Lubricating oil pollution degree prediction method and monitoring system thereof

Abstract

The invention belongs to the technical field of lubricating oil pollution monitoring, and particularly relates to a lubricating oil pollution degree prediction method and a monitoring system thereof. The prediction method comprises the steps of establishing a lubricating oil pollution index set, performing equalization processing on lubricating oil pollution indexes, and optimizing an index set based on a lubricating oil pollution grade sequence after equalization processing and the lubricating oil pollution index sequence; and establishing a lubricating oil pollution degree prediction model, and obtaining prediction results of different lubricating oil pollution levels according to output results. According to the lubricating oil pollution degree prediction method, through optimization and screening processing of pollution factor indexes, repeated occurrence of repeated or implicit relevance influence factors can be effectively avoided, meanwhile, the expression ability of high-relevance influence factors is enhanced, and by combining a monitoring system of the lubricating oil pollution degree prediction method, the lubricating oil pollution degree is predicted. And comprehensive and efficient lubricating oil pollution state prediction analysis can be realized.

Description

Technical Field

[0001] This invention belongs to the field of lubricating oil contamination monitoring technology, and particularly relates to a method for predicting lubricating oil contamination and its monitoring system. Background Technology

[0002] Lubricating oil is one of the most important guarantees for the stable operation of various equipment. As the equipment operates for longer periods, the high-temperature and high-pressure working environment causes irreversible changes to the composition of the lubricating oil. Coupled with the influence of complex factors such as the peeling of materials from structural surfaces, the physicochemical properties and composition of the lubricating oil undergo continuous changes. This change constitutes contamination of the lubricating oil, and the detection and management of contamination are essential conditions for maintaining the stable performance of lubricating oil. Currently, lubricating oil testing methods include various spectrometers, thermogravimetric analyzers, various sensors, and specialized testing instruments. These methods and equipment are used to collect data on various components and the physicochemical properties of the lubricating oil. However, the diverse types of sensor data and the large volume of data involved mean that conventional lubricating oil contamination monitoring usually only analyzes a few key parameters or the characteristic parameters of the equipment, and cannot continuously monitor and analyze the contamination status of the lubricating oil throughout its entire lifespan. Summary of the Invention

[0003] The purpose of this invention is to provide a method with better universality based on actual needs, which can better screen lubricating oil contamination factor indicators according to real-time contamination status in the context of a large number of lubricating oil contamination status factors, achieve a more reasonable and accurate analysis of contamination status, and optimize the current contamination status analysis method.

[0004] To achieve the above objectives, the present invention adopts the following technical solution.

[0005] A method for predicting lubricating oil contamination includes the following steps:

[0006] Stp1, Establish a set of lubricating oil contamination indicators, including a lubricating oil contamination level sequence and a lubricating oil contamination indicator sequence;

[0007] Stp2, Average processing of lubricating oil contamination indicators, including average processing of lubricating oil contamination indicators based on normalization algorithm;

[0008] Stp3, Lubricating oil contamination index optimization: Based on the mean-processed lubricating oil contamination level sequence and lubricating oil contamination index sequence, the amplitude difference sequence is solved, the total correlation coefficient of lubricating oil contamination index types is solved, and the optimization is performed to obtain the optimized index set;

[0009] Stp4. Establish a lubricating oil contamination prediction model, specifically including: establishing training datasets and validation datasets; using lubricating oil contamination indicators as particle attributes and lubricating oil contamination levels as the search or evolution direction, establishing an optimization model based on particle swarm optimization algorithm, initializing particle population size and iteration parameters, configuring constraint conditions with contamination indicators under different lubricating oil contamination levels, selecting fitness functions, and establishing a prediction model; performing training optimization, adjusting prediction model parameters, and establishing a lubricating oil contamination prediction model.

[0010] Stp5: Input the real-time monitoring data into the lubricating oil contamination prediction model, and obtain the prediction results for different lubricating oil contamination levels based on the output results.

[0011] In a further improved or preferred embodiment of the aforementioned lubricating oil contamination prediction method, step Stp1, establishing a lubricating oil contamination index set, the lubricating oil contamination level sequence Y and the lubricating oil contamination index sequence X are represented as follows:

[0012] ;

[0013] ;

[0014] ;

[0015] in It refers to the first Each lubricating oil contamination level ; This refers to the m-th lubricating oil contamination index dataset. It refers to the m-th lubricating oil contamination index dataset. Individual indicator values, This represents the data volume of the m-th lubricating oil contamination index dataset.

