Predictive maintenance method

Abstract

The invention relates to a method for predictive maintenance of an electrical apparatus (14) powered by a cable (16) including at least two conductors, including first and second electrical conductors (18i) electrically insulated from each other and which carry first and second electrical currents, having first and second intensities, respectively, the method including repeating, in real time, an updated cycle including the following consecutive steps: 1) measuring, at an updated instant, the first and second intensities, and determining, by computer, first and second updated values, for at least one attribute of the first and second intensities, respectively; 2) calculating, by computer, - at least one indicator depending on the first updated value and a first predetermined "prior" value, for the first intensity, prior to the updated cycle, for the at least one attribute; and - at least one indicator depending on the first and second updated values, without using such prior values, and then determining a risk of failure depending on the difference between the value of each indicator and a corresponding reference value; and 3) generating, by computer, depending on the risk of failure, an alert and, preferably, carrying out an intervention on the apparatus.

Description

[0001]DescriptionTitle: Predictive maintenance methodTechnical field The present invention relates to a predictive maintenance method and a monitoring device implementing such a method for monitoring an industrial electrical device. Prior art An industrial installation conventionally uses a wide variety of electrical devices, of different ages, and whose load is variable. The failure of a device can have very detrimental economic consequences. Maintenance operations are therefore planned in order to regularly check the condition of the devices. However, they often require a production shutdown. In particular, the motors must generally be dismantled in order to undergo a vibration analysis in the laboratory. This analysis makes it possible to evaluate the level of aging and, consequently,to decide on the scrapping of an engine or its renovation. There is a constant need for a solution allowing simplified and more efficient predictive maintenance. One aim of the present invention is to meet, at least partially, this need.Summary of the inventionAccording to the invention, this aim is achieved by means of a method for predictive maintenance of an electrical appliance powered by a cable comprising at least two conductors, comprising first and second electrical conductors electrically insulated from each other and in which first and second electric currents, having first and second intensities, respectively, flow, said method comprising a repetition, in real time, of an "updated" cycle comprising the following successive steps: 1) at an updated time, measurement of the first and second intensities, and determination, by computer, of first and second updated values,for at least one attribute of the first and second intensities, respectively, preferably for at least the amplitude or a phase shift of said intensities;2) by computer, calculation of- at least one indicator as a function of the first updated value and a first “previous” value determined, for the first intensity, prior to the updated cycle, for said at least one attribute, preferably determined during a cycle of steps 1) to 3) prior; and- at least one indicator as a function of the first and second updated values, without using said previous values, i.e. determined, for the first and / or second intensity, prior to the updated cycle, for said at least one attribute, then determination of a risk of failure as a function of the difference between the value of each indicator and a corresponding reference value;3) as a function of the risk of failure, generation, by computer, of an alert and, preferably,intervention on the device. An indicator may be a function of, or even be equal to, the difference between the first and second updated values. An indicator may be a function of, or even be equal to, the difference between one of the first and second updated values ​​and the corresponding previous value. As will be seen in more detail in the remainder of the description, a method according to the invention makes it possible to detect slow changes in the operation of the device, but also sudden changes in this operation. Advantageously, the method makes it possible to prevent a failure of the device, and therefore to avoid disruption resulting from the occurrence of this failure. Furthermore, it can be implemented in situ, on the device in operation. A method according to the invention may also include one or more of the following optional characteristics: - said previous values ​​are measured for more than 1 hour, more than 1 day, more than 1 week,more than one month, and / or less than six months before the updated time;- the first and second intensities are out of phase during normal operation of the device, preferably by 180° (two-phase current) or 120° (three-phase current), and at least one indicator measures an imbalance between said intensities, in particular a deviation from the phase shift during normal operation;- alternatively, the first and second intensities are in phase, as in a multi-conductor cable comprising several conductors insulated from each other and supplied by the same phase;- the device is a motor, a compressor or an extruder, said device preferably having a nominal power greater than 1 kW;- in step 1), the first and second intensities are measured by means of magnetic field sensors arranged around the cable, configured to measure, for each of the conductors,at least one component of the magnetic field produced by the current flowing in the conductor;- said first and second intensities are measured by following steps consisting of:E1. placing a plurality of said magnetic field sensors around said cable, at at least one location of said cable;E2. simultaneously measuring, for each of said conductors, at least one component of the magnetic field produced by the current flowing in said conductor, by means of said plurality of magnetic field sensors;E3. for each of said conductors, determining the angle between said conductor and the nearest magnetic field sensor of said plurality of magnetic field sensors,said angle being defined with respect to the center of said cable and by assimilating said conductors and said sensors to points; the intensities of the currents in said conductors being linked to the components of the magnetic field measured by the relation B = kMI where B is the matrix of said components of the magnetic field, I is the matrix of said intensities of the currents, M is a matrix