The invention relates to the field of predictive maintenance. More precisely, it relates to methods and devices for predictive maintenance of at least one component of a road vehicle.
Preventive maintenance of a road vehicle enables the user of the road vehicle to anticipate maintenance that has already been scheduled in the life of the road vehicle.
The document EP 0,661,673 A1 relates to a method of predictive maintenance in which a plurality of predetermined parameters representing the wear of the component to be taken into account is identified in an initialization step, the value of each wear parameter is read, the current value of the wear function is calculated using a predetermined wear function, and the value of the wear function obtained is compared with a threshold.
The document DE 102 35,525 A1 relates to methods of predictive maintenance in which the expected nominal value of a parameter of a component is predicted, and this value is compared with the value currently measured in the component, in order to determine abnormal behavior. This document also describes a method for evaluating the wear of a component as a function of various parameters, on the basis of frequency distributions. The wear evaluated in this way is used to update the predictive model used.
However, this predictive maintenance does not take into account the real state of the components of the road vehicle. This would make it possible to detect a potential fault in which a component is degraded as a result of continuous operation over a long time interval.
Furthermore, it does not allow real anticipation of maintenance, because it does not take into account the conditions of use of the component. This is because the duration of use of a component, usually expressed as a number of hours of operation, remains statistical in nature, and does not allow disparities of manufacture and/or use to be taken into account.
Consequently, the user is unable to draw the maximum benefit from the long life of the component, and therefore of the road vehicle, in a context of normal use.
Similarly, if a sudden failure occurs in the performance of the component, the user is only able to observe the failure of his component, without having been warned of the degradation of the component.
The present invention is therefore intended to overcome the aforesaid drawbacks.
For this purpose, a first aspect of the invention relates to a method for predictive maintenance of at least one component of a road vehicle.
A second aspect of the invention relates to a computer program with a program code for executing the steps of the method according to the first aspect of the invention.
And a third aspect of the invention relates to a device for predictive maintenance of at least one component of a road vehicle.
Thus the invention relates to a method for predictive maintenance of at least one component of a road vehicle, the component being connected to a computer. The method comprises the following steps:
In a first implementation, the computer is connected to an electronic controller of the component. In this case, the method further comprises the following steps:
In a second implementation, the computer is connected to a plurality of sensors of the road vehicle, which represent its dynamic behavior and/or its traffic environment. In this case, the method further comprises the following steps:
In a third implementation, the method further comprises a step in which the computer is arranged for calculating at least one statistical quantity on the basis of the wear, adaptation and/or driving profiles.
The invention also relates to a computer program with a program code for executing the steps of a method according to the invention when the computer program is loaded into the computer or executed in the computer.
The invention also covers a device for predictive maintenance of at least one component of a road vehicle. The device comprises a computer arranged to be connected to the component, wherein the computer is configured for:
In a first implementation, the computer is arranged to be connected to an electronic controller of the component. In this case, the computer is also configured for:
In a second implementation, the computer is arranged to be connected to a plurality of sensors of the road vehicle, which represent its dynamic behavior and/or its traffic environment. In this case, the computer is also configured for:
In a third implementation, the computer is arranged for calculating at least one statistical quantity on the basis of the wear, adaptation and/or driving profiles.
In a fourth implementation, the device comprises predictive maintenance display unit connected to the computer.
Other characteristics and advantages of the invention will be more readily understood by a perusal of the following description with reference to the attached drawings, provided for illustration and in a non-limiting way.
For the sake of clarity, the elements represented are not necessarily shown to scale with respect to each other, unless specified otherwise.
The general principle of the invention is based on the combination of the ranges of values of parameters that represent the wear of a road vehicle component. The invention proposes observing the duration of use of the combinations of ranges of values in order to deduce therefrom a wear profile which is compared with a predetermined wear profile. This mechanism makes it possible to reduce the amount of information to be stored.
In the example of
The computer 12 is also connected to the component 11, to the electronic controller 13 and to the plurality of sensors 14, for example, via a data communication bus of the CAN (Controller Area Network) or FlexRay type.
In a particular implementation, the road vehicle 10 further comprises a predictive maintenance display unit (not shown) connected to the computer 12.
In the invention, the aforementioned elements of the road vehicle 10 are of types known to those skilled in the art.
Thus, the component 11 corresponds to all the components of a road vehicle 10 whose wear can be measured by electronic means. In the example of
The computer 12 also corresponds to a processor. In the example of
Additionally, the electronic controller 13 is a processor. In the example of
Additionally, the sensors 14 are arranged to acquire physical characteristics describing the dynamic behavior of the road vehicle 10 and/or of its traffic environment.
In the example of
Similarly, the predictive maintenance display unit may be a liquid crystal screen, such as a computer or tablet screen, possibly associated with an audible alarm. In the invention, the predictive maintenance display unit may give a warning to a user of the road vehicle 10 on the basis of information supplied by the computer 12.
In the example of
In the example of
In the invention, each wear parameter may take a value in a first predetermined range of values. In the invention, the first predetermined range of values is delimited by a first extreme value and a second extreme value.
For example, in
Step 120 then consists in dividing, by means of the computer 12, each first range of values into a plurality of predetermined intervals.
For example, in
The example of
Thus, in the invention, the division of each range of values is specific to it and is not necessarily performed in the same way for the other ranges of values.
Returning to
In the example of
In the example of
In the invention, the combination of intervals of the first range of values is performed according to a first predetermined combination pattern. The predetermined combination pattern may be determined in the laboratory during the validation of the component 11. The predetermined combination pattern may also be supplemented with field measurements made on training vehicles. The data collected may subsequently be analyzed by statistical tools or machine learning, to identify the intervals of combination of parameters that are most representative.