[0016] In a further improvement or preferred embodiment of the aforementioned lubricating oil contamination prediction method, the total correlation of lubricating oil contamination index types in step Stp3 is obtained based on the following method:

[0017] Based on the mean-normalized lubricating oil contamination level sequence Y and the lubricating oil contamination index sequence X, for each lubricating oil contamination index sequence... Solve for the amplitude difference sequence between it and the lubricating oil contamination level sequence Y, which is expressed as:

[0018]

[0019] Solve for the amplitude difference sequence for each lubricating oil contamination level under different lubricating oil contamination index datasets. Then, the maximum amplitude difference of each type of pollution indicator at each pollution level is extracted. and minimum amplitude difference The correlation sequence of this pollution index under the lubricating oil pollution level was obtained. ; This refers to the mean of the m-th lubricating oil contamination index dataset;

[0020] Furthermore, the overall correlation of contamination indicators of a certain type of lubricating oil under all lubricating oil contamination levels was obtained.

[0021] .

[0022] In a further improvement or preferred embodiment of the aforementioned lubricating oil contamination prediction method, in step Stp3, the total correlation of all measurable lubricating oil contamination indicators under each lubricating oil contamination level is sorted, and the following judgments and operations are performed to obtain a preferred indicator set:

[0023] S1. Under each lubricating oil contamination level, determine whether the sum of the total correlation of multiple lubricating oil contamination indicators exceeds a preset threshold. , Furthermore, if the total number of indicators in this combination of lubricating oil contamination indicators is less than 30% of the total number of lubricating oil contamination indicators, and if so, assign a preference score of 0.5 to each lubricating oil contamination indicator in this combination of lubricating oil contamination indicators.

[0024] S2. Based on S1, determine whether there is a lubricating oil contamination indicator whose overall correlation exceeds a preset single indicator threshold. , If it exists, assign a priority score of 0.5 to the lubricating oil contamination index, assign a priority score of -0.5 to the lubricating oil contamination index with a correlation of 0 or not detected, and assign a priority score of 0 to the remaining indexes.

[0025] S3. Rank the priority scores of each lubricating oil contamination index under all lubricating oil contamination levels, and select the lubricating oil contamination indexes with the highest priority scores as the final selection results to establish a set of preferred indicators. The total priority scores of the selected lubricating oil contamination indicators should not be less than 80% of the total priority scores of all indicators to ensure the validity of the data.

[0026] A further improvement or preferred embodiment of the aforementioned lubricating oil contamination prediction method, specifically step Stp4, establishing a lubricating oil contamination prediction model, includes:

[0027] T1. Establish a sample dataset based on historical monitoring data of existing lubricating oil contamination elements. The lubricating oil contamination element indicators in the sample dataset serve as the input values ​​for the prediction model, and the lubricating oil contamination level serves as the output value. After applying appropriate indexing and processing to the sample data values, divide them into a training dataset and a validation dataset. The number of samples in the training dataset is... Verify the number of samples in the dataset;

[0028] T2. Using lubricating oil contamination index as particle attribute and lubricating oil contamination level as search or evolution direction, establish an optimization model based on particle swarm optimization algorithm, initialize particle population size and iteration parameters, configure constraint conditions with contamination index constraints under different lubricating oil contamination levels, select fitness function, and establish prediction model.

[0029] T3. Use training dataset samples to train and optimize the optimization model, input lubricating oil contamination factor indicators, and obtain the lubricating oil contamination degree output prediction result. Use validation dataset samples to verify the accuracy of the model output result. Adjust the prediction model parameters according to the accuracy of the prediction result until the output result meets the prediction accuracy requirements or reaches the preset number of iterations. Output the model parameters and establish the lubricating oil contamination degree prediction model.

[0030] In a further improvement or preferred embodiment of the aforementioned lubricating oil contamination prediction method, the averaging process in Stp2 can be expressed as follows: ,in This refers to the sample values ​​of lubricating oil contamination indicators. The value after mean normalization This refers to the maximum value of the lubricating oil contamination index sample. This refers to the minimum value of the lubricating oil contamination index sample.

[0031] This application also provides a lubricating oil contamination monitoring system based on the aforementioned lubricating oil contamination prediction method, including a lubricating oil monitoring component, a data transmission component, and a control execution component;

[0032] Lubricating oil monitoring components include sensors for acquiring various lubricating oil contamination elements or factors affecting the health status of lubricating oil within the lubricating oil chamber;

[0033] The data transmission components include a serial communication unit and a serial configuration unit;

[0034] The serial communication unit includes an RS485 / 232 signal converter, used to connect the sensor signal transceiver unit and the control execution component to realize data transmission and storage; and a serial port configuration unit, used to establish sensor data writing and reading protocol rules, determine serial port configuration, and complete serial port debugging.