comprising a plurality of proportionality coefficients depending on said angles between said conductors and said magnetic field sensors and k is a predetermined coefficient, E4. calculate the inverse M, -1 of the matrix M, so as to deduce the values ​​of the said current intensities I = (µ0 / 2π).M -1.B, where µ0 is an equivalent magnetic permeability which takes into account the presence of insulating materials in said cable;- each sensor is powered by a respective battery, a gauge preferably transmitting to a computer implementing steps 2) and 3), a charge level of said battery, the computer taking into consideration or not an intensity supplied by said sensor depending on whether the charge level exceeds or not a threshold charge level;- at least one said reference value is determined, by computer, depending on the operating mode of the device;- in step 2), at least one indicator is calculated by computer as a function of a difference between the first and second updated values, and / or as a function of a difference between the first updated value and the first previous value;- in step 2), at least one indicator is calculated by computer as a function of a difference between the first and second updated values, and / or as a function of a difference between the first updated value and the first previous value;at least one indicator chosen from the intensity and the phase shift between the different currents;- the first and second electric currents are alternating currents and at least one indicator is a function of or consists of a difference between the phases of the intensities of said currents or a difference between the amplitudes of the intensities of said currents;- at least one indicator and / or at least one reference value is / are determined, by computer, by statistical processing of historical data recorded on historical devices identical to said device powered by the cable, the statistical processing being configured to establish a correlation between indicator values ​​and the occurrence of a failure of the device;- in step 2), it is determined, by comparison of the value of each indicator with a corresponding reference value,a predicted time interval before a failure occurs;- the reference value is stored in a memory accessible to the computer or determined by computer based on operating conditions of the device at the updated instant;- the method is implemented while the device is in operation;- in step 3), the updated first and second intensities are displayed in the same graph, on a computer screen, the graph showing, preferably superimposed, the temporal evolutions of the first and second intensities;- the cable comprises first, second and third electrical conductors electrically insulated from each other, in step 1), the first, second and third intensities of the first, second and third electric currents flowing in the first, second and third conductors, respectively, are measured, and in step 2),the risks of failure are determined for each pair of two intensities chosen from the first, second and third intensities, that is to say by using, for each pair of two intensities, the updated and previous values ​​of said intensities.The invention also relates to the use of a method according to the invention for:- detecting imbalances between the phases of the intensities of the currents flowing in the different conductors of the cable, in particular in a cable supplying, in three-phase, a motor or a compressor, and / or- detecting a drop in intensity in a cable, in particular in a cable supplying an extruder. The invention also relates to a monitoring device for implementing a method according to the invention, said device comprising:- at least two sensors, comprising first and second sensors capable of measuring the first and second intensities;- a computer configured to receive,from the first and second sensors, the measurements of the first and second intensities respectively, and comprising code instructions for implementing steps 2) and 3) and for determining the first and second values ​​updated in step 1). In one embodiment, the device further comprises a third sensor, measuring said third intensity of the third electric current flowing in the third conductor. The computer preferably comprises a screen capable of displaying, in the same graph, the temporal evolutions of the different intensities and / or of displaying a said alert. The invention also relates to: - a computer program comprising program code instructions for executing steps 2) and 3) and for determining the first and second values ​​updated in step 1) of a method according to the invention, when said program is executed by a computer,- a computer medium on which such a program is recorded, for example a memory or a CD-ROM.The invention finally relates to an industrial installation comprising:- a monitoring device according to the invention;- an electrical apparatus;- a cable supplying electrical energy to said apparatus, said cable comprising at least two conductors, these conductors comprising first and second electrical conductors electrically insulated from one another and in which first and second electrical currents circulate, respectively; the first and second sensors being coupled to the first and second conductors, respectively, so as to measure first and second intensities of the first and second electrical currents, respectively; the computer of the device being configured to receive, from the first and second sensors, the measurements of the first and second intensities respectively,and having access to a program comprising code instructions for implementing steps 2) and 3) and for determining the first and second values ​​updated in step 1). Definitions A "cable" comprises a set of electrical wires, or "electrical conductors", or "conductors", electrically insulated from each other, adjacent to each other and fixed to each other, the conductors being conventionally housed in a common sheath. A "real-time" cycle repetition means that the time interval between two successive cycles is less than 5 s, preferably less than 3 s, preferably less than 2 s, preferably less than 1 s. "Computer" means a computer processing unit, which includes a set of several machines, having computer processing capabilities. This unit may be integrated in particular in a tablet, a mobile phone or be a PC-type computer or a server,for example a server remote from the user, for example being the "cloud". The computer can also be, at least in part, integrated into the housing of the sensors. The sensors and the computer include means of communication to exchange between them. Conventionally, a computer includes in particular a processor, a memory, a human-machine interface, conventionally including