Additionally, step 140 consists in determining, by means of the computer 12, a duration of use of each interval of combination of parameters as a function of at least one distance traveled by the road vehicle 10, so as to obtain a wear profile.
In practice, the computer 12 may comprise a time counter which is launched, during the use of the road vehicle 10, on each use of an interval of combination of parameters. The computer 12 may also comprise an odometer for determining the distance traveled by the road vehicle 10. Thus it is possible to establish a wear profile corresponding to the coupling between the duration of use of each interval of combination of parameters and a distance traveled by the road vehicle 10. In other words, the wear profile is a statistical distribution (also called a frequency distribution) of the intervals of combination of parameters. For example, the invention may produce a wear profile of the component 11 at 10,000 km, 20,000 km or 50,000 km.
Finally, step 150 consists in comparing the wear profile, by means of the computer 12, with a predetermined wear profile. This step makes it possible to detect a divergence from the predetermined wear profile. If such a divergence is detected, the computer 12 may give a warning to a user of the road vehicle 10 via the predictive maintenance display unit.
The predetermined wear profile may be determined in the laboratory during the validation of the component 11. The predetermined wear profile may also be supplemented with field measurements made on training vehicles. The data collected may subsequently be analyzed by statistical tools or machine learning, in order to identify the intervals of combination of parameters that are most representative according to the distance traveled.
A number of particular implementations of the method 100 may be envisaged.
In a first particular implementation of the method 100, the wear of the component 11 is detected by observing the variation of the error signals used by the electronic controller 13 for regulating the control of the component 11.
For example, in
In practice, the method 100 may consist, in step 111, in a similar manner to step 110, in identifying, by means of the computer 12, a plurality of error signals arranged for supplying the electronic controller 13, each of which represents a difference between an output value of the component and a target output value of the component. In the invention, each error signal may take a value in a second predetermined range of values.
Step 121 then consists, in a similar manner to step 120, in dividing, by means of the computer 12, each second range of values into a plurality of predetermined intervals.
Additionally, step 131, in a similar manner to step 130, consists in combining, by means of the computer, some or all of the intervals of one second range of values with some or all of the intervals of the other second ranges of values, according to a second predetermined combination pattern, so as to obtain a plurality of intervals of combination of error signals.
Additionally, step 141, in a similar manner to step 140, consists in determining, by means of the computer 12, a duration of use of each interval of combination of error signals as a function of at least one distance traveled by the road vehicle, so as to obtain an adaptation profile.
Finally, step 151, in a similar manner to step 150, consists in comparing the adaptation profile, by means of the computer 12, with a predetermined adaptation profile.
In a second particular implementation of the method 100, the wear of the component 11 is detected by observing the driving style of the driver of the road vehicle 10.
In practice, the method 100 may consist, in step 112, in a similar manner to step 110, in identifying, by means of the computer 12, at least one output value of each sensor. In the invention, each output value may take a value in a third predetermined range of values.
Step 122 then consists, in a similar manner to step 120, in dividing, by means of the computer 12, each third range of values into a plurality of predetermined intervals.
Additionally, step 132, in a similar manner to step 130, consists in combining, by means of the computer, some or all of the intervals of one third range of values with some or all of the intervals of the other third ranges of values, according to a third predetermined combination pattern, so as to obtain a plurality of intervals of combination of sensor values.
Additionally, step 142, in a similar manner to step 140, consists in determining, by means of the computer 12, a duration of use of each interval of combination of sensor values as a function of at least one distance traveled by the road vehicle, so as to obtain a driving profile.
Finally, step 152, in a similar manner to step 150, consists in comparing the driving profile, by means of the computer 12, with a predetermined driving profile.
In one implementation of the invention, the method 100 comprises a step in which the computer 12 is arranged for calculating at least one statistical quantity on the basis of the wear, adaptation and/or driving profiles.
In practice, this statistical quantity makes it possible to synthesize the information contained in the wear, adaptation and/or driving profiles in order to facilitate the comparison of these with the predetermined wear, adaptation and/or driving profiles.
For example, the computer 12 may calculate all the statistics required for characterizing a statistical series, such as the position characteristics (e.g. the mode, the median, the arithmetic mean, the quantiles) and the dispersion characteristics (e.g. the spread, the mean deviation, the inter-quantile deviation, the variance, the standard deviation and the coefficient of variation). However, other statistical quantities may be envisaged.
In a particular embodiment of the invention, the various steps of the method 100 are determined by instructions of computer programs. Therefore, the invention also proposes a program with a computer program code recorded in a non-volatile storage medium. In the invention, this program code is capable of executing the steps of the method 100 when the computer program is loaded into the computer or executed in the computer.
The present invention has been described above in the detailed description and illustrated in the figure. However, the present invention is not limited to the embodiments described. Thus other variants and embodiments may be deduced and implemented by those skilled in the art from a perusal of the present description and the attached figure.
Number | Date | Country | Kind |
---|---|---|---|
1900865 | Jan 2019 | FR | national |
This application is the U.S. national phase of International Application No. PCT/EP2020/052237 filed Jan. 30, 2020 which designated the U.S. and claims priority to French Application No. 1900865 filed Jan. 30, 2019, the entire contents of each of which are hereby incorporated by reference.
Filing Document | Filing Date | Country | Kind |
---|---|---|---|
PCT/EP2020/052237 | 1/30/2020 | WO | 00 |