[0035] The control and execution component consists of a controller, a data storage unit, and a display unit.

[0036] The controller is used to store the lubricating oil contamination prediction model constructed by the coding language, and to complete the sensor data processing and lubricating oil contamination prediction model calculation; the data storage unit includes a storage device for obtaining lubricating oil contamination indicators, lubricating oil contamination prediction model parameters, and lubricating oil contamination prediction model output data from the controller, and creating arrays or data tables for standardized storage according to various data formats; the display unit includes a display device for generating corresponding waveform charts based on the lubricating oil contamination element indicators transmitted by the controller.

[0037] In a further improvement or preferred embodiment of the aforementioned lubricating oil contamination monitoring system, the lubricating oil contamination elements or lubricating oil health status influencing elements include one or more of the following elements or their related elements: lubricating oil kinematic viscosity, lubricating oil temperature, lubricating oil density, oil pH value, and content of specific components.

[0038] In a further improvement or preferred embodiment of the aforementioned lubricating oil contamination monitoring system, the specific component refers to one or more of the following components: effective components of lubricating oil, water, air bubbles, organic molecules, solid particles, and oxide components.

[0039] Its beneficial effects are as follows:

[0040] The lubricating oil contamination prediction method of this application can effectively avoid the repetition of duplicate or implicitly correlated influencing factors by optimizing and screening contamination factor indicators, while enhancing the expressive power of highly correlated influencing factors. Combined with its monitoring system, it can achieve a more comprehensive and efficient prediction and analysis of lubricating oil contamination status. Attached Figure Description

[0041] Figure 1 This is a basic flowchart of the lubricating oil contamination prediction method.

[0042] Figure 2 This is a system structure diagram of a lubricating oil contamination monitoring system. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0044] This invention relates to a method for predicting lubricating oil contamination levels. It is mainly used to provide a method that can better optimize the processing of monitoring data for multiple types of contamination based on existing lubricating oil contamination monitoring schemes, and achieve more accurate and effective analysis and prediction of lubricating oil contamination status by selecting effective contamination elements.

[0045] The basic process of the lubricating oil contamination prediction method in this application is as follows: Figure 1 As shown below, each specific process step will be explained in detail.

[0046] Step 1: Establish a set of lubricating oil contamination indicators

[0047] The lubricating oil contamination index set is a basic standard used to judge the contamination status of lubricating oil. The contamination status (grade) of lubricating oil involves many factors and is not unique. For lubricating oils with different functions or different working environments, the judgment and evaluation of their contamination status often depends on different influencing factors. However, in general, due to different detection methods or principles, the influencing factors are often reflected in monitoring results in a variety of different ways. In order to better sort out and analyze the effectiveness of lubricating oil contamination factor indicators, it is necessary to first establish a lubricating oil contamination index set.

[0048] This application mainly includes a lubricating oil contamination level sequence Y and a lubricating oil contamination index sequence X; wherein

[0049] ;

[0050] ;

[0051] ;

[0052] The lubricating oil contamination level sequence Y is mainly used to characterize the contamination state of lubricating oil. In practical applications, based on the different usage requirements of lubricating oils and the application requirements of the working environment, corresponding standards are usually specified for different types of contamination levels and degrees of different lubricating oils. It refers to the first Each lubricating oil contamination level ;

[0053] The Lubricating Oil Contamination Index Sequence X is used to establish and organize the lubricating oil contamination index sequence. Each lubricating oil contamination index element is formulated based on the contamination elements given in the usage specifications and standards of various lubricating oils. This refers to the m-th lubricating oil contamination index dataset. It refers to the m-th lubricating oil contamination index dataset. Individual indicator values, This represents the data size of the m-th lubricating oil contamination index dataset;

[0054] Step 2: Averaging of lubricating oil contamination indicators;

[0055] The averaging of lubricating oil contamination indicators is primarily used to standardize the expression of contamination indicators of different orders of magnitude and parameter ranges, ensuring a generally consistent data range. This allows subsequent analysis to disregard specific parameter ranges and focus solely on the magnitude of changes in influencing indicators, analyzing the relative changes between various indicators throughout the contamination process. This enhances the ability to identify the decisive factors influencing contamination. Averaging can be expressed as follows: ,in This refers to the sample values ​​of lubricating oil contamination indicators. The value after mean normalization This refers to the maximum value of the lubricating oil contamination index sample. This refers to the minimum value of the lubricating oil contamination index sample;

