Method for implementing data-based position sensor of electromagnetic actuating part, fluid valve and fluid system

Abstract

A method for implementing a data-based position sensor 16 of an electromagnetically actuated part 11 is provided. The data-based position sensor 16 comprises a predictive model for the position of the electromagnetic actuating element 14 of the electromagnetic actuating part 11. In the method, a training data set is generated using an electromagnetic actuation component 11, and a prediction model is trained using the training data set. In particular, this makes it possible to determine the position of the valve element 14 of an electromagnetically actuated fluid valve 11 comprising only one electromagnet 13 for actuating the valve element 14, without using a hardware sensor for position measurement.

Description

Technical Field

[0001] The present invention relates to a method for implementing a data-based position sensor for an electromagnetically actuated component, preferably an electromagnetically actuated fluid valve, a method for determining the armature position of an individual electromagnet of a specific electromagnet type, a method for determining the valve element position of an individual electromagnetically actuated fluid valve of a specific fluid valve type, a fluid valve with a data-based position sensor, and a fluid system. Background Art

[0002] The fluid system in the sense of the present invention can be a hydraulic system or a pneumatic system. Therefore, the fluid valve can be configured as a hydraulic valve or a pneumatic valve.

[0003] In fluid systems, such as hydraulics, the parameters pressure and volume flow are crucial for the respective application. Using suitable hardware sensors, pressure in such fluid systems can be detected relatively easily and cost-effectively and processed via corresponding electronic control or regulation units. Hardware sensors for volume flow, on the other hand, are often complex and expensive to implement, which is why they are not an economical option for many applications.

[0004] The volume flow in a fluid system is typically set via a fluid valve. By moving the valve element of such a fluid valve, the opening cross-section of the fluid valve is changed, and a volume flow rate dependent on the opening cross-section is provided through the fluid valve. Therefore, the volume flow through the fluid valve is directly dependent on the position of the valve element. In an electromagnetically actuated fluid valve, which comprises an electromagnet having a coil and an armature for actuating the valve element, movement and, therefore, positioning of the valve element is achieved by energizing the coil with an actuating current, and the resulting movement and positioning of the armature within the coil.

[0005] The opening cross-section of such a fluid valve depends primarily on the current flowing through the electromagnet, allowing the electronic control unit to essentially regulate the volume flow through the fluid valve by controlling the current flowing through the electromagnet. However, the actual opening cross-section of the fluid valve also depends on other parameters, such as hysteresis effects, friction effects, system pressure, or temperature, such as ambient temperature and system temperature. These interfering variables can lead to control errors, which are fundamentally undesirable and must be compensated. For this purpose, independent position sensors are commonly used in the prior art to monitor the position of the valve element and the downstream control circuit. Depending on the measuring principle, existing position sensors have two to three coils for detecting the position of the armature within the coils. This enables the use of a temperature-independent measuring principle, thereby ensuring high temporal and spatial resolution of the position measurement. However, such position sensors are expensive and require additional installation space. Moreover, each additional component in the overall system represents an additional potential source of error.

[0006] DE 10 2022 202 224 B3 discloses a method for determining the armature position of an electromagnet, which makes hardware position sensors or volume flow sensors superfluous for electromagnetically actuated fluid valves having two electromagnets for actuating the fluid valve. Using the method of DE 10 2022 202 224 B3, the unactuated electromagnet of such a fluid valve can be used for position measurement and, correspondingly, for position or volume flow control. It can also be seen from DE 10 2022 202 224 B3 that the method taught therein is only suitable for detecting the end position of a valve element in electromagnetically actuated fluid valves having only a single electromagnet for actuating the fluid valve, since the method is limited to use on the unactuated electromagnet. Summary of the Invention

[0007] Against this background, the object of the present invention is to disclose a possibility for comprehensive monitoring of the position of a valve element of an electromagnetically actuated fluid valve, which comprises only one electromagnet for actuating the valve element, which solution is less expensive than known solutions, takes up less installation space and reduces the risks due to component failures.

