Method for determining the state of aging of a lubricant

Abstract

Method for determining the aging state of a lubricant. The present invention relates to a method for determining the aging state of a lubricant, comprising: a phase of constructing a training database (DB) from different lubricants, a phase of training a model (M) based on the training database (DB) so as to obtain a trained model (M') to determine physico-chemical analysis data of a lubricant based on measurements of the lubricant's characteristics of interest, a phase of using the trained model (M') for a target lubricant, comprising: receiving measurements of characteristics of interest of the target lubricant, the measurements having been acquired by a sensor (C), the determination by the trained model (M') of physico-chemical analysis data of the target lubricant.a phase of determining the aging state of the target lubricant based on the determined physico-chemical analysis data. Figure for the abstract: 3,

Description

Title of the invention: Method for determining the state of aging of a lubricant

[0001] The present invention relates to a method for determining the state of aging of a lubricant. The present invention also relates to an associated computer program product.

[0002] Lubricants are used in industry for many applications, particularly in the agricultural, construction, and automotive sectors.

[0003] To ensure the proper functioning of a lubricant, it is common practice to perform physicochemical analyses on the lubricant to obtain analytical data. Such an analysis makes it possible to determine the lubricant's state of aging, in particular whether the lubricant retains its intrinsic properties essential for good lubrication, and whether the machine is in good working order, without excessive mechanical wear.

[0004] However, carrying out these analyses is time-consuming, and the reliability of the results can be affected by the multiple manipulations involved (contamination during sampling, possible errors during analysis, possible errors in writing the analysis report, etc.).

[0005] There is therefore a need for a tool that allows the aging state of a lubricant to be determined in a simplified and reliable manner.

[0006] To this end, the present description relates to a method for determining the state of aging of a lubricant, the method being implemented by computer and comprising: - a phase of building a training database from different lubricants, the construction phase including: • obtaining initial data for each lubricant, the initial data being measurements of a set of characteristics, known as characteristics of interest, of the lubricant, the measurements having been acquired by at least one sensor, • the processing of the initial data in such a way as to compensate for temperature variations from at least one sensor, • obtaining second data sets for each lubricant, the second data sets being derived from a physico-chemical analysis carried out on the lubricant, • the construction of the training database (TD) by associating, for each lubricant, the first data processed with the second set of data, - a model training phase based on the training database to obtain a model trained to determine physico-chemical analysis data of a lubricant based on measurements of the lubricant's characteristics of interest, and - an exploitation phase of the trained model for a target lubricant, comprising the following steps: • the reception of measurements of characteristics of interest of the target lubricant, the measurements having been acquired by at least one sensor, • the determination by the trained model of physico-chemical analysis data of the target lubricant, - a phase of determining the aging state of the target lubricant based on the determined physico-chemical analysis data.

[0007] According to particular embodiments, the process comprises one or more of the following features, taken individually or in all technically possible combinations:

[0008] - the processing of the first data also includes the elimination of values aberrant in the initial data;

[0009] - the processing of the first data also includes filtering the first data on the range of validity of the application for which the lubricant is used and / or the range of validity of at least one sensor;

[0010] - the phase of determining the aging state of the target lubricant includes the determination of a desirability score for each determined physicochemical analysis data, the aging state of the target lubricant being determined based on the desirability scores;

[0011] - the phase of determining the aging state of the target lubricant includes also the determination of an overall desirability score based on all the desirability scores determined, the overall desirability score being representative of the aging state of the target lubricant;

[0012] - the phase of determining the aging state of the target lubricant includes also the generation of an alert or recommendation by comparing desirability scores or the overall desirability score to a predetermined threshold;

[0013] - the driven model is specific to a category of lubricants, the process including the repetition of the construction and training phases for other lubricant categories, so as to obtain a library of trained models for different lubricant categories, the method comprising, before the operation and aging state determination phases, a phase of selecting a trained model from the model library according to the target lubricant considered ;

[0014] - at least one feature of interest is chosen from among the features the following of the lubricant: temperature, viscosity, density and dielectric constant;

[0015] - the sensors are installed on operating equipment, such as a engine, hydraulic circuit, or gearbox, so as to allow monitoring of the aging status of the target lubricant in real time.

[0016] This description also relates to a computer program product comprising program instructions recorded on a computer-readable medium, for the execution of a process as described above when the computer program is executed on a computer.

[0017] This description also relates to a readable information medium on which a computer program product as previously described is stored.