a screen, a communication module via the internet, WIFI, Bluetooth® or the telephone network. Software configured to implement a method of the invention is loaded into the computer memory. The computer can also be connected to a printer. "Comprising" or "comprising" or "having" should be interpreted in a non-restrictive manner, unless otherwise indicated. A cable comprising two conductors can therefore include more than two conductors,for example be a three-phase power cable.Brief description of the figures Other characteristics and advantages of the invention will become apparent from reading the detailed description which follows and from examining the appended drawing in which:- [Fig 1] Figure 1 schematically represents the different stages of a method according to the invention;- [Fig 2] Figure 2 schematically represents an installation according to the invention, and- [Fig 3] Figure 3 illustrates the operation of a set of magnetic field sensors for evaluating an electrical intensity.An index "i" applied to a reference to an object designates, generically, the different occurrences of this object. For example, if a cable comprises first, second and third conductors 18i, this means that it comprises a first conductor 181,a second conductor 182 and a third conductor 183. Detailed description The objective of the method according to the invention is to alert on the probable occurrence of a failure of an electrical device in an industrial installation, thus allowing preventive intervention on the device. As illustrated in Figure 2, the industrial installation 10 comprises: - a monitoring device 12 according to the invention; - an electrical device 14; - a power cable 16 supplying electrical energy to said device, said cable comprising at least two conductors, these conductors comprising first and second electrical conductors 18, ielectrically insulated from each other and in which first and second electric currents ii flow, respectively. The electrical apparatus 14 may be of any type. Conventionally, its nominal power is greater than 1 kW, greater than 3 kW, or greater than 5 kW, and / or less than 1000 kW, or less than 100 kW, or less than 10 kW. It may in particular be a motor, a compressor or an extruder, in particular an extruder used to form a sheath around electrical conductors to manufacture a cable. Such an extruder conventionally comprises one or more heating rings arranged so as to melt plastic granules so that the molten material obtained can be extruded around electrical conductors, then cooled in order to form a cable.The electrical appliance is conventionally supplied with energy, generally from the public electricity network, by means of the power cable 16, generally three-phase for high powers. The monitoring device is provided so that maintenance can be carried out before the occurrence of failures. The monitoring device 12 comprises: - at least two sensors comprising first and second sensors 20i coupled to the first and second conductors, respectively, so as to measure the first and second intensities, respectively; - a computer 22 in communication with the first and second sensors, so that the computer can receive the measurements of the first and second intensities respectively. The computer 22 can be a computer of any type. However, it is specifically programmed for the implementation of steps 2) and 3) and for the determination of the first and second values ​​updated in step 1).It is preferably installed in the industrial installation, but could be, at least in part, remote from the installation, the communication means used to communicate with the computer 22 being adapted accordingly. The sensors are preferably arranged outside the conductors whose current intensity they measure. In a preferred embodiment, the sensors are magnetic field sensors arranged around the cable, at at least one location of the cable. Preferably, at least one component of the magnetic field produced by the current flowing in the conductor is measured simultaneously by means of the sensors for each of the conductors. For each of the conductors, the angle between the conductor and the nearest magnetic field sensor of the plurality of magnetic field sensors is determined, this angle being defined relative to the center of the cable and by assimilating the conductors and the sensors to points.The current intensities in the conductors are related to the magnetic field components measured by the relation B = kMI where B is the matrix of magnetic field components, I is the matrix of current intensities, M is a matrix comprising a plurality of proportionality coefficients depending on the angles between the conductors and the magnetic field sensors and k is a predetermined coefficient. We can then calculate the inverse M. -1 of the matrix M, so as to deduce the values ​​of the current intensities I = (µ0 / 2π).M -1.B, where µ0 is an equivalent magnetic permeability that takes into account the presence of insulating materials in the cable. Since a polyphase cable has several current densities coming from its different conductors, one can first calculate the magnetic field produced by the current using the Biot-Savart law, and then invert all the local measurements of the magnetic field components by determining an inverse matrix, in order to obtain the current intensities coming from the different current sources. The preferred method of measuring the current intensity is described below in detail for a cable with five conductors, but the cable could have a different number of conductors.This method consists in simultaneously measuring the intensity of the current in the conductors of the plurality of conductors by performing a first step E1 consisting in placing a plurality of magnetic field sensors around the cable, at at least one location of the cable. During the operation of installing the sensors in step E1, no movement is required, neither of the sensors, nor of the cable, whether it is a translational movement, a rotational movement, or any other movement. Furthermore, there is no constraint as to the knowledge or application of the intensity values ​​of the electric current flowing in the conductors of the cable. Then a step E2 consists in simultaneously measuring, for each of the conductors of the cable, at least one component of the magnetic field produced by the current flowing in this conductor. These simultaneous measurements are carried out by means of the plurality of magnetic field sensors.In a particular embodiment, the plurality of magnetic field sensors can measure for each conductor only the tangential component or only the radial component of the magnetic field. Alternatively, for greater precision, the plurality of magnetic field sensors can measure for each