[0008] This object is initially achieved by a method for implementing a data-based position sensor for an electromagnetically actuated component. The electromagnetically actuated component comprises an armature and a coil. The data-based position sensor comprises a predictive model for the position of an electromagnetically actuated element of the electromagnetically actuated component. The method according to the invention comprises the following steps:

[0009] - generating a training data set using electromagnetic actuation components; and

[0010] -Train a predictive model using the training dataset.

[0011] The electromagnetic actuation component may be an electromagnet, and the electromagnetic actuation element may be an armature of the electromagnet.

[0012] Alternatively, the electromagnetically actuated component may be an electromagnetically actuated fluid valve, preferably a directly controlled electromagnetically actuated hydraulic valve, wherein the electromagnetically actuated fluid valve comprises a valve element and an electromagnet having an armature and a coil for actuating the valve element, wherein the electromagnetically actuated element is the valve element.

[0013] The predictive model is preferably a software-based machine learning model. By using a training data set to train a software-based predictive model based on a data-based position sensor, the predictive model can be used to accurately determine the position of the electromagnetically actuated element without the use of a hardware sensor. Therefore, by using the data-based position sensor, the position of the armature of the electromagnet can be accurately determined even when the electromagnet is actuated. Therefore, the position of the valve element of an electromagnetically actuated fluid valve can be determined using the actuated electromagnet using the data-based position sensor. This means that even in the case of an electromagnetically actuated fluid valve that uses only a single electromagnet to actuate the valve element, preferably a directly controlled electromagnetically actuated hydraulic valve, the position of the valve element can be accurately determined without the use of a hardware sensor.

[0014] Preferably, the method is configured such that generating a training dataset comprises:

[0015] - performing a test procedure on the electromagnetically actuated component; and

[0016] - During the testing process, the input data to the forecasting model is recorded in the form of time series data.

[0017] The testing process and the recording of input data are preferably performed separately from the expected use of the electromagnetic actuation component, for example, during the production of the electromagnetic actuation component. The recording of input data preferably includes determining and storing relevant input variables for the prediction model using hardware sensors that are typically not available during the expected use of the electromagnetic actuation component. This means that the prediction model can be trained based on the electromagnetic actuation component that is comprehensively measured during the testing process. During the expected use of the electromagnetic actuation component, due to the reduced hardware sensor technology, a data-based position sensor trained in this manner has less data available to determine the position of the electromagnetic actuation element. However, due to the comprehensive basis of the training data set, the data-based position sensor can also use the reduced input data to accurately determine the position of the electromagnetic actuation element during the expected use.

[0018] It is also useful to note that the execution of the test process includes the following steps:

[0019] - generating an actuation current curve in the coil; and

[0020] -Generate a test current curve in the coil.

[0021] The actuation current profile is preferably in the form of an APRBS signal (“Amplitude Modulated Pseudo Random Binary Sequence”). This means that by applying an actuation voltage to the coil, a substantially random actuation current with variable amplitude is generated in the coil in order to control a wide range of possible positions of the electromagnetic actuation element in a random sequence and to measure the corresponding positions of the electromagnetic actuation element.

[0022] A test current curve is generated by applying a test voltage to the coil. The test current curve preferably has a maximum test current within the dithering current range. In other words, the maximum amplitude of the test current curve is preferably within the range of the dithering amplitude. The use of dithering signals is known in the field of continuous valves. There, a rectangular AC voltage signal with a low amplitude (dithering amplitude) is superimposed on the DC actuating voltage to cause the electromagnetic actuating element (e.g., an armature or valve element) to oscillate, thereby avoiding static friction and thus reducing hysteresis effects. The fact that the maximum test current is "within the dithering current range" means that temporary voltage peaks above the dithering amplitude may also occur, but these peaks will not lead to significant movement of the electromagnetic actuating element due to their short duration and the inertia of the entire system. Therefore, the test current curve can have an amplitude that causes a small oscillatory movement of the electromagnetic actuating element, but this small oscillatory movement has no significant effect on the position of the electromagnetic actuating element.

[0023] The test current curve is preferably superimposed on the actuation current curve. Thus, the input data recorded during the test process contains information about the behavior of the test current curve when the electromagnetic actuation component is actuated. The test current curve preferably corresponds to the current curve taught in DE 10 2022 202 224 B3.

