Relative position detector between a rotor and a stator of a multiphase motor

Abstract

Position detector (Pi) for a multiphase motor (1), the detector (Pi) comprising: a linear Hall effect sensor (Hi) capable of generating an analog signal that varies continuously according to the orientation of a magnetic field rotating with a rotor (4) of the multiphase motor relative to a stator (2) of the multiphase motor; and a neural network (RPi) configured to determine a relative position between the rotor (4) and the stator (2) from the analog signal. Figure for the abstract: Fig. 3

Description

Title of the invention: Relative position detector between a rotor and a stator of a multiphase motor. Technical field

[0001] The present disclosure relates to a relative position detector between a rotor and a stator of a multiphase motor. STATE OF THE ART

[0002] It is essential to know the relative position between the stator of an electric motor and a rotating rotor relative to the stator in order to achieve precise control. Several methods are known for obtaining this position. The most widespread method today remains the use of a resolver placed at the end of the rotor shaft. The resolver then provides an absolute position with reasonable accuracy (accuracy ranging from a few mechanical degrees to a few tenths of a degree at best). However, this solution is expensive (the cost of the resolver is equivalent to that of some motors). The resolver cannot easily be duplicated because it is located at the end of the shaft, leaving no room for a second one, and its loss is critical for the system since nothing functions without the position information.

[0003] To overcome the drawbacks of the resolver, other methods have been developed. So-called "sensorless" methods most often use the back electromotive force (EMF) generated within a motor to determine the position of the motor's rotor. However, this method has the disadvantage of being unable to provide a position when the motor is stopped or at low speed, since no back EMF is measurable at low speed or when stopped. Furthermore, this method requires observers to estimate this force at all times.

[0004] To overcome these problems, other solutions exist, such as the use of magnetoresistive or tunnel magnetoresistive (TMR) position sensors. These sensors are less expensive and just as accurate as a resolver, but it is still difficult to make them redundant since they are located at the end of the rotor shaft. Currently, this solution requires adding a magnet to the end of the shaft and then placing the sensor directly opposite it. Therefore, it is difficult to make such a system redundant since the location where the sensor can be placed is unique (the other end of the rotor shaft is connected to the system that the motor drives and is therefore unavailable).

[0005] For low speeds where the electromotive force amplitude is too low, methods of injecting high-frequency signals have also been proposed, which assume the presence of a variable reluctance effect within the machine. However, these methods have the disadvantage of only being applicable to certain types of electrical machines.

[0006] A solution that overcomes most of the drawbacks listed above relies on the use of digital Hall effect sensors. A digital Hall effect sensor, also called a binary Hall effect sensor, provides a digital signal that takes only two possible values. Several sensors of this type are distributed around the rotor's axis of rotation. An algorithm estimates a rotor position from the digital signals provided by these different sensors. However, this solution remains unsatisfactory at low speeds. The position determined by the algorithm below is not accurate when the rotor rotates at low speed relative to the stator. SUMMARY

[0007] One problem to be solved is that of accurately detecting a relative position between a rotor and a stator of a multiphase motor, including when the rotor is rotating at low speed relative to the stator.

[0008] This problem is solved by a position detector for a multiphase motor, the detector comprising: a linear Hall effect sensor suitable for generating an analog signal varying continuously as a function of the orientation of a magnetic field rotating with a rotor of the multiphase motor relative to a stator of the multiphase motor; and a neural network configured to determine a relative position between the rotor and the stator from the analog signal.

[0009] The detector, which is a first subject of this disclosure, may also include the optional features below.

[0010] Preferably, the relative position consists of Cartesian coordinates in a plane perpendicular to an axis of rotation of the rotor with respect to the stator.

[0011] Preferably, the neural network is configured to generate the relative position from several values ​​taken successively by the analog signal at different times.

[0012] Preferably, the neural network comprises only one hidden layer.