conductor both the tangential component and the radial component of the magnetic field. Then, during a step E3, for each of the conductors, the angle α between this conductor and the nearest magnetic field sensor of the plurality of magnetic field sensors is determined. The angle α is defined relative to the center of the section of the cable and by assimilating the conductors and the sensors to points. Indeed, for simplicity, it is assumed that each conductor has an infinitely small section and that the magnetic field captured by each sensor is located at a point corresponding to the location of the sensor.Figure 3 schematically illustrates, by way of non-limiting example, a cable of circular cross-section comprising five conductors regularly distributed inside the cable, which are assimilated to five points C1 to C5 equidistant from each other on the circumference of a circle T. Only the magnetic field sensor closest to the conductor C1 has been represented and is symbolized by the point A. The radius of the circle T is designated by r, the distance between the conductor C1 and the sensor A is designated by d1, the straight line segment connecting the sensor A and the center of the circle T is designated by d'1, the angle at point A between the straight line segment d'1 and the straight line segment connecting the conductor C1 and the point A is designated by β. The magnetic field captured by the sensor A is represented by the vector B1, which is orthogonal to the straight line segment connecting the conductor C1 and the point A.For a cable comprising N conductors each producing a magnetic field Bi, i = 1, …, N, the component B. A of the magnetic field at point A coming from the N conductors is defined as follows: ^^ ^^^ ^^^ ^^^ ^ où : B im is the component of the magnetic field coming from the i ème driver captured by the mth sensor; the angles αi and βi are defined for the i ème conductor in a similar way to the angles α and β defined above, respectively;di denotes the distance between the ith conductor and the nearest sensor;µ0 is an equivalent magnetic permeability which takes into account the presence of insulating materials in the cable;r is as defined above the radius of the circle T; andIim is the value of the intensity of the current flowing in the i ème conductor and deduced from the magnetic field measurement carried out by the m ièmesensor. The number of magnetic field sensors is at least equal to the total number N of conductors in the cable. Thus, the current intensities in the conductors are related to the measured magnetic field components, by the relation B = kMI where B is the matrix of the magnetic field components measured in all the conductors by all the sensors, I is the matrix of the current intensities flowing in all the conductors, M is a matrix comprising a plurality of proportionality coefficients depending on the angles between the conductors and the magnetic field sensors and k is a predetermined coefficient. This results in I = (µ0 / 2π).M -1 .B, where M -1 is the inverse matrix of M. Thus, following step E3 of determining the angle α between each conductor and the nearest sensor, we carry out a step E4 consisting of calculating the inverse matrix M- 1, so as to deduce the values ​​of the intensities I of the currents in all the conductors of the cable. As a non-limiting example, for N = 5 conductors and five magnetic field sensors placed respectively at points A, B, C, D and E, the analytical expression allowing the intensities of the currents in the conductors to be deduced is as follows:[Math.2] ^^ ^ ^^ ^^ = ∙ where Ii, i = 1, …, 5 denotes the intensity of the current flowing in the i èmeconductor and BA, BB, BC, BD and BE denote the magnetic field components respectively measured by the five sensors. The equivalent magnetic permeability µ0 is a macroscopic permeability, which makes the calculation simpler than if we considered the local magnetic permeability. In a particular embodiment, the angle α between this conductor and the nearest magnetic field sensor of the plurality of magnetic field sensors is determined so as to maximize the following function F: [Math.3] Yes i denotes the intensity of the current flowing in the i èmeconductor. There are various known mathematical convergence methods for maximizing F, such as the Levenberg-Marquardt algorithm (also called the LM algorithm) or the Nelder-Mead method. The computer 22 is programmed to apply steps E3 of angle determination and E4 of inverse matrix calculation of the method described above, to deduce the intensity of the current flowing in each of the conductors. This embodiment makes it possible to measure the intensity of the current in all the conductors of the cable in a single operation and to quickly obtain extremely accurate results, without having to remove the cable sheath. In addition, the installation of the magnetic field sensors around the cables is easy and does not cause any damage, marks or deformation to the cable.Furthermore, since the position of the magnetic field sensors relative to the conductors of the cable is unknown, taking into account the angular offset between sensors and conductors makes it possible to increase the accuracy of the intensity values ​​obtained. Preferably, each sensor 20. iis powered by an “autonomous” energy source, preferably by a battery 24i associated with the sensor, preferably physically incorporated in the sensor. More preferably, a gauge 26i is associated with each battery 24i to measure a charge level of the associated battery 24i. The monitoring device is used to implement steps 1) to 3), as shown in Figure 1. The current in a conductor, preferably in each conductor, is preferably an alternating current, preferably sinusoidal. In step 1), the sensors 20i measure, at an “updated time”, the intensity of the currents ii which flow in the conductors 18i. Each sensor 20 i can directly measure the intensity of the current i iwhich circulates in a conductor 18i associated with it, and / or communicate to the computer 22 the measurement it takes so that the computer calculates the updated intensity from all the measurements received from the sensors. In a particularly advantageous embodiment, each gauge 26i communicates to the computer 22, preferably at regular intervals, the instantaneous charge level of the battery powering the associated sensor. The delay between two transmissions of the charge level is preferably less than 24 hours, preferably less than 1 hour. The transmission of the charge level can also be in real time. Communication between the sensors and the gauges on the one hand, and the computer 22 on the other hand, can be ensured by any means, preferably by radio or wired means, preferably by wired means.In step 2), the