[0024] Preferably, the test current curve includes a variable maximum test current that is dependent on the actuation current curve, wherein the variable maximum test current is preferably at least 1% of the current actuation current and preferably at most 10% of the current actuation current. Further preferably, the variable maximum test current is at least 2% of the current actuation current and at most 6% of the current actuation current. Because the test current curve is superimposed on the actuation current curve, it is important to ensure that the test current is not so low as to be lost in the actuation signal. On the other hand, the test current must not be so high as to cause significant actuation of the electromagnetic actuation component. This is achieved by means of specified limit values.

[0025] Preferably, the input data include an actuation current, a test current, a position of the electromagnetic actuation element, a rise time of the generated test current and / or a decay time of the generated test current. The rise time and / or decay time of the test current generally allow conclusions to be drawn about the position of the electromagnetic actuation element. However, due to the superposition of the test current and the actuation current in a single coil, there is no longer a simple analytically solvable relationship. By recording the input data of the prediction model in the form of time series data during the test process and then using it to train the prediction model, the prediction model can identify and store the dynamic characteristics of the underlying process and subsequently use them to predict the position of the electromagnetic actuation element (e.g., a corresponding armature or valve element) based on the reduced input data during the expected use of the electromagnetic actuation component.

[0026] Preferably, the input data also includes coil resistance, maximum actuation current, and / or minimum actuation current. The more input data available for training the prediction model, the more accurate the position sensor's function based on that data. For example, coil resistance can be used for temperature compensation.

[0027] Preferably, the method further comprises the following steps before training the prediction model: cleaning and filtering the training dataset. This allows measurement errors that occurred during the generation of the training dataset to be removed from the training dataset, thereby improving the accuracy of the prediction model.

[0028] Preferably, the prediction model includes an artificial neural network and has the position of the electromagnetic actuator as an output. Preferably, the prediction model is a NARX model (nonlinear autoregressive exogenous model), an ANARX model (additive nonlinear autoregressive exogenous model), an LSTM model (long short-term memory model), an ARIMA model (autoregressive integrated moving average model), a naive Bayes model, or an autoencoder model. These artificial neural network-based machine learning models can be selected based on the data base available for the intended use, the available computing power, and the existing accuracy requirements.

[0029] Furthermore, the object is achieved by a method according to the invention for determining the armature position of an individual electromagnet of a specific electromagnet type, wherein the individual electromagnet comprises an armature and a coil, wherein the method comprises the following steps:

[0030] - implementing a data-based position sensor for an electromagnet of a specific electromagnet type by the above method;

[0031] - embedding data-based position sensors into electronic control units associated with individual electromagnets;

[0032] - generating a test current curve in the coil of a separate electromagnet;

[0033] - obtaining input data for a predictive model based on data from a location sensor; and

[0034] - Determining the position of the armature of the individual electromagnet based on the acquired input data and a predictive model of the position sensor based on the data.

[0035] Preferably, the input data comprises at least the current actuation current, the generated test current and the rise time and / or decay time of the test current.

[0036] Essentially, due to serial production variations, structural deviations exist between each individual electromagnet of the same electromagnet type. Consequently, each individual electromagnet of the same electromagnet type is a unique electromagnet. These manufacturing-related structural deviations or uniquenesses cause the actual behavior of each individual electromagnet of a specific electromagnet type to deviate slightly from the actual behavior of each other individual electromagnet of the same electromagnet type, and therefore deviate from the ideal behavior. However, a data-based position sensor implemented using the above-described method for an individual electromagnet of a specific electromagnet type is able to provide sufficiently accurate results for the armature position of each of the other individual electromagnets of the same electromagnet type. Thus, by implementing a data-based position sensor once for an electromagnet of a specific electromagnet type, the armature position of any other individual electromagnet of the same electromagnet type can be determined with sufficient accuracy.