[0018] Other features and advantages of the invention will become apparent from the following description of embodiments of the invention, given by way of example only and with reference to the drawings which are:

[0019] [Fig. 1], [Fig. 1], a schematic view of an example computer for implementing a method for determining the aging state of a lubricant,

[0020] [Fig. 2], [Fig. 2], a flowchart of an example implementation of a method determining the state of aging of a lubricant, and

[0021] [Fig.3], [Fig.3], a schematic representation of an example of the constitution of a database used to train a model to determine physico-chemical analysis data of a lubricant based on measurements of the lubricant's characteristics of interest.

[0022] A calculator 10 and a computer program product 12 are illustrated by [Fig.1].

[0023] Calculator 10 is preferably a computer.

[0024] More generally, the calculator 10 is an electronic calculator specific to manipulate and / or transform data represented as electronic or physical quantities in computer registers 10 and / or memories into other similar data corresponding to physical data in memories, registers or other types of display, transmission or storage devices.

[0025] The calculator 10 interacts with the computer program product 12.

[0026] As illustrated in [Fig. 1], the computer 10 comprises a processor 14 including a data processing unit 16, memories 18, and a data storage reader 20. In the example illustrated in [Fig. 1], the computer 10 includes a keyboard 22 and a display unit 24.

[0027] The computer program product 12 includes an information carrier 26.

[0028] The information support 26 is a support readable by the computer 10, usually by the data processing unit 16. The readable information support 26 is a medium suitable for storing electronic instructions and capable of being coupled to a bus of a computer system.

[0029] By way of example, the information medium 26 is a floppy disk or flexible disk (from the English name "Floppy disk"), an optical disk, a CD-ROM, a magneto-optical disk, a ROM memory, a RAM memory, an EPROM memory, an EEPROM memory, a magnetic card or an optical card.

[0030] The computer program 12, comprising program instructions, is stored on the information support 26.

[0031] The computer program 12 is loadable on the data processing unit 16 and is adapted to drive the implementation of a method for determining the aging state of a lubricant, when the computer program 12 is implemented on the processing unit 16 of the computer 10.

[0032] The operation of the calculator 10 will now be described with reference to [Fig.2], which schematically illustrates an example of the implementation of a process for determining the state of aging of a lubricant, and to [Fig.3], which is an example of a phase of the process.

[0033] The determination method comprises a phase 100 of constructing a drive database BD from different lubricants. Phase 100 is implemented by the computer 10 in interaction with the product computer program 12, i.e., is implemented by computer.

[0034] Phase 100 includes a step 110 of obtaining initial DI data for each lubricant. The initial DI data are measurements of a set of characteristics, referred to as characteristics of interest, of the lubricant. The measurements were acquired by at least one sensor C.

[0035] Preferably, at least one characteristic of interest is chosen from among the following characteristics of the lubricant: the temperature T, the viscosity V, the density D and the dielectric constant DC.

[0036] For example, as illustrated by [Fig.3], the characteristics of interest were measured by one or more sensors C installed on operating equipment E, such as an engine, a hydraulic circuit, or a gearbox.

[0037] Sensors C are, for example, connected sensors.

[0038] For example, the first DI data are measured at regular time intervals by the sensor(s) C, for example every 30 seconds.

[0039] Phase 100 includes a step 120 of processing the first DI data to obtain first processed Dl' data.

[0040] The processing makes it possible in particular to compensate for temperature variations from at least one sensor C. A smoothing filter is preferably applied to the temperature-compensated data.

[0041] More specifically, processing step 120 consists of determining values ​​for the characteristics of interest corrected for the effect of temperature (and measurement biases), for example, the corrected viscosity V*, the corrected density D* and the corrected dielectric constant DC*.

[0042] In one example implementation, the temperature curves of each sensor C are measured or provided in manufacturer data. The temperature sensitivity (the slopes) of the characteristics of interest is thus estimated. Compensation is then applied to the initial DI data to offset the temperature effect (for example, by setting a reference temperature).

[0043] Alternatively, a model is trained (machine learning or neural network) to determine the characteristics of interest (V*, D*, DC*) corrected for the effect of temperature as a function of the characteristics of interest (V, D, DC) and the temperature considered.

[0044] Preferably, the processing of the first DI data also includes the elimination of outliers in the first Dl data. The eliminated data are, for example, data outside the validity range of the sensor C. The validity range is, for example, given by the manufacturer and consists of intervals of acceptable values, beyond which the manufacturer does not guarantee the reliability of the data.