[0056] Step 3: Optimization of Lubricating Oil Contamination Indicators

[0057] Because lubricating oil testing may involve various types of lubricating oil contamination indicators, including a large number of interrelated unnecessary or inherently repeatable indicators, it is necessary to select and eliminate non-essential and secondary indicators to determine and optimize the lubricating oil contamination indicators and avoid their influence on the actual lubricating oil contamination status. Specifically:

[0058] Based on the mean-normalized lubricating oil contamination level sequence Y and the lubricating oil contamination index sequence X, for each lubricating oil contamination index sequence... Solve for the amplitude difference sequence between it and the lubricating oil contamination level sequence Y, which is expressed as:

[0059]

[0060] Solve for the amplitude difference sequence for each lubricating oil contamination level under different lubricating oil contamination index datasets. Then, the maximum amplitude difference of each type of pollution indicator at each pollution level is extracted. and minimum amplitude difference The correlation sequence of this pollution index under the lubricating oil pollution level was obtained. Furthermore, the overall correlation of contamination indicators of a certain type of lubricating oil under all lubricating oil contamination levels was obtained. , This refers to the mean of the m-th lubricating oil contamination index dataset;

[0061] Solve for the overall correlation coefficient of all lubricating oil contamination index types, and select the best lubricating oil correlation index according to the following rules:

[0062] The total correlation of all measurable lubricant contamination indicators under each lubricant contamination level was ranked, and the following judgments and operations were performed:

[0063] S1. Under each lubricating oil contamination level, determine whether the sum of the total correlation of multiple lubricating oil contamination indicators exceeds a preset threshold. , Furthermore, if the total number of indicators in this combination of lubricating oil contamination indicators is less than 30% of the total number of lubricating oil contamination indicators, and if so, assign a preference score of 0.5 to each lubricating oil contamination indicator in this combination of lubricating oil contamination indicators.

[0064] S2. Based on S1, determine whether there is a lubricating oil contamination indicator whose overall correlation exceeds a preset single indicator threshold. , If it exists, assign a priority score of 0.5 to the lubricating oil contamination index, assign a priority score of -0.5 to the lubricating oil contamination index with a correlation of 0 or not detected, and assign a priority score of 0 to the remaining indexes.

[0065] S3. Rank the priority scores of each lubricating oil contamination index under all lubricating oil contamination levels, and select the lubricating oil contamination indexes with the highest priority scores as the final selection results to establish a set of preferred indicators. The total priority scores of the selected lubricating oil contamination indicators should not be less than 80% of the total priority scores of all indicators to ensure the validity of the data.

[0066] Step 4: Lubricating Oil Contamination Prediction Model

[0067] The actual monitoring values ​​of lubricating oil contamination indicators usually cannot cover the detection range of all indicators or the actual value range of all lubricating oil contamination elements. Therefore, this application introduces a processing scheme based on genetic mutation algorithm in the lubricating oil contamination degree prediction and analysis process to achieve more comprehensive tracking and prediction of lubricating oil contamination element indicators. The specific steps are as follows:

[0068] T1. Establish a sample dataset based on historical monitoring data of existing lubricating oil contamination elements. The lubricating oil contamination element indicators in the sample dataset serve as the input values ​​for the prediction model, and the lubricating oil contamination level serves as the output value. After applying appropriate indexing and processing to the sample data values, divide them into a training dataset and a validation dataset. The number of samples in the training dataset is... Verify the number of samples in the dataset;

[0069] T2. Using lubricating oil contamination index as particle attribute and lubricating oil contamination level as search or evolution direction, establish an optimization model based on particle swarm optimization algorithm, initialize particle population size and iteration parameters, configure constraint conditions with contamination index constraints under different lubricating oil contamination levels, select fitness function, and establish prediction model.

[0070] T3. Use training dataset samples to train and optimize the optimization model, input lubricating oil contamination factor indicators, and obtain the lubricating oil contamination degree output prediction result. Use validation dataset samples to verify the accuracy of the model output result. Adjust the prediction model parameters according to the accuracy of the prediction result until the output result meets the prediction accuracy requirements or reaches the preset number of iterations. Output the model parameters and establish the lubricating oil contamination degree prediction model.