[0037] Furthermore, the object is achieved by a method according to the invention for determining the position of a valve element of an individually electromagnetically actuated fluid valve of a specific fluid valve type, preferably a specific hydraulic valve type, wherein the individually electromagnetically actuated fluid valve comprises a valve element and an electromagnet having an armature and a coil for actuating the valve element, wherein the method comprises the following steps:

[0038] - implementing a data-based position sensor for an electromagnetically actuated fluid valve of a specific fluid valve type by the above method;

[0039] - embedding data-based position sensors into electronic control units associated with individual solenoid-actuated fluid valves;

[0040] - generating a test current curve in the coil of the electromagnet;

[0041] - obtaining input data for a predictive model based on data from a location sensor; and

[0042] - Determining the position of a valve element of an individual solenoid-actuated fluid valve based on the acquired input data and a predictive model of the position sensor based on the data.

[0043] Preferably, the input data comprises at least the current actuation current, the generated test current and the rise time and / or decay time of the test current.

[0044] Fundamentally, due to manufacturing variations, structural deviations exist between each individual electromagnetically actuated fluid valve of the same fluid valve type. Consequently, each individual electromagnetically actuated fluid valve of the same fluid valve type is a unique fluid valve. These manufacturing-related structural deviations or uniqueness cause the actual behavior of each individual electromagnetically actuated fluid valve of a particular fluid valve type to deviate slightly from the actual behavior, and therefore, the ideal behavior, of each other individual electromagnetically actuated fluid valve of the same fluid valve type. However, a data-based position sensor implemented using the above-described method for an individual electromagnetically actuated fluid valve of a particular fluid valve type is also capable of providing sufficiently accurate valve element position results for other individual electromagnetically actuated fluid valves of the same fluid valve type. Thus, by implementing a data-based position sensor once for an electromagnetically actuated fluid valve of a particular fluid valve type, the position of the valve element of any other individual electromagnetically actuated fluid valve of the same fluid valve type can be determined with sufficient accuracy.

[0045] Furthermore, the object is achieved by an electromagnetically actuated fluid valve of a specific fluid valve type, preferably a directly controlled electromagnetically actuated hydraulic valve, having a valve element, an electromagnet and an integrated electronic control unit, wherein the electromagnet comprises an armature and a coil for actuating the valve element, wherein the integrated electronic control unit comprises a data-based position sensor for the electromagnetically actuated fluid valve of the specific fluid valve type, wherein the data-based position sensor has been implemented by the above-described method.

[0046] Using an electromagnetically actuated fluid valve with an integrated electronic control unit according to the present invention, the position of a valve element of the electromagnetically actuated fluid valve can be accurately determined without the use of hardware sensors. Thus, using the electromagnetically actuated fluid valve according to the present invention, position control of the valve element and / or volumetric flow control of individual electromagnetically actuated fluid valves can be implemented using a data-based position sensor. Because the data-based position sensor is embedded in the integrated electronic control unit, individual electromagnetically actuated fluid valves can be equipped with the data-based position sensor during production. Thus, the electromagnetically actuated fluid valve according to the present invention provides the aforementioned functionality without having to rely on additional hardware sensors, which were previously required.

[0047] Furthermore, the object is achieved by a fluid system, preferably a hydraulic system, according to the invention, comprising a single electromagnetically actuated fluid valve, preferably a single directly controlled electromagnetically actuated hydraulic valve, and an electronic control unit associated with the single electromagnetically actuated fluid valve, wherein the single electromagnetically actuated fluid valve comprises a valve element and an electromagnet having an armature and a coil for actuating the valve element. The electronic control unit comprises a data-based position sensor for determining the position of the valve element, wherein the data-based position sensor has been implemented by the above-described method.

[0048] With the fluid system according to the present invention, the position of the valve element can be accurately determined without the use of hardware sensors. Thus, data-based position sensors can be used in electronic control units to implement position control of the valve element and / or volume flow control of a separate electromagnetically actuated fluid valve.