[0013] Preferably, the detector comprises at least one linear Hall effect sensor additionally, each additional linear Hall effect sensor is unique in generating an additional analog signal that varies continuously depending on the orientation of the magnetic field rotating with the rotor relative to the stator; the neural network is configured to determine the relative position from the analog signal and each additional analog signal.

[0014] Preferably, the detector also includes a post-processing unit configured to smooth a sequence of relative positions between the rotor and the stator of the motor successively generated by the neural network.

[0015] A second subject of this disclosure is a multiphase motor comprising: a stator; coils configured to jointly generate a magnetic field rotating relative to the stator; a rotor suitable for being driven by the magnetic field rotating in rotation relative to the stator; and the detector constituting the first subject of this disclosure.

[0016] Preferably, the linear Hall effect sensor is arranged at least partly inside one of the coils.

[0017] A third object of this disclosure is a method for detecting the relative position between a rotor and a stator of a multiphase motor, the detection method comprising: acquiring, via a linear Hall effect sensor, an analog signal that varies continuously according to the orientation of a magnetic field rotating with the rotor relative to the stator; and determining, via a neural network, the relative position between the rotor and the stator from the analog signal. DESCRIPTION OF FIGURES

[0018] Other features, objectives and advantages of the invention will become apparent from the following description, which is purely illustrative and not limiting, and which should be read in conjunction with the accompanying drawings on which:

[0019] Fig. 1 is a schematic cross-sectional view of a multiphase motor according to one embodiment.

[0020] Fig. 2 is a schematic representation of components of a multiphase motor according to one embodiment.

[0021] Fig. 3 is a schematic representation of a set of position detectors for a multiphase motor, according to a first embodiment.

[0022] Fig. 4 is a schematic representation of a set of position detectors for a multiphase motor, according to a second embodiment.

[0023] The [Fig.5] is a flowchart of steps of a method for detecting a relative position between a rotor and a stator of a multiphase motor, according to one embodiment.

[0024] The [Fig.6] includes a first curve representing the evolution of a detected position, a second curve representing the evolution of an actual position, and a third curve representing a difference between the first curve and the second curve.

[0025] Throughout the figures, similar elements bear identical references.

[0026] DETAILED DESCRIPTION OF AT LEAST ONE EMBODIMENT Multiphase motor#: general architecture

[0027] Figure [1] shows a schematic cross-section of a multiphase motor 1 in a plane (X,Y) defined by two axes X and Y, according to one embodiment.

[0028] The multiphase motor 1 can be installed in an aircraft. In this context, it can serve as a primary or secondary flight control actuator, as a pump actuator (for example, for fuel pumps), or even be used for aircraft propulsion.

[0029] The multiphase motor 1 comprises a stator 2 and a rotor 4 movable in rotation relative to the stator 2 around an axis Z perpendicular to the plane (X, Y).

[0030] The multiphase motor 1 comprises N coils B1 to BN, with N>3. The coils are fixed to the stator 2. In the embodiment illustrated in [Fig.1], we have N=9. In another embodiment, we have N=3 and the motor is then said to be three-phase.

[0031] The N coils are configured to jointly generate a rotating magnetic field relative to the stator 2, from phase signals with respective indices ranging from 1 to N. The rotating magnetic field results from a superposition of N magnetic fields respectively generated by the N coils. In the literature, the phase signals are sometimes more simply called "phases." The phase signals can be electric currents or electric voltages. As is known, the rotating nature of the magnetic field is obtained using periodic phase signals with phases shifted relative to each other.

[0032] The rotor 4 is designed to be driven in rotation relative to the stator 2 by the effect of the rotating magnetic field, so as to generate torque. To this end, the multiphase motor comprises a plurality of magnets 6 fixed to the rotor 4. The magnets 6 are arranged so as to cooperate magnetically with the coils B1 to BN. The magnets 6 have alternating polarities about the axis of rotation Z, in the sense that when traversing the magnets 6 around the axis of rotation Z of the rotor 4, one encounters alternately a magnet having a north pole oriented in a centripetal direction with respect to the axis Z (towards the stator), and a magnet having a south pole oriented in the centripetal direction.