[0045] Preferably, the processing of the initial Dl data also includes filtering the initial Dl data based on the application's validity range for which the lubricant is used. For example, measurements taken during engine shutdown are eliminated because lubricant circulation is no longer ensured when the engine is stopped.

[0046] Preferably, the processing of the first data Dl also includes the normalization of the first data Dl with respect to the invariants of the respective signal from which the first data DL are derived. An invariant is, for example, the minimum value over an interval or certain quantiles of the distribution of the signal values.

[0047] Phase 100 includes a step 130 of obtaining second data D2 for each lubricant. The second data D2 are obtained from a physicochemical analysis performed on the lubricant. The second data D2 have typically been obtained in the laboratory.

[0048] Preferably, the second data D2 have also been preprocessed, for example so as to remove outliers or correct biases in the data.

[0049] The second data D2 are, for example, obtained at regular intervals, for example once a week.

[0050] The second data D2 are, for example, chosen from the following data:

[0051] - Standard analyses (Noack, flash point, pour point, cloud point, foaming, density, ash content, flash point...

[0052] - Kinematic viscosities (KV40, KV100, VI).

[0053] - Gas chromatography (fuel content).

[0054] - IR spectroscopy (soot content, oxidation, nitration).

[0055] - Titration (TAN, TBN, ipH, water content).

[0056] - Element content (ICP).

[0057] Phase 100 includes a step 140 of constructing the training database BD by associating, for each lubricant, the first processed data Dl' with the second data D2 (see [Fig.3]).

[0058] For example, in the case where the first processed data Dl' are more numerous than the second data D2, the association is made on the basis of the dates (i.e. the first sensor data for which second data D2 are available).

[0059] The determination method comprises a step 200 of training a model M against the training database BD so as to obtain a trained model M' (see [Fig. 3]) for determining physicochemical analysis data of a lubricant based on measurements of the lubricant's characteristics of interest. Step 200 is implemented by the computer 10 in interaction with the product computer program 12, i.e., is computer-implemented.

[0060] The model is, for example, a neural network. The learning technique allows the neural network to be configured as it learns from the database (supervised learning). In one example, part of the database is used to configure the neural network and the other part to validate the configuration.

[0061] Alternatively, the model implements one of the following algorithms: Random Forest, XGboost Regressor, Gradient Boosting, Linear Regression, Ridge Regression (alpha=l), and SVM (with linear kernel and radial basis function).

[0062] The determination method includes a phase 300 of operating the driven model M' for a target lubricant. Phase 300 is implemented by the computer 10 in interaction with the product computer program 12, i.e., is implemented by computer.

[0063] Phase 300 includes receiving measurements of characteristics of interest of the target lubricant. The measurements were acquired by at least one sensor C.

[0064] Preferably, the sensors C are installed on operating equipment E, such as an engine, a hydraulic circuit, or a gearbox, so as to allow real-time monitoring of the aging state of the target lubricant. C sensors are, for example, connected sensors.

[0065] Phase 300 then includes the determination by the trained model M' of the state of physico-chemical analysis data of the target lubricant.

[0066] The determination process includes a phase 400 for determining the aging state of the target lubricant based on the determined physicochemical analysis data. Phase 400 is implemented by the computer 10 in interaction with the product computer program 12, i.e., is computer-implemented.

[0067] In one example, phase 400 includes determining a desirability score for each determined physicochemical analysis data point. The desirability score is, for example, between 0 and 1.

[0068] For example, the desirability score is obtained using the following equation:

[0069] 0si?,(x) <Li ^(Ÿi) = sist,

[0070] Where: - y denotes the characteristic of interest i to be predicted, - L, denotes the minimum value to be set for the characteristic of interest i, and - Tt denotes the maximum value to be set for the characteristic of interest i.

[0071] In one variant, dt is not bounded at 1 and values ​​greater than 1 are allowed for d,.

[0072] Preferably, phase 400 also includes determining an overall desirability score based on all the determined desirability scores. The overall desirability score is representative of the aging state of the target lubricant.

[0073] For example, the total desirability score is obtained using the following equation: [°°741 o=( < / ,(^2(^2).

[0075] Where k denotes the number of characteristics of interest considered. The desirability score is typically expressed as a percentage.