[0049] Preferably, the electronic control unit is integrated in the individual electromagnetically actuated fluid valve. This means that the individual electromagnetically actuated fluid valve can already be equipped with a data-based position sensor during production. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The present invention will now be explained in more detail with reference to the embodiments shown in the accompanying drawings. These drawings schematically show:

[0051] Figure 1 A fluid system having a directly controlled electromagnetically actuated fluid valve according to an embodiment of the present invention is shown;

[0052] Figure 2 A flow chart showing a method according to the present invention is shown;

[0053] Figure 3 shows an example graph of an actuation current curve;

[0054] Figure 4 An example graph showing a test current curve; and

[0055] Figure 5 An example graph showing an alternative test current curve. DETAILED DESCRIPTION

[0056] Figure 1 A fluid system 10, in this case a hydraulic system, according to an exemplary embodiment of the present invention is shown. Fluid system 10 includes a single electromagnetically actuated fluid valve 11. In this case, fluid valve 11 is a hydraulic valve, more specifically a directly controlled, electromagnetically actuated, proportional 2 / 2-way poppet valve having an electromagnet 13, a valve element 14, and a biasing device 15, which is shown here, by way of example, as a spring element. In a generally known manner, electromagnet 13 includes an armature A and a coil S. By energizing coil S, armature A, which is directly connected to valve element 14 via, for example, an actuating rod, moves and thus actuates fluid valve 11.

[0057] It will be apparent to those skilled in the art of hydraulics that the directly controlled, solenoid-actuated, proportional 2 / 2-way poppet valve described herein is an example of a specific type of solenoid-actuated fluid valve 11. The solenoid-actuated fluid valve 11 may also be any other solenoid-actuated fluid valve, such as a spool valve or an on-off valve. In particular, the solenoid-actuated fluid valve 11 need not include only one electromagnet 13 for actuating the valve element 14. The data-based position sensor 16 described below may also be used with a solenoid-actuated fluid valve 11 having two complementary electromagnets 13, where only one electromagnet is energized to actuate the valve element 14.

[0058] It will also be clear to those skilled in the art of hydraulics that, for the purposes of the present invention, the electromagnetically actuated fluid valve 11 is an example of an electromagnetically actuated component, and the valve element 14 is an example of an electromagnetically actuated element. Similarly, it will be clear that, for the purposes of the present invention, the electromagnet 13 is an example of an electromagnetically actuated component, and the armature A of the electromagnet 13 is an example of an electromagnetically actuated element.

[0059] according to Figure 1 The exemplary fluid system 10 further includes an electronic control unit 12 associated with the electromagnetically actuated fluid valve 11 for energizing the electromagnet 13 to actuate the electromagnetically actuated fluid valve 11. In this embodiment, the electronic control unit 12 is integrated into the electromagnetically actuated fluid valve 11. The electronic control unit 12 includes a data-based position sensor 16.

[0060] Below, refer to Figures 2 to 5 A method for implementing a data-based position sensor 16 for an electromagnetically actuated fluid valve 11 according to the present invention is described.

[0061] In step S1, a training dataset is first generated using an electromagnetically actuated fluid valve of the same fluid valve type as the individual electromagnetically actuated fluid valve 11. The training dataset does not necessarily need to be generated using the individual electromagnetically actuated fluid valve 11 of the fluid system 10 itself. Because the dynamic characteristics of individual fluid valves of the same fluid valve type are sufficiently comparable, any individual fluid valve of the same fluid valve type is sufficient to generate the training dataset.

[0062] To generate a training data set, in step S1 a test process is performed on the electromagnetically actuated fluid valve 11. During the test process, input data for the prediction model of the data-based position sensor 16 are recorded in the form of time series data.

[0063] The test process includes generating an actuation current curve in the coil S of the electromagnet 13 and generating a test current curve in the coil S of the electromagnet 13 .

[0064] Figure 3An exemplary actuation current curve IB is shown as a function of time t. It can be clearly seen here that actuation current curve IB is an APRBS signal, in which each random amplitude jump of current I corresponds to a switching operation, i.e., a position change, of valve element 14. More precisely, each amplitude jump of current I of actuation current curve IB generated in coil S corresponds to a position change of armature A in coil S and, therefore, to a position change of valve element 14, which is directly connected to armature A.