computer 22 analyzes the updated intensities received from the sensors in order to search for signs identified as warning of a future failure of the device. The intensity of a current in a conductor is conventionally characterized by a set of attribute values. The attributes are not limiting. We can distinguish between “intrinsic” or “relative” attributes, depending on whether they only take into account values ​​measured on a single conductor or whether they take into account values ​​measured on several conductors. We can also distinguish the attributes depending on whether they only take into account values ​​measured at the updated instant, or “instantaneous attributes”, or whether they take into account values ​​measured at the updated instant and values ​​measured at a previous instant, or “temporal attributes”.For example, the intensity of a sinusoidal current in a first conductor, as a function of time t, can be substantially equal to i1(t) = i01⋅sin(ω1⋅t + φ1) in a time interval centered on an instant T, where i01 is the amplitude of the intensity, in amperes (A), φ1 is the phase shift, or phase at the origin, expressed in radians, and ω1 is the pulsation, in radians per second (rad⋅s. -1 ), and- to i1'(t) = i01'⋅sin(ω1't + φ1') in a time interval centered on an instant T', where i01' is the amplitude of the current, in amperes (A), φ1' is the phase at the origin, expressed in radians, and ω1' is the pulsation, in radians per second, and the intensity of a sinusoidal current in a second conductor, as a function of time t, can be substantially equal- to i2(t) = i02⋅sin(ω2⋅t + φ2) in a time interval centered on an instant T, where i02 is the amplitude of the current, in amperes (A), φ2 is the phase at the origin, expressed in radians, andω2 is the pulsation, in radians per second (rad⋅s-1), and- at i2'(t) = i02'⋅sin(ω2't + φ2') in a time interval centered on an instant T', where i02' is the amplitude of the intensity, in amperes (A), φ2' is the phase at the origin, expressed in radians, and ω2' is the pulsation, in radians per second. The origin is a "zero" instant from which an intensity is measured. i1, i01 , ω1, φ1, i2, i02 , ω2 and φ2 are examples of intrinsic and instantaneous attributes, i01 - i02 , ω1 – ω2 and φ1 – φ2 are examples of relative and instantaneous attributes, i1 – i1', i01 - i01' , ω1 – ω1', φ1 – φ1', i2 – i2', i02 - i02', ω2 – ω2', φ2 – φ2', (i1 – i1') / (T-T'), (i01 -i01') / (T-T'), (ω1 – ω1') / (T-T'), (φ1 – φ1') / (T-T'), (i2 – i2') / (T-T'), (i02 - i02' ) / (T-T'), (ω2 –ω2') / (T-T'), (φ2 – φ2') / (T-T') are examples of intrinsic and temporal attributes, andi1 - i2', i01 - i02', ω1 – ω2', φ1 – φ2', (i01 - i02' ) / (T-T'), (ω1 – ω2' / (T-T'), (φ1 – φ2') / (T-T') are examples of relative and temporal attributes.The combinations of attributes mentioned above are also examples of attributes. An indicator is an attribute whose value, compared with a corresponding reference value, provides information on the probability of occurrence of a future failure of the device, i.e. on a "risk of failure". A statistical analysis makes it possible to determine the indicators, depending on the device considered. In particular, for a given device, we can identify the attributes whose values ​​evolve significantly (from a statistical point of view) before the failure occurs, and deduce one or more indicators using these attributes. We can also compare the values ​​of the attributes for a device that has not suffered a failure, with the values ​​for these same attributes for the same device that has suffered a failure.It is thus possible to associate an indicator value with a probability of occurrence of the failure in the future. In practice, the pulsation is imposed by the electrical network. The preferred attributes, and the preferred indicators are functions, or even consist of i1 – i2, i01 - i02 ("difference in amplitudes of the current intensity in different conductors"), φ1 – φ2 (or "phase difference at the origin of the current intensity in different conductors", or "phase shift between phases"), i1 – i1', i01 - i01' , φ1 – φ1', i2 – i2', i02 - i02' , φ2 – φ2', (i1 – i1') / (T-T'), (i01 -i01') / (T-T') (or "speed of change of the amplitude of the current intensity in a conductor", (φ1 – φ1') / (T-T') (or "speed of change of the phase at the origin of the current intensity in a conductor"), (i2 – i2') / (T-T'), (i02 - i02' ) / (T-T'), (φ2 – φ2') / (T-T').The indices "1" and "2" given here designate indifferently the first, second, third, or ith conductor of the cable, i being an integer greater than or equal to 1, so that for example, for a three-phase cable ie comprising three conductors, the attributes and indicators mentioned above can involve the three conductors. For example, for a motor, the indicator can be an imbalance between the intensities of the different phases. Indeed, if the intensity is not equivalent on the three phases, this can mean that there is a malfunction which can cause premature wear.The statistical analyses described above also make it possible to determine, for an indicator, a reference value defining a limit between an acceptable situation, i.e. for which the probability of occurrence of the failure is sufficiently low to be acceptable, and an unacceptable situation, i.e. for which the probability of occurrence of the failure is sufficiently high for a maintenance intervention to be planned. More preferably, similar statistical analyses can also be used to evaluate the time interval separating the updated instant and the instant of the failure. The computer can thus advantageously evaluate the instant of failure, i.e. the future instant at which the failure should statistically occur, from the difference between the value of an indicator and the corresponding reference value.Determining the instant of failure advantageously makes it possible to plan the intervention on the device as best as possible, in step 3). Preferably again, similar statistical analyses can also be used to evaluate a threshold charge level to assess whether the energy supplied by a battery to a sensor is sufficient for the measurement made by the sensor to be considered reliable. The reference values ​​of the various indicators and the threshold charge level are accessible to the computer. They can in particular be recorded in a memory accessible to the computer. In a preferred embodiment, the reference value of at least one indicator is determined by the computer as a function of the operating mode of the device.The computer 22 then receives information characteristic of the operation of the device, for example information relating to the instructions given to the device, and deduces therefrom, according to pre-established rules to which the computer has