[0071] like Figure 2 As shown, based on the aforementioned lubricating oil contamination prediction method, this application also provides a lubricating oil contamination monitoring system for implementing the above prediction method, including a lubricating oil monitoring component, a data transmission component, and a control execution component.

[0072] Lubricating oil monitoring components include sensors for acquiring various lubricating oil contamination elements or factors affecting the health status of lubricating oil within the lubricating oil chamber;

[0073] The lubricating oil contamination factors or lubricating oil health status influencing factors include one or more of the following factors or their related factors: lubricating oil kinematic viscosity, lubricating oil temperature, lubricating oil density, oil pH value, and content of specific components;

[0074] The specific component refers to one or more of the following components: effective components of lubricating oil, water, air bubbles, organic molecules, solid particles, and oxide components;

[0075] The data transmission components include a serial communication unit and a serial configuration unit;

[0076] The serial communication unit includes an RS485 / 232 signal converter, used to connect the sensor signal transceiver unit and the control execution component to realize data transmission and storage; and a serial port configuration unit, used to establish sensor data writing and reading protocol rules, determine serial port configuration, and complete serial port debugging.

[0077] The control and execution component consists of a controller, a data storage unit, and a display unit.

[0078] The controller is used to store the lubricating oil contamination prediction model constructed by the coding language, and to complete the sensor data processing and lubricating oil contamination prediction model calculation; the data storage unit includes a storage device for obtaining lubricating oil contamination indicators, lubricating oil contamination prediction model parameters, and lubricating oil contamination prediction model output data from the controller, and creating arrays or data tables for standardized storage according to various data formats; the display unit includes a display device for generating corresponding waveform charts based on the lubricating oil contamination element indicators transmitted by the controller.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the contamination level of lubricating oil, characterized in that, Includes the following steps: Stp1, Establish a set of lubricating oil contamination indicators, including a lubricating oil contamination level sequence and a lubricating oil contamination indicator sequence; Stp2, Average processing of lubricating oil contamination indicators, including average processing of lubricating oil contamination indicators based on normalization algorithm; Stp3, Lubricating oil contamination index optimization: Based on the mean-processed lubricating oil contamination level sequence and lubricating oil contamination index sequence, the amplitude difference sequence is solved, the total correlation coefficient of lubricating oil contamination index types is solved, and the optimization is performed to obtain the optimized index set; Stp4. Establish a lubricating oil contamination prediction model, specifically including: establishing training datasets and validation datasets; using lubricating oil contamination indicators as particle attributes and lubricating oil contamination levels as the search or evolution direction, establishing an optimization model based on particle swarm optimization algorithm, initializing particle population size and iteration parameters, configuring constraint conditions with contamination indicators under different lubricating oil contamination levels, selecting fitness functions, and establishing a prediction model; performing training optimization, adjusting prediction model parameters, and establishing a lubricating oil contamination prediction model. Stp5: Input the real-time monitoring data into the lubricating oil contamination prediction model, and obtain the prediction results for different lubricating oil contamination levels based on the output results.

2. The lubricating oil contamination prediction method according to claim 1, characterized in that, Step Stp1 involves establishing a set of lubricating oil contamination indicators, where the lubricating oil contamination level sequence Y and the lubricating oil contamination indicator sequence X are represented as follows: ， ， in It refers to the first Each lubricating oil contamination level ; This refers to the m-th lubricating oil contamination index dataset. It refers to the m-th lubricating oil contamination index dataset. Individual indicator values, This represents the data volume of the m-th lubricating oil contamination index dataset.