[0033] With reference to [Fig. 2], the multiphase motor 1 also includes N control modules Cl to CN to control the N coils B1 to BN in parallel. Thus, each control module Ci selectively controls the coil Bi of the same index, and is not intended to control the other coils.

[0034] The multiphase motor 1 also includes N source modules indexed from 1 to N. For any i from 1 to N, the source module Si has the function of providing the control module Ci with data which it uses to control the coil Bi.

[0035] Each source module Si includes a coil availability detector Di and a torque sensor CPLi. In [Fig.2], these components are shown for the source module SI, but are also present in each of the other source modules S2 to SN.

[0036] The availability detector Di is configured to detect whether coils B1 to BN are available or unavailable. "Unavailable coil" means a coil Incapable of generating a magnetic field that contributes to the formation of the rotating magnetic field. For example, a coil in "open phase" is an unavailable coil. A coil can also be unavailable when it is short-circuited. The availability detector is capable of performing this detection coil by coil, thus determining, among the N coils, which are available and which are unavailable. The coil availability detector is known from the prior art. By convention, the data produced by the availability detector is called "availability data," this availability data indicating for each coil whether it is available or not.

[0037] The CPLi torque sensor is configured to measure the torque generated by the multiphase motor 1 during the rotation of the rotor 4 relative to the stator 2. The CPLi torque sensor is known from the prior art. This sensor is, for example, a linear Hall effect sensor. Alternatively, the sensor can be an estimator operating from an analytical model.

[0038] Modules and method for detecting a relative position between the rotor and the stator

[0039] Each source module Si also includes a position detection module Pi.

[0040] With reference to [Fig. 3], the position detection module Pi comprises a linear Hall effect sensor Hi. As is known per se, a linear Hall effect sensor, sometimes also called an analog Hall effect sensor in the literature, differs from a binary or digital Hall effect sensor in its ability to acquire an analog signal, and not a digital signal. A digital signal is limited to two values, whereas an analog signal can take on more values, and therefore provides more detailed information.

[0041] The linear Hall effect sensor Hi is positioned in the multiphase motor to specifically acquire an analog signal varying continuously as a function of the orientation of the rotating magnetic field discussed previously, relative to the stator 2. The Hall effect sensor is fixed to the stator 2.

[0042] For example, the analog signal takes a maximum value when the north pole of one of the magnets 6 is facing the linear Hall effect sensor, and a minimum value when the south pole of one of the magnets 6 is facing the Hall effect sensor. The reverse is also possible. During the rotation of the rotating magnetic field, the analog signal will oscillate continuously between the maximum and minimum values, due to the alternating arrangement of the magnets 6 fixed to the rotor 4. This oscillation constitutes a much richer source of information than a simple "tap" acquired by a binary Hall effect sensor, i.e., a simple alternation between two values ​​such as 0 and 1.

[0043] The Pi position detection module further includes an RPi neural network.

[0044] In this text, the term "neural network" refers to a neural network Artificial intelligence implemented by any processor, having been trained to perform a specific task. Thus, when we say that the engine includes a neural network, this implies that the engine includes the hardware necessary to implement this task.

[0045] The RPi neural network is configured to determine a relative position between the rotor 4 and the stator 2 from the analog signal provided by the analog Hall effect sensor Hi.

[0046] To perform this function, the RPi neural network underwent pre-training using training data. For example, this training is supervised, and the engine is instrumented with a resolver that is used as a truth source. The engine is started, the neural network provides a position, which is compared to a reference position provided by the resolver, which is assumed to be reliable. If the position provided by the RPi neural network deviates from a position provided by the resolver (assumed to be reliable), then the weights of the neural network are updated to reduce this deviation, for example, by the backpropagation method. Once the training is complete, the resolver is removed from the engine.

[0047] The RPi neural network preferably comprises a single hidden layer. In this case, the neuron comprises only three layers: an input layer, the hidden layer, and an output layer.

[0048] The hidden layer preferably comprises at least three neurons, for example 10 neurons.

