Method for operating a sensor

Abstract

A method is for operating a sensor. Influences on the sensor are detected and compensated for by an artificial neural network (ANN). The influences on the sensor are described by information from surroundings of the sensor, and an output signal of the sensor is linked in the ANN to further data representing the information from the surroundings of the sensor, such that a compensated output signal is obtained.

Claims

1. A method for operating a sensor included in a device, comprising: detecting and compensating for influences on the sensor using an artificial neural network (ANN); describing the influences on the sensor based on information from surroundings of the sensor; linking an output signal of the sensor in the ANN to further data representing the information from the surroundings of the sensor, such that a compensated output signal is obtained; and operating the device based on the compensated output signal.

2. The method according to claim 1, wherein the information from the surroundings of the sensor, which information is represented by the further data, is linked by mathematical methods.

3. The method according to claim 1, wherein the information from the surroundings of the sensor, which information is represented by the further data, is linked to a past time period by mathematical methods.

4. The method according to claim 2, wherein the mathematical methods include at least one of a derivation, higher-order derivatives, signal filtering, and window integrals having different window lengths.

5. The method according to claim 1, wherein the output signal of the sensor is split into a plurality of signals before the linking.

6. The method according to claim 1, wherein the further data relating to information from the surroundings of the sensor are provided via the Internet of Things.

7. The method according to claim 1, wherein information relating to historical information is taken into account.

8. The method according to claim 1, wherein the sensor includes a MEMS sensor.

9. An arrangement for operating a sensor, wherein the arrangement is configured to carry out the method according to claim 1.

10. The arrangement according to claim 9, wherein the arrangement includes the ANN.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG. 1 shows a module for processing information within the scope of the proposed method.

[0021] FIG. 2 is a schematic representation of a design of the overall structure.

[0022] FIG. 3 shows a motor vehicle having an arrangement for carrying out the proposed method.

EMBODIMENTS OF THE INVENTION

[0023] The invention is represented schematically in the drawings on the basis of embodiments and is described below with reference to the drawings.

[0024] FIG. 1 shows a module 10 for processing information, as can be carried out within the scope of the proposed method. In this case, an input 12 for the module 10 is an item of information I or a course of said item of information I.

[0025] The item of information I is any variable that changes over time. The item of information can relate, for example, to the operating voltage, the housing temperature, the ambient temperature, the power consumption of the module or the device, and output variables of other sensors. The items of information I are processed in the module 10 in such a way that a reference to history is created and compaction is achieved. t.sub.0 is the current time and t.sub.x is in the past.

[0026] Output variables are:

I.sub.1 14 by calculating the difference (ΔI (t.sub.0, t.sub.x)) between the current I at the time t.sub.0 and at the time t.sub.x,
I.sub.2 16 by forming a window integral with length t.sub.1,
I.sub.3 18 by applying a low-pass filter with cutoff frequency f.sub.Grenz and order,
I.sub.4 20 by applying a high-pass filter with cutoff frequency f.sub.Grenz and order, and

I.SUB.n .22.

[0027] Any desired methods from signal processing can be used here. It is important that each output I.sub.1, . . . I.sub.n contains one item of information. The parameters of the methods used, such as f.sub.Grenz, order, selection t.sub.x, depend on the application and need to be determined. The determination can, for example, also be done using AI structures (AI: artificial intelligence) that perform parameter optimization.

[0028] FIG. 2 is a schematic representation of the design of the overall structure of an arrangement, which is denoted as a whole by the reference numeral 50. The representation shows a first module 52 and a second module 54 as well as an artificial neural network (ANN) 56. These modules 52, 54 correspond to the module 10 from FIG. 1.

[0029] Input variables are an output signal S 60 of a sensor and a signal I 62, which carries data representing further information. The signal S 60 is split into signals S.sub.1 70 to S.sub.n 72, for example according to the information preparation according to FIG. 1. The signal I 62 is also split into signals I.sub.1 80 to I.sub.n 82. The ANN, which records and evaluates the different signals, outputs a compensated output signal 86, i.e. the influences on the output signal S 60 have been taken into account or compensated for in the compensated output signal.

[0030] When splitting the output signal S 60, it should be noted that it is important to use properties from the past to predict the future. There are several options for this, such as mean value, window integral, filter, etc. There is currently no specification for this. Effects which are addressed therewith are, for example in MEMS acceleration sensors, e.g. the fading of mechanical shocks.

[0031] The proposed method thus links the output signal S 60 of a sensor to additional items of information I 62, which are provided, for example, by further sensors and thus by other structures. It is also conceivable for the sensor to be enhanced such that additional elements therein generate this information.

[0032] The type and quantity of information required to achieve an improvement depends, in particular, on the specific application.

[0033] The items of information I 62 can still be linked to the “past” by means of mathematical methods. These mathematical methods include, in addition to derivation, higher-order derivatives, signal filtering, and window integrals having different window lengths. This function is implemented, for example, by the modules 52 and 54.

[0034] These signal processing methods offer the ANN 56 a large quantity of information which has an influence on the output signal S 60. One possible form of information processing is shown by way of example in FIG. 1.

[0035] During development of the sensors, the optimum information is selected and offered to the ANN for the purpose of training. Known methods can be used to train the ANN.

[0036] FIG. 3 shows a motor vehicle 100 in which an embodiment of the arrangement for carrying out the method is provided, which arrangement is denoted as a whole by the reference numeral 102. In the motor vehicle 100, in addition to the arrangement 102, a sensor 104 is shown which supplies an output signal 106 which is to be processed accordingly such that a signal which is as free of errors as possible is obtained. To this end, further data 110 are acquired via further sensors 108, which further data relate to information, in particular information relating to typically technical variables from the surroundings of the sensor 104. These variables, for example the temperature, have an influence on the sensor 104 or on the functioning thereof and thus also on the output signal 106 delivered.

[0037] An artificial neural network 112 is provided in the arrangement 102 and links the output signal 106 of the sensor 104 to the further data 110 of the further sensors 108 and, in this way, can compensate for the influence of said data 110 on the output signal 106. A compensated output signal 114 can then be output.