[0065] Figure 4 An exemplary first test current curve IP1 is shown as a function of time t. Figure 4 In the first test current curve IP1, the test current increases to a defined maximum test current IPmax and remains at that maximum test current IPmax. The voltage used to generate test current curve IP1 is then turned off. This allows the test current to decay without the influence of an external voltage. The inductance of coil S varies depending on the distance of armature A within coil S, i.e., the current position of valve element 14. This is why the decay time of the test current varies even without the influence of an external voltage. Figure 4 An example of a first decay time T1 and a second decay time T2 is shown, each decay time representing the time required for the test current to fall from its defined maximum value IPmax to a defined minimum value IPmin. The longer second decay time T2 ( Figure 4 The dotted curve in the figure corresponds to the case where the armature A is located further inside the coil S, i.e. the inductance of the coil S is higher than the shorter decay time T1 ( Figure 4 The position of the valve element 14 in the electromagnetically actuated fluid valve 11 can be derived from this relationship.

[0066] Figure 5 An alternative second test current curve IP2 is shown, which also alternates between a defined maximum test current IPmax and a defined minimum test current IPmin. Figure 5 In the second test current curve IP2, the test current is not maintained at its maximum value IPmax, but when the maximum test current IPmax is reached, the voltage of the coil S is directly turned off. Figure 4 Another difference between the first test current curve IP1 and the Figure 5 In the second test current curve IP2, the test current does not increase in a rapid manner to reach the maximum test current IPmax. On the contrary, in the second test current curve IP2, the rise time of the test current also depends on the position of the armature A in the coil S. Figure 5 The two exemplary curves shown in FIG. 3 produce a shorter first rise time T3 ( Figure 5 The solid curve in the figure) and the longer second rise time T4 ( Figure 5 The dashed curve in ). Figure 4 Similarly, there is a shorter third decay time T5 and a longer fourth decay time T6. The rise time and decay time of the test current are a measure of the position of the armature A within the coil S and the position of the valve element 14 in the electromagnetically actuated fluid valve 11.

[0067] Therefore, during step S1, the test current curves IP1 and IP2 are superimposed on the actuation current curve IB. The maximum test current IPmax and the minimum test current IPmin are variable and depend on the currently generated (current) actuation current. Preferably, the maximum test current IPmax and the minimum test current IPmin are in the range of 1% to 10% of the current actuation current, more preferably in the range of 2% to 6% of the current actuation current. Preferably, the maximum test current IPmax is in the range of the dithering current of the electromagnetically actuated fluid valve 11. On the one hand, this ensures that the test current is large enough not to disappear in the actuation current signal, i.e., the test current can still be detected. On the other hand, it also ensures that the test current is low enough not to cause any significant actuation of the armature A or the valve element 14, so that the volume flow through the electromagnetically actuated fluid valve 11 is not significantly affected, as is well known when using a dithering signal.

[0068] exist Figure 3 In the embodiment of the present invention, each step of the actuation current curve IB corresponds to a switching position of the valve element 14 in the electromagnetically actuated fluid valve 11. During the test process, the frequencies of the corresponding test current curves IP1, IP2 and the actuation current curve IB must be matched to each other so that at least one cycle of the test current curves IP1, IP2 runs during one switching position of the electromagnetically actuated fluid valve 11 under the actuation current curve IB.

[0069] During the described test process, all available data was recorded as time-series data so that it could be used as input data for a data-based predictive model for position sensor 16. Specifically, the input data included actuation current IB, test currents IP1, IP2, the position of armature A and / or valve element 14, and the decay times of test currents T1, T2, T5, and T6. If a second test current curve IP2 was used, the rise times T3 and T4 of the test currents were also recorded. Furthermore, the coil resistance, maximum actuation current, minimum actuation current, the voltage applied to generate actuation current curve IB, and the voltage applied to generate test current curves IP1 and IP2 were also recorded as time-series data during the test process so that they could subsequently be used as input data for the predictive model.

[0070] During the testing process, hardware sensors are used to accurately record the position of the armature A and / or valve element 14. This provides a well-founded training data set for the predictive model of the data-based position sensor 16 so that it can later be used as an accurate position sensor for the electromagnetically actuated fluid valve 11.

