mean and standard deviation of the operating temperature fluctuation amplitude in each window. The average flow rate and standard deviation of the flow rate are calculated for the fluid velocity over the continuous time period. The flow fluctuation coefficient is calculated using the average flow rate and the standard deviation of the flow rate. A smooth trend curve is generated by using the moving average method to combine the dominant vibration frequency component with the slope of pressure drop over time, the standard deviation of temperature fluctuation, and the flow fluctuation coefficient. The vibration difference is calculated by comparing the dominant vibration frequency component with the reference operating frequency of the machine operating equipment. A preset deviation threshold is established; it is then determined whether the vibration difference exceeds the deviation threshold. If so, it is determined that the machine's operating equipment is vibrating abnormally and there is a blockage. If not, then identify whether the slope of the pressure drop over time increases based on the smoothed trend curve; If so, it is determined that the machine's operating equipment is experiencing a trend of increasing congestion; Record the abnormal duration of the aforementioned blockage; The separation efficiency evaluation value is obtained by weighting the vibration difference with the slope of the increase in pressure drop over time and the duration of the abnormality.

4. The method for classifying and assessing the contamination level of lubricating oil according to claim 3, characterized in that, The separation efficiency evaluation value was used to analyze the source classification of metal particle contamination in the lubricating oil sample. The specific operation steps are as follows: Using the separation efficiency evaluation value, lubricating oil samples are re-collected to identify the particle size distribution and gum content of this type of metal particles, generating trend data; the trend data is used to analyze the main contamination factors of the lubricating oil samples; and the contamination sources of the metal particles in the lubricating oil samples are classified according to the main contaminant factors.

5. The method for classifying and assessing the contamination level of lubricating oil according to claim 4, characterized in that, Using the separation efficiency evaluation value, lubricating oil samples were re-collected to identify the particle size distribution and gum content of metal particles, generating trend data. The specific operation steps are as follows: Extract separation efficiency indicators from the separation efficiency evaluation values; preset separation thresholds; Determine whether the separation efficiency index is less than the separation threshold; If so, the separation efficiency evaluation value is determined to be abnormal, and a new lubricating oil sample is collected from the machine operating equipment. The lubricating oil sample is then pre-processed to collect the particle size distribution of the metal particles. The content of gum was determined by solvent extraction of the re-collected lubricating oil samples. The particle size distribution of the re-collected metal particles is converted into a particle size distribution curve; the peak values ​​of the particle size distribution curve are identified, and the largest peak value is selected as the main peak. Preset a baseline data value; use the baseline data value to calculate the particle size offset and the gum growth rate by comparing it with the gum content value and the maximum peak value; The particle size offset and the gel growth rate are sorted in chronological order to form trend data.

6. The method for classifying and assessing the contamination level of lubricating oil according to claim 5, characterized in that, The main contamination factors of the lubricating oil samples were analyzed using the aforementioned trend data. Based on these main contaminant factors, the sources of metal particle contamination in the lubricating oil samples were identified and classified. The specific operational steps are as follows: Based on the aforementioned trend data, preset offset thresholds and gel growth rate thresholds are established; Determine whether the particle size offset is greater than the offset threshold; If so, then the shift in the particle size distribution of the metal particles is determined to be the main factor affecting pollution. If not, then determine whether the gel growth rate is greater than the gel growth rate threshold; If so, then the abnormal increase in colloid content is determined to be the main factor causing the pollution change; Furthermore, the second derivative of the gel growth rate is calculated according to the time change to determine the gel polymerization value; if the gel polymerization value is positive, it is determined that the gel is polymerizing. Based on the main factors causing the pollution changes, a distribution map of the viscous substance content was extracted from the re-collected lubricating oil samples. Calculate the surface area of ​​the viscous substance content distribution map; The overall adsorption value is calculated using the surface area of ​​the viscous substance content distribution map and the polymerization value of the gel. Determine whether the overall adsorption value is less than the critical value for clogging risk; If so, then it is determined that the adsorption characteristics of the viscous substance have changed; Particle images of metal particles were obtained from the lubricating oil sample with altered adsorption properties. The particle image is used to identify the particle size distribution, particle outline, and surface texture image of the metal particles. The metal particles were identified by using a metal instrument to determine their metal element type. Calculate the proportion of each metal element type in the metal particles; Preset threshold values ​​for each ratio; determine whether the ratio of each metal is greater than each threshold value; If so, the metal element corresponding to the metal ratio is labeled as mechanical wear type by combining the particle outline and surface texture image, and pollution source classification results are generated.

7. A lubricating oil contamination level classification and assessment system, characterized in that, include: Data acquisition module; Recognition module; The acquisition module is used to acquire lubricating oil samples from multiple machine operating devices, and to preprocess the lubricating oil samples to obtain samples to be tested. The identification module is used to perform the steps of the lubricating oil contamination level classification and assessment method according to any one of claims 1-6.

8. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of a lubricating oil contamination level classification and assessment process as described in any one of claims 1-6.

Images