3. The lubricating oil contamination prediction method according to claim 2, characterized in that, The overall correlation of the lubricating oil contamination index types in step Stp3 was obtained based on the following method: Based on the mean-normalized lubricating oil contamination level sequence Y and the lubricating oil contamination index sequence X, for each lubricating oil contamination index sequence... Solve for the amplitude difference sequence between it and the lubricating oil contamination level sequence Y, which is expressed as: Solve for the amplitude difference sequence for each lubricating oil contamination level under different lubricating oil contamination index datasets. Then, the maximum amplitude difference of each type of pollution indicator at each pollution level is extracted. and minimum amplitude difference The correlation sequence of this pollution index under the lubricating oil pollution level was obtained. ; This refers to the mean of the m-th lubricating oil contamination index dataset; Furthermore, the overall correlation of contamination indicators of a certain type of lubricating oil under all lubricating oil contamination levels was obtained. 。 4. The lubricating oil contamination prediction method according to claim 3, characterized in that, In step Stp3, the total correlation of all measurable lubricating oil contamination indicators under each lubricating oil contamination level is sorted, and the following judgments and operations are performed to obtain the optimal indicator set: S1. Under each lubricating oil contamination level, determine whether the sum of the total correlation of multiple lubricating oil contamination indicators exceeds a preset threshold. , Furthermore, if the total number of indicators in this combination of lubricating oil contamination indicators is less than 30% of the total number of lubricating oil contamination indicators, and if so, assign a preference score of 0.5 to each lubricating oil contamination indicator in this combination of lubricating oil contamination indicators. S2. Based on S1, determine whether there is a lubricating oil contamination indicator whose overall correlation exceeds a preset single indicator threshold. , If it exists, assign a priority score of 0.5 to the lubricating oil contamination index, assign a priority score of -0.5 to the lubricating oil contamination index with a correlation of 0 or not detected, and assign a priority score of 0 to the remaining indexes. S3. Rank the priority scores of each lubricating oil contamination index under all lubricating oil contamination levels, and select the lubricating oil contamination indexes with the highest priority scores as the final selection results to establish a set of preferred indicators. The total priority scores of the selected lubricating oil contamination indicators should not be less than 80% of the total priority scores of all indicators to ensure the validity of the data.

5. The lubricating oil contamination prediction method according to claim 1, characterized in that, Step Stp4, establishing a lubricating oil contamination prediction model, specifically includes: T1. Establish a sample dataset based on historical monitoring data of existing lubricating oil contamination elements. The lubricating oil contamination element indicators in the sample dataset serve as the input values ​​for the prediction model, and the lubricating oil contamination level serves as the output value. After applying appropriate indexing and processing to the sample data values, divide them into a training dataset and a validation dataset. The number of samples in the training dataset is... Verify the number of samples in the dataset; T2. Using lubricating oil contamination index as particle attribute and lubricating oil contamination level as search or evolution direction, establish an optimization model based on particle swarm optimization algorithm, initialize particle population size and iteration parameters, configure constraint conditions with contamination index constraints under different lubricating oil contamination levels, select fitness function, and establish prediction model. T3. Use training dataset samples to train and optimize the optimization model, input lubricating oil contamination factor indicators, and obtain the lubricating oil contamination degree output prediction result. Use validation dataset samples to verify the accuracy of the model output result. Adjust the prediction model parameters according to the accuracy of the prediction result until the output result meets the prediction accuracy requirements or reaches the preset number of iterations. Output the model parameters and establish the lubricating oil contamination degree prediction model.

6. The lubricating oil contamination prediction method according to claim 1, characterized in that, In Stp2, the mean-averaging process can be expressed as: ,in This refers to the sample values ​​of lubricating oil contamination indicators. The value after mean normalization This refers to the maximum value of the lubricating oil contamination index sample. This refers to the minimum value of the lubricating oil contamination index sample.

7. A lubricating oil contamination monitoring system based on the lubricating oil contamination prediction method of claim 1, characterized in that, Includes lubricating oil monitoring components, data transmission components, and control execution components; Lubricating oil monitoring components include sensors for acquiring various lubricating oil contamination elements or factors affecting the health status of lubricating oil within the lubricating oil chamber; The data transmission components include a serial communication unit and a serial configuration unit; The serial communication unit includes an RS485 / 232 signal converter, which is used to connect the sensor signal transceiver unit and the control execution component to realize data transmission and storage; The serial port configuration unit is used to establish sensor data writing and reading protocol rules, determine serial port configuration, and complete serial port debugging. The control and execution component consists of a controller, a data storage unit, and a display unit. The controller is used to store the lubricating oil contamination prediction model constructed by the coding language, and to complete the sensor data processing and lubricating oil contamination prediction model calculation; the data storage unit includes a storage device for obtaining lubricating oil contamination indicators, lubricating oil contamination prediction model parameters, and lubricating oil contamination prediction model output data from the controller, and creating arrays or data tables for standardized storage according to various data formats; the display unit includes a display device for generating corresponding waveform charts based on the lubricating oil contamination element indicators transmitted by the controller.

8. The lubricating oil contamination monitoring system according to claim 6, characterized in that, The lubricating oil contamination factors or lubricating oil health status influencing factors include one or more of the following factors or their related factors: lubricating oil kinematic viscosity, lubricating oil temperature, lubricating oil density, oil pH value, and content of specific components.

9. The lubricating oil contamination monitoring system according to claim 7, characterized in that, The specific component refers to one or more of the following components: active ingredients of lubricating oil, water, air bubbles, organic molecules, solid particles, and oxide components.

Images