[0049] The hidden layer is preferably fully connected to the input layer, which means that each neuron in the hidden layer will process the analog signal.

[0050] The hidden layer is preferably fully connected to the output layer, meaning that each neuron in the hidden layer is connected to the output layer.

[0051] Furthermore, the RPi neural network preferentially uses the ReLu function as its activation function. The advantage of this ReLu function is that it limits the computational load consumed by the neural network. However, other activation functions can be used, for example, sigmoid or hyperbolic tangent functions.

[0052] The position detector Pi further includes a smoothing unit Li arranged at the output of the RPi neural network. The smoothing unit Li is configured to apply smoothing to data produced by the neural network.

[0053] In practice, the RPi neural network and the Li smoothing unit can take the form of computer programs or parts of the same computer program executed by a processor of any structure. This processor may include one or more cores. For example, the processor is a microcontroller, a DSP, an FPGA, an ASIC, etc.

[0054] The linear Hall effect sensors H1 to HN are arranged around the axis of rotation of the rotor 4. Preferably, for any i from 1 to N, the linear Hall effect sensor with index i is located at least partially inside the coil with index i. In other words, at least one turn of the coil with index i extends around the linear Hall effect sensor with index i. In [Fig. 1], the linear Hall effect sensors H1 to Hn are represented by black rectangles.

[0055] In a decentralized embodiment of the position detectors, represented in [Fig.3], the neural network of index i is connected at the input only to the linear Hall effect sensor of index i.

[0056] However, in other embodiments, an RPi neural network can receive signals from several linear Hall effect sensors among the sensors H1 to HN. Figure 4 thus shows an embodiment in which any RPi neural network receives signals from each of the N sensors H1 to HN. In another embodiment, an RPi neural network can selectively receive signals from K adjacent Hall effect sensors, with 1 <K<N, par exemple K capteurs adjacents autour de l’axe de rotation Z.

[0057] A method for detecting a relative position between the rotor 4 and the stator 2 of the multiphase motor 1, implemented by the source module of index Pi, comprises the following steps.

[0058] It is assumed that the coils B1 to BN have been pre-controlled so as to jointly generate the rotating magnetic field described above, causing the rotor 4 to rotate relative to the stator 2. During this rotation, the orientation of the rotating magnetic field varies, and the magnets 6 move relative to the linear Hall effect sensor Hi.

[0059] In an acquisition step 100, the linear Hall effect sensor Hi acquires the analog signal described above, varying continuously as a function of the orientation of a magnetic field rotating with the rotor 4 relative to the stator 2.

[0060] In a determination step 102, the RPi neural network takes the analog signal as input, and generates on its basis a relative position between the rotor 4 and the stator 2.

[0061] The combination of the linear Hall effect sensor and the neural network makes it possible to accurately detect the relative position between the rotor 4 and the stator 2 of the multiphase motor 1, including when the rotor 4 is rotating at low speed relative to the stator 2.

[0062] Preferably, the relative position consists of Cartesian coordinates in a plane perpendicular to an axis of rotation of the rotor 4 with respect to the stator 2. For example, if working with normalized coordinates, the Cartesian coordinates consist of the cosine and sine of an angle indicating the relative orientation between the rotor 4 and the stator 2 in the plane considered. Such Cartesian coordinates have the advantage of evolving continuously over time, unlike the aforementioned angle which evolves from 0 to 2ir, then returns to 0 once the magnetic field has completed a full rotation around the axis of rotation of the rotor 4. The inventors have observed that this discontinuity in the value of the angle degrades the performance of the neural network, especially when the size of the neural network is limited.In comparison, it is much easier for the neural network to learn to estimate continuously changing coordinates, especially when the network size is limited.

[0063] The RPi neural network can generate the relative position between the rotor 4 and the stator 2 on the basis of a single value taken by the analog signal at a time t.