[0076] Optionally, different weights are applied to the scores of the different characteristics of interest when calculating the total desirability score. The different weights, minimum values, and maximum values ​​are determined for each application.

[0077] Preferably, phase 400 also includes generating an alert or recommendation by comparing the desirability scores or the overall desirability score to a predetermined threshold. For example, an alert or recommendation is made when the desirability score is greater than 85% (0% denoting a state of (least worn lubricant and 100% represents the most worn lubricant state). This indicates, for example, that maintenance is required.

[0078] Preferably, the trained model is specific to a lubricant category, the method comprising repeating the construction 100 and training 200 phases for other lubricant categories, so as to obtain a library of trained models for different lubricant categories. In this case, the method includes, before the operation 300 and determination 400 phases, a phase 125 of selecting a trained model from the model library according to the target lubricant in question. The selection is, for example, performed by a user, or automatically based on the lubricant category type.

[0079] Thus, once the model is trained, the present method makes it possible to determine in a simplified way the state of aging of a lubricant, without physicochemical analyses and with only measurements from C sensors. The model having been trained on the basis of data taking into account the temperature variations of the sensor, the reliability is improved.

[0080] The present method thus makes it possible to prevent failures of a lubricant in operation, to help plan the maintenance of the equipment, and to replace the lubricant only when it is failing or aging.

[0081] A person skilled in the art will understand that the embodiments and variants described above can be combined to form new embodiments provided that they are technically compatible.

Claims

1. Claims Method for determining the aging state of a lubricant, the method being implemented by computer and comprising: - a phase of construction of a training database (DB) from different lubricants, the construction phase comprising: • obtaining first data (Dl) for each lubricant, the first data (Dl) being measurements of a set of characteristics, called characteristics of interest, of the lubricant, the measurements having been acquired by at least one sensor (C), • processing of the first data (Dl) so as to compensate for temperature variations of at least one sensor (C), • obtaining second data (D2) for each lubricant, the second data (D2) being derived from a physicochemical analysis carried out on the lubricant, • the construction of the training database (DB) by association, for each lubricant, of the first processed data (Dl') with the second data (D2), - a phase of training a model (M) based on the training database (BD) so as to obtain a trained model (M') to determine physicochemical analysis data of a lubricant based on measurements of the characteristics of interest of the lubricant, - an exploitation phase of the trained model (M') for a target lubricant, comprising the following steps: • receiving measurements of characteristics of interest of the target lubricant, the measurements having been acquired by at least one sensor (C), • the determination by the trained model (M') of physicochemical analysis data of the target lubricant, - a phase of determining the aging state of the target lubricant based on the physico-analysis data determined chemical.

2. The method of claim 1, wherein processing the first data (Dl) also comprises removing outliers from the first data (Dl).

3. Method according to claim 1 or 2, wherein the processing of the first data (D1) also comprises the filtering of the first data (D1) on the domain of validity of the application for which the lubricant is used and / or the domain of validity of the at least one sensor (C).

4. A method according to any one of claims 1 to 3, wherein the step of determining the aging state of the target lubricant comprises determining a desirability score for each determined physicochemical analysis data, the aging state of the target lubricant being determined as a function of the desirability scores.

5. The method of claim 4, wherein the step of determining the aging state of the target lubricant also comprises determining an overall desirability score based on all of the determined desirability scores, the overall desirability score being representative of the aging state of the target lubricant.

6. The method of claim 5, wherein the step of determining the aging state of the target lubricant also comprises generating an alert or recommendation by comparing the desirability scores or the overall desirability score to a predetermined threshold.

7. Method according to any one of claims 1 to 6, in which the trained model (M') is specific to a category of lubricants, the method comprising the repetition of the construction and training phases for other categories of lubricants, so as to obtain a library of trained models for different categories of lubricants, the method comprising, before the exploitation and aging state determination phases, a phase of selecting a trained model (M') from the library of models as a function of the target lubricant considered.

8. A method according to any one of claims 1 to 7, wherein at least one characteristic of interest is chosen from the following characteristics of the lubricant: temperature, viscosity, density and dielectric constant.

9. Method according to any one of claims 1 to 8, in which the sensors (C) are installed on equipment (E) in operation, such as an engine, a hydraulic circuit, or a gearbox, so as to allow the monitoring of the aging state of the target lubricant in real time.

10. A computer program product comprising program instructions recorded on a computer-readable medium, for executing a determination method according to any one of claims 1 to 9 when the computer program is executed on a computer.

Images