[0071] In optional step S2 , after the training dataset has been created in step S1 , the training dataset may be filtered and / or cleaned in order to remove measurement errors that may have occurred during the testing process.

[0072] Then, in step S3, the recorded training data set is used to train a prediction model for the data-based position sensor 16. The prediction model preferably comprises an artificial neural network in the form of a NARX model (non-linear autoregressive exogenous model) or an ANARX model (additive non-linear autoregressive exogenous model), which has as its output the position of the armature A or the valve element 14, respectively.

[0073] After step S3 is completed, the execution of the data-based position sensor 16 is completed.

[0074] In step S4, the data-based position sensor 16 is now embedded in the electronic control unit 12, which is associated with the electromagnetically actuated fluid valve 11. In the present case, the electronic control unit 12 is integrated into the electromagnetically actuated fluid valve 11, so that the electronic control unit 12 and the electromagnetically actuated fluid valve 11 form a structural unit. Alternatively, however, the fluid system 10 can also include a central electronic control unit that is respectively associated with the electromagnetically actuated fluid valve 11 or is configured to control the electromagnetically actuated fluid valve 11.

[0075] Finally, in step S5, the data-based position sensor 16 is used to determine the position of the valve element 14 of the electromagnetically actuated fluid valve 11. To this end, when the electromagnetically actuated fluid valve 11 is in its intended use in the fluid system 10, the electronic control unit 12 generates test current profiles IP1 and IP2 in the coil S of the electromagnet 13 based on the current actuation current of the electromagnetically actuated fluid valve 11. The test current generation process by the electronic control unit 12 and the current actuation current are provided as input data to the data-based position sensor 16, which then outputs the current position of the valve element 14.

[0076] Furthermore, in step S5 , the control unit 12 may use the position of the valve element 14 determined by the data-based position sensor 16 to implement path control of the valve element 14 and / or volume flow control of the volume flow through the electromagnetically actuated fluid valve 11 , as required.

[0077] Finally, in optional step S6, the data-based position sensor 16 can be updated or fine-tuned. To this end, steps S1 to S4 can be repeated, for example, using a single electromagnetically actuated fluid valve 11 as part of a testing process tailored to the actual application environment of the single electromagnetically actuated fluid valve 11 in the fluid system 10, in order to obtain a particularly accurate training data set for the data-based position sensor 16. Reference numeral 10: fluid system / hydraulic system; 11: electromagnetically actuated fluid valve (electromagnetic actuated component); 12 control units 13 Electromagnet (electromagnetic actuation component) 14 valve element (electromagnetic actuator) 15 Biasing device / spring element 16 Data-based position sensors A Armature (electromagnetic actuator) I Current IB actuation current curve IP1 first test current curve IP2 second test current curve IPmax maximum test current IPmin minimum test current S coil t time T1 first decay time T2 second decay time T3 first rise time T4 second rise time T5 third decay time T6 fourth decay time

Claims

1. A method for implementing a data-based position sensor (16) of an electromagnetically actuated component (11, 13), wherein the electromagnetically actuated component (11, 13) comprises an armature (A) and a coil (S), wherein the data-based position sensor (16) comprises a predictive model for the position of an electromagnetically actuated element (14, A) of the electromagnetically actuated component (11, 13), the method comprising the following steps: - generating a training data set using said electromagnetic actuation means (11, 13); as well as - training the prediction model using the training dataset.

2. The method according to claim 1, It is characterized by Generating the training data set includes: - performing a testing process on the electromagnetic actuation component (11, 13); and - During the testing process, recording input data of the prediction model in the form of time series data.

3. The method according to claim 2, It is characterized by The test process includes the following steps: - generating an actuation current curve (IB) in said coil (S); and - Generating a test current curve (IP1, IP2) in said coil (S).

4. The method according to claim 3, It is characterized by The test current curve (IP1, IP2) comprises a variable maximum test current (IPmax) according to the actuation current curve (IB), wherein the variable maximum test current (IPmax) is preferably at least 1%, more preferably at least 2%, of the current actuation current, and preferably at most 10%, more preferably at most 6% of the current actuation current.