[0064] Alternatively, the neural network can generate this position based on several values ​​successively taken by the analog signal at different times, therefore not only a value at time t, but also previous values ​​of the signal, acquired at respective earlier times t-1, t-2,... tk and constituting a history of values. This history of values ​​allows the neural network to perceive the dynamics of the rotor 4, enabling it to improve its accuracy.

[0065] Alternatively or in addition, the RPi neural network can determine the relative position between the rotor and the stator on the basis of analog signals respectively provided by several linear Hall effect sensors among the N available, or even for example by the N sensors in the embodiment shown in [Fig.4].

[0066] The preceding steps are repeated over time, so that the RPi neural network is led to generate a succession of relative positions between the rotor 4 and the stator 2.

[0067] This sequence of positions may contain noise. As an example, Figure 6 shows the evolution of the sine of the angle determined by the neural network (top), the actual evolution of this sine of the angle (middle), and the difference between these two evolutions (bottom). The presence of peaks in this difference shows that the evolution of the sine determined by the neural network is subject to occasional noise.

[0068] To eliminate or at least reduce this noise, the smoothing unit Li implements, in step 104, a smoothing of the sequence of positions generated by the neural network. The inventors have found that such smoothing can, in some cases, reduce an amplitude error at a peak from 10% to 1%. For the implementation of the smoothing, the smoothing unit Li can use a moving average or include a A first-order recursive filter is simpler to implement in real time because it is less expensive. In principle, the signal is at the motor's rotation frequency, so it is preferable to filter only the high frequencies using a high-pass filter.

[0069] The position determined by the position detector Pi can advantageously be used by the control module Ci to control the coil Bi. Other embodiments

[0070] In the description above, it was assumed that each neural network used is trained in a supervised manner. This implies that a large amount of data is available. Alternatively, it is possible to train either of the neural networks used with unsupervised methods, such as reinforcement learning, which allows training without training data, but based on a simple model.

Claims

Demands

1. Position detector (Pi) for a multiphase motor (1), the detector (Pi) comprising: • a linear Hall effect sensor (Hi) suitable for generating an analog signal varying continuously as a function of the orientation of a magnetic field rotating with a rotor (4) of the multiphase motor relative to a stator (2) of the multiphase motor, • a neural network (RPi) configured to determine a relative position between the rotor (4) and the stator (2) from the analog signal.

2. Detector according to the preceding claim, wherein the relative position consists of Cartesian coordinates in a plane perpendicular to an axis of rotation of the rotor (4) with respect to the stator (2).

3. Detector according to any one of the preceding claims, wherein the neural network (RPi) is configured to generate the relative position from several values ​​taken successively by the analog signal at different times.

4. Detector according to any one of the preceding claims, wherein the neural network comprises a single hidden layer.

5. Detector according to any one of the preceding claims, further comprising: • at least one additional linear Hall effect sensor, each additional linear Hall effect sensor being capable of generating an additional analog signal varying continuously as a function of the orientation of the magnetic field rotating with the rotor relative to the stator, • the neural network (RPi) being configured to determine the relative position from the analog signal and each additional analog signal.

6. Detector according to any one of the preceding claims, further comprising a post-processing unit (Li) configured to smooth a sequence of relative positions between the rotor and the stator of the motor successively generated by the neural network (RPi).

7. Multiphase motor (1) comprising: • a stator (2), • coils (B 1, ..., BN) configured to jointly generate a magnetic field rotating relative to the stator (2), • a rotor (4) adapted to be driven by the magnetic field rotating in rotation relative to the stator (2), • a detector (Pi) according to any one of the preceding claims for detecting a relative position between the rotor (4) and the stator (2).

8. Multiphase motor (1) according to the preceding claim, wherein the linear Hall effect sensor (Hi) is arranged at least partly inside one of the coils (Bi).

9. Method for detecting a relative position between a rotor and a stator of a multiphase motor, the detection method comprising: • acquiring (100), via a linear hall effect sensor, an analog signal varying continuously as a function of an orientation of a magnetic field rotating with the rotor relative to the stator, • determining (102), via a neural network, the relative position between the rotor and the stator from the analog signal.

Images