Magnetic position sensor system, device and method

Patent metadata

Field	Value
Publication number	US-12596017-B2
Application number	US-202318350262-A
Country	US
Kind code	B2
Filing date	Jul 11, 2023
Priority date	Jul 11, 2022
Publication date	Apr 7, 2026
Grant date	Apr 7, 2026

Abstract

Method of determining a position (f a sensor device movable relative to a magnetic source, or vice versa; the sensor device comprising at least two magnetic sensors; the method comprising the steps of: a) obtaining a plurality of magnetic sensor signals from said magnetic sensors; b) determining or estimating the position of the sensor device based on said plurality of sensor signals or signals derived therefrom; wherein step b) comprises: determining said position (sing an artificial neural network; the artificial neural network being a recurrent neural network trained for determining said position using at most three hundred trainable parameters per degree of freedom. A position sensor system. A position sensor device.

First claim

The invention claimed is:

1 . A method of determining a position of a sensor device,
wherein the sensor device is movable relative to a magnetic source with 1 or 3 mechanical degrees of freedom, or vice versa; the sensor device comprising a semiconductor substrate comprising a plurality of at least two magnetic sensors situated in at least two different locations; the method comprising the steps of: a) obtaining a plurality of sensor signals from said plurality of magnetic sensors; b) determining the position of the sensor device relative to the magnetic source based on said plurality of magnetic sensor signals and/or signals derived therefrom; wherein step b) comprises determining said position using an artificial neural network; wherein the artificial neural network is a recurrent neural network having a predefined number of trainable parameters, which are trained for determining said position; and wherein the number of trainable parameters is at most 300 per mechanical degree of freedom.

2 . The method according to claim 1 , wherein the recurrent neural network is a stateful recurrent network.

3 . The method according to claim 1 , wherein the semiconductor substrate comprises at least three or only three magnetic sensors situated in at least three different locations; or
wherein the semiconductor substrate comprises at least four or only four magnetic sensors situated in at least four different locations; or wherein the semiconductor substrate comprises a two-dimensional array or a two-dimensional arrangement of magnetic sensors.

4 . The method according to claim 1 , wherein the sensor device furthermore comprises a temperature sensor, and
wherein step a) further comprises: measuring a temperature of the semiconductor substrate using said temperature sensor, and providing the measured temperature as an input to the neural network; and wherein step b) comprises: determining the position of the sensor device relative to the magnetic source based on said plurality of magnetic sensor signals and based on the measured temperature signal.

5 . The method according to claim 1 , wherein the neural network is trained for estimating the position using training data obtained from or derived from simulation data provided by computer simulations and/or obtained from or derived from measurement data provided by actual measurements.

6 . The method according to claim 5 , wherein the simulation data and/or the measurement data is interpolated to increase the spatial resolution at least by a factor of 2.

7 . The method according to claim 5 , wherein at least some or all of the actual measurements are performed by physically moving a sensor device relative to a magnetic source, or vice versa.

8 . The method according to claim 5 , wherein at least some or all of the actual measurements are performed by generating a magnetic field using a test device comprising at least one coil, and by causing at least one current to flow through said at least one coil.

9 . The method according to claim 5 , wherein artificial noise is added to the training data; and/or
wherein a magnetic disturbance field is added to the training data; and/or wherein a mounting offset is added to the training data.

10 . The method according to claim 5 , wherein the training data comprises measurement data provided by actual measurements performed on at least 3 different sensor devices;
wherein each of these at least 3 different sensor devices comprise a semiconductor substrate obtained from at least three different semiconductor wafers.

11 . The method according to claim 1 ,
wherein the sensor device is movable relative to the magnetic source or vice versa with only 2 mechanical degrees of freedom, and wherein the training data comprises at least four trajectories for approaching various measurement positions of a measurement range in at least four different directions; or wherein the sensor device is movable relative to the magnetic source or vice versa with only 3 mechanical degrees of freedom, and wherein the training data comprises at least eight trajectories for approaching various measurement positions of a measurement range in at least eight different directions.

12 . The method according to claim 1 , wherein step b) further comprises determining one or more additional signals, in one or more of the following ways: by determining one or more pairwise differences, by determining one or more magnetic field gradients, by determining at least one average signal and by subtracting this average signal from at least two measured signals, by normalizing the signals, by calculating a ratio of two measured signals, by calculating a ratio of two pairwise differences, by calculating a ratio of two gradients, and feeding at least one of these additional signals into the neural network; and
wherein the neural network is trained for estimating the position using training data derived from computer simulations and/or actual measurements and trained with one or more of these additional signals.

13 . The method according to claim 1 , wherein the recurrent neural network comprises at most twelve Gated Recurrent Units (GRU); or
wherein the neural network comprises at most twelve simple RNN units (SRNN); or wherein the neural network comprises at most twelve LSTM units.

14 . A position sensor system comprising:
a magnetic source; a sensor device comprising a semiconductor substrate comprising a plurality of at least two magnetic sensors situated in at least two different locations; a processing circuit configured for performing a method according to claim 1 .

15 . The position sensor system according to claim 14 ,
wherein the sensor device is movable relative to the magnetic source with only 2 mechanical degrees of freedom, and wherein the sensor device comprises 4 to 25 magnetic sensors, and wherein the sensor device or the magnetic source is movable in two directions in a virtual plane or over a virtual surface, and wherein the number of trainable parameters is at most 300.

16 . The position sensor system according to claim 14 ,
wherein the movement of the sensor device relative to the magnetic source is a combination of a translation and a rotation, but the rotation is dependent on the translation.

17 . The position sensor system according to claim 14 , wherein a mean square error (MSE) of the position determined by the artificial neural network is smaller than 2% of the predefined measurement range.

18 . The position sensor system according to claim 14 , wherein the semiconductor substrate comprising the plurality of magnetic sensors has a size of at most 3.0 mm×3.0 mm; and/or
wherein the processing circuit comprises a programmable processor having a 32 bit CPU core and a floating point unit (FPU), configured to run at an internal clock frequency of at most 400 MHz, and comprises at most 2 Mbytes of flash and at most 512 Kbytes of RAM,
wherein the artificial neural network is implemented in software configured to be executed by said programmable processor.

19 . The position sensor system according to claim 14 , wherein the semiconductor substrate contains 4 to 25 horizontal Hall elements; and
wherein all of the magnetic sensor elements are Horizontal Hall elements.

20 . A position sensor device comprising:
a semiconductor substrate comprising at least two magnetic sensors spaced apart from each other, and configured for providing at least two magnetic sensor signals; a processing cir

Assignees

• Melexis Tech Sa

Inventors

• Denis Leon
• Munteanu Adrian
• Khvastunov Illia
• CODDENS Kristof

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G01B7/003

  for measuring position, not involving coordinate determination (coordinate measuring G01B7/004) · CPC title