access, the reference value. This information can be entered by an operator or result from measurements on the device. For example, if the device is an extruder, the amplitude of the intensity of the currents will be different depending on whether the temperature supplied by the heating rings is increasing, for example at the start of the extruder, or whether it is stable. Between these two phases, a large change in the amplitude of the intensity can be considered acceptable, whereas it will not be between two instants during the stable operating phase. For example, if the device is a motor, the normal intensity of the currents will be different depending on whether the motor is operating at full load or at reduced load.The computer therefore determines a higher reference value when the motor is operating at full load. Indicators using relative attributes are particularly well suited when a "normal" relationship (i.e., in the absence of a fault) is known between the attributes of the currents in the different conductors. In particular, for a three-phase current, the currents in the three conductors classically evolve, temporally, in the same way, with a phase shift of 120°. They have the same amplitude. A deviation from this normal relationship can constitute an indicator that is advantageously easy to evaluate. When the computer uses an indicator requiring values ​​at different times, i.e., uses a temporal attribute, the values ​​of the attributes determined during successive cycles are time-stamped and stored in a memory accessible by the computer.The computer can thus retrieve these values ​​from the memory to calculate the indicator. Preferably, the computer compares the values ​​of several indicators with corresponding reference values ​​in order to better assess the probability of a future occurrence of a failure. More preferably, the computer 22 also analyzes the charge level received from each gauge 26i. If a charge level of a sensor is lower than a threshold charge level, the computer issues a corresponding alert so that a recharge or a battery change is planned and / or rejects the intensities determined from the measurements made by the sensor, considering that their quality is insufficient. In one embodiment, the sensors communicate with the computer 22 by radio, preferably by radio frequencies.Preferably, the computer evaluates the quality of the signals received, according to any known method, and, if the quality is insufficient, - issues a corresponding alert so that a maintenance operation is planned, and / or - rejects the intensities determined from these signals. In step 3), if the result of the comparison of a value of at least one indicator with the corresponding reference value is associated with an unacceptable situation, for example if the value of said indicator is higher or lower than the reference value, the computer issues an alert. The alert can be of any nature, for example visual and / or audible. In particular, it can be a message and / or an image displayed on the computer screen. An operator having received the alert can plan a maintenance operation O to return to a normal situation for the device.The intervention may consist in particular of replacing the device or modifying it, in particular to update or repair it. The alert may also be processed electronically by a maintenance planning tool. The cycle of steps 1) to 3) is repeated, the time interval between two steps preferably being less than 1 hour, preferably less than 1 minute, preferably less than 5 seconds. The cycle of steps 1) to 3) is preferably repeated instantaneously, for real-time monitoring. The measurements are preferably displayed on a computer screen, preferably in the form of a graph showing, as a function of time, the measured intensities and / or the value of one or more intensity attributes, the curves of the different intensities preferably being superimposed.In one embodiment, the time scale represents a duration greater than 1 hour, preferably greater than 1 day or greater than 1 week and / or less than 6 months. More preferably, the computer displays an interface allowing the operator to- select the information he wishes to view, and / or- select display options for the selected information, and / or- select one or more sensors in order to limit the display to the information provided by this or these sensors, and / or- perform operations on the information received, for example to add intensities. Remarkably, the method according to the invention makes it possible in particular to detect imbalances between the intensities in the conductors of the cable, leading to overconsumption by the device. This overconsumption can in particular reflect fatigue of the device, in particular of a motor, and therefore a risk of future failure.The method according to the invention also makes it possible to detect a drop in intensity in a conductor of a cable supplying an extruder. This drop may in particular reflect deterioration of a heating collar and therefore a risk of failure, for example poor mixing of the material to be extruded, jamming or physical degradation of the heating collar. As is now clearly apparent, the invention makes it possible, by analyzing the intensities of the electric currents circulating in the different conductors of a power cable of an appliance, to detect slow changes in indicators, by using intensity measurements at different times, in particular on the same conductor, but also to detect more rapid changes, in particular by using intensity measurements at the same time, carried out on different conductors.Monitoring these indicators, preferably in real time, makes it possible to anticipate a failure of the device, and therefore to intervene preventively on the device to avoid this failure. The use of autonomous sensors, arranged outside the conductors, facilitates the implementation of the invention. The measurement of the gauges of the batteries supplying the sensors and the non-use of measurements carried out with an insufficient charge level improves the reliability in the assessment of the risk of failure. Of course, the invention is not limited to the embodiments described above and shown. In particular, the preceding description refers to first and second conductors, but is not limited to a configuration comprising only two conductors.Preferably, the invention is applied in particular to a power cable comprising three conductors for supplying a three-phase appliance, said first and second conductors being able to be any pair of two conductors chosen from the three conductors of the cable. The invention is also not limited to alternating currents. The currents can also be direct. The conductors of the cable are not necessarily identical.