5. The method according to any one of claims 2 to 4, It is characterized by The input data includes an actuation current, a test current, a position of the electromagnetic actuation element (14, A), a rise time (T3, T4) of the generated test current and / or a decay time (T1, T2, T5, T6) of the generated test current.

6. The method according to any one of claims 2 to 5, It is characterized by The input data includes coil resistance, maximum actuation current and / or minimum actuation current.

7. The method according to any one of the preceding claims, It is characterized by The prediction model comprises an artificial neural network and has as its output the position of the electromagnetic actuating element (14, A).

8. The method according to any one of the preceding claims, It is characterized by The electromagnetic actuating component is an electromagnet (13), and the electromagnetic actuating element is the armature (A).

9. The method according to any one of claims 1 to 7, It is characterized by The electromagnetic actuation component is an electromagnetically actuated fluid valve (11), preferably a directly controlled electromagnetically actuated hydraulic valve, wherein the electromagnetically actuated fluid valve (11) comprises a valve element (14) and an electromagnet (13) having the armature (A) and the coil (S) for actuating the valve element (14), wherein the electromagnetic actuation element is the valve element (14).

10. A method for determining the position of an armature (A) of an individual electromagnet (13) of a specific electromagnet type, wherein the individual electromagnet (13) comprises the armature (A) and a coil (S), wherein the method comprises the following steps: - implementing a data-based position sensor (16) of the electromagnet (13) for a specific electromagnet type by means of the method according to claim 8; - embedding the data-based position sensor (16) in the electronic control unit (12) associated with the individual electromagnet (13); - generating a test current curve (IP1, IP2) in the coil (S) of the individual electromagnet (13); - obtaining input data for the prediction model of the data-based position sensor (16); as well as - determining the position of the armature (A) of the individual electromagnet (13) based on the acquired input data and the predictive model of the data-based position sensor (16).

11. A method for determining the position of a valve element (14) of an individually electromagnetically actuated fluid valve (11) of a specific fluid valve type, preferably a specific hydraulic valve type, wherein the individually electromagnetically actuated fluid valve (11) comprises the valve element (14) and an electromagnet (13) having an armature (A) and a coil (S) for actuating the valve element (14), wherein the method comprises the following steps: - implementing a data-based position sensor (16) of the electromagnetically actuated fluid valve (11) for a specific fluid valve type by the method according to claim 9; - embedding the data-based position sensor (16) in an electronic control unit (12) associated with the individual electromagnetically actuated fluid valves (11); - generating a test current curve (IP1, IP2) in the coil (S) of the electromagnet (13); - obtaining input data for the prediction model of the data-based position sensor (16); as well as - determining the position of the valve element (14) of the individual solenoid-actuated fluid valve (11) based on the acquired input data and the predictive model of the data-based position sensor (16).

12. An electromagnetically actuated fluid valve (11) of a specific fluid valve type, preferably a directly controlled electromagnetically actuated hydraulic valve, having a valve element (14), an electromagnet (13) and an integrated electronic control unit (12), wherein the electromagnet comprises an armature (A) and a coil (S) for actuating the valve element (14), wherein the integrated electronic control unit (12) comprises a data-based position sensor (16) for the electromagnetically actuated fluid valve (11) of the specific fluid valve type, wherein the data-based position sensor (16) has been implemented by the method according to claim 9.

13. A fluid system (10), preferably a hydraulic system, having a single electromagnetically actuated fluid valve (11), preferably a single directly controlled electromagnetically actuated hydraulic valve, and an electronic control unit (12) associated with the single electromagnetically actuated fluid valve (11), wherein the single electromagnetically actuated fluid valve (11) comprises a valve element (14) and an electromagnet (13) having an armature (A) and a coil (S) for actuating the valve element (14), wherein the electronic control unit (12) comprises a data-based position sensor (16) for determining the position of the valve element (14), wherein the data-based position sensor (16) has been implemented by the method according to claim 9.

14. Fluid system (10) according to claim 13, It is characterized by The electronic control unit (12) is integrated into the individual electromagnetically actuated fluid valve (11).

Images