Claims

Claims 1 . Procédé de maintenance prédictive d’un appareil électrique (14) alimenté par un cable (16) comprising at least two conductors, comprising first and second electrical conductors (18 i ) electrically isolated from each other and in the esquels des premier et deuxième courants électriques, ayant des première et deuxième intensités, respectivement, circulent, said method comprising a repetition, in real time, of an updated cycle comprising the following successive steps: 1) at an updated time, measurement of the first and second intensities, and étermination, par ordinateur, de première et deuxième valeurs actualisées, pour au moins un attribut des première et deuxième intensités, respectivement ; 2) par ordinateur, calcul de - au moins un indicateur en fonction de la première valeur actualisée et d’une première valeur « antérieure » déterminée, pour la première intensité, antérieurement au cycle actualisé, pour ledit au moins un attribut ; et - au moins un indicateur en fonction des première et deuxième valeurs actualisées, sans utiliser de dites valeurs antérieures, then determination of a risk of failure based on the difference between the v aleur de chaque indicateur et une valeur de référence correspondante ; 3) en fonction du risque de défaillance, génération, par ordinateur, d’une alerte et, de preference, intervention on the device. 2 . Procédé selon la revendication immédiatement précédente, dans lequel l’appareil (14) is a motor, a compressor or an extruder, said apparatus having a p uissance nominale supérieure à 1 kW.

3. Procédé selon l’une quelconque des revendications précédentes, dans lequel, à l’étape 1), les première et deuxième intensités sont mesurées au moyen de capteursmagnetic field sensors arranged around the cable, configured to measure, for each of the conductors, at least one component of the magnetic field produced by the current flowing in the conductor.

4. Procédé selon la revendication immédiatement précédente, dans lequel on mesure lesdites première et deuxième intensités en suivant des étapes consistant à : E1. placing a plurality of said magnetic field sensors around said cable, in a u moins un emplacement dudit câble ; E2. simultaneously measure, for each of said conductors, at least one component of the magnetic field produced by the current flowing in said c onducteur, au moyen de ladite pluralité de capteurs de champ magnétique ; E3. for each of said conductors, determine the angle between said conductor and the nearest magnetic field sensor of said plurality of magnetic field sensors, said angle being defined relative to the center of said cable and in ssimilant lesdits conducteurs et lesdits capteurs à des points ;the intensities of the currents in said conductors being linked to the components of the magnetic field measured by the relation B = kMI where B is the matrix of said components of the magnetic field, I is the matrix of said intensities of the currents, M is a matrix comprising a plurality of proportionality coefficients depending on said angles between said conductors and said magnetic field sensors and k is a predetermined coefficient, E4. calculate the inverse M -1 of the matrix M, so as to deduce the values ​​of said current intensities I = (µ 0 / 2π).M -1 .B, where µ 0 is an equivalent magnetic permeability which takes into account the presence of insulating materials in said cable.

5. Procédé selon l’une quelconque des deux revendications immédiatementprevious, in which each sensor is powered by a respective battery, a gauge preferably transmitting to a computer (22) implementing steps 2) and 3), a charge level of said battery, the computer taking into consideration or not an intensity supplied by said sensor depending on whether the charge level exceeds or not a threshold charge level.

6. Procédé selon l’une quelconque des revendications précédentes, dans lequel au at least one said reference value is determined, by computer, depending on the operating mode of the device.

7. Procédé selon l’une quelconque des revendications précédentes, dans lequel, à step 2), we calculate, by computer, at least one indicator as a function of a difference between the first and second updated values, and / or function of a d ifférence entre la première valeur actualisée et la première valeur antérieure.

8. Procédé selon l’une quelconque des revendications précédentes, dans lequel, à step 2), at least one indicator chosen from the intensity and the phase shift between the different currents is calculated by computer.

9. Procédé selon l’une quelconque des revendications précédentes, dans lequelthe first and second electric currents are alternating currents and at least one indicator is a function of or consists of a difference between the phases of the i ntensités desdits courants ou une différence entre les amplitudes des intensités of said currents.

10. Procédé selon l’une quelconque des revendications précédentes, dans lequel au at least one indicator and / or at least one reference value is / are determined, by computer, by statistical processing of historical data recorded on historical devices identical to said device (14) powered by the cable, the statistical processing being configured to establish a correlation between indicator values ​​and the occurrence of a failure of the device.

11. Procédé selon l’une quelconque des revendications précédentes, dans lequel, à step 2), by comparing the value of each indicator with a corresponding reference value, a forecast time interval before a failure occurs is determined.

12. Procédé selon l’une quelconque des revendications précédentes, mis en œuvre alors that the device (14) is in operation.

13. Procédé selon l’une quelconque des revendications précédentes, dans lequel, àstep 3), the first and second updated intensities are displayed in the same graph, on a computer screen, the graph showing, superimposed, the temporal evolutions of the first and second intensities.

14. Utilisation d’un procédé selon l’une quelconque des revendications précédentes pour : - détecter des déséquilibres entre les phases des intensités circulant dans les différents conducteurs du câble, en particulier dans un câble alimentant, en triphasé, un moteur or a compressor, and / or - détecter une baisse d’intensité dans un câble, en particulier dans un câble alimentant an extruder.

15. Dispositif de surveillance pour la mise en œuvre d’un procédé selon l’une quelconque des revendications 1 à 13, ledit dispositif comportant : - au moins deux capteurs, comportant des premier et deuxième capteurs (20i) aptes à mesurer les première et deuxième intensités (ii) ; - un ordinateur (22) configuré pour recevoir, depuis les premier et deuxième capteurs, les mesures des première et deuxième intensités respectivement, et comportant des instructions de code pour la mise en œuvre des étapes 2) et 3) et pour la détermination des première et deuxième valeurs actualisées à l’étape 1) dudit procédé.

16. Programme d’ordinateur comprenant des instructions de code de programme pour l'exécution des étapes 2) et 3) d’un procédé selon l’une quelconque des revendications 1 à 13, et pour la détermination des première et deuxième valeurs actualisées à l’étape 1) dudit procédé.

Images