Method for determining torque

Abstract

The present invention relates to a method for determining a torque (T) of a drivetrain (1) by means of a mathematical model (9). The method may include taking in input data (E). The input data (E) may include a voltage (U) measured using a torque sensor (5). The input data (E) may also include at least one signal value (Ω, Ψ, I) of a motor controller (4). Furthermore, the method may include determining the torque (T) by means of the mathematical model (9) based on the voltage (U) and the at least one signal value (Ω, Ψ, I). The present invention also relates to a machine learning model for determining the torque (T) of a drivetrain (1).

Description

Technical Field

[0001] The present invention generally relates to the technical field of methods for determining the torque of a driven device, particularly a drive train.

Background Art

[0002] Methods for determining torque have many applications in the field of drive technology. For example, the torque of a drive train is measured or determined by calculation in order to improve the driving behavior of a vehicle for passenger transportation. A drive train typically comprises a motor having a motor shaft, a motor controller, a torque sensor having a microcontroller, and a transmission having an output shaft. The term "torque" in the context of the present invention is understood by those skilled in the art to refer to the torque applied to the output shaft of the drive train. In addition to the field of automotive engineering, torque is also an important parameter in the field of robotics. Industrial robots often require high torque, particularly to move the joints of a multi-element manipulator with sufficient force.

[0003] Methods known to date for determining the torque of a drive train typically consist of attaching a torque sensor to the output shaft of the drive train. Such torque sensors are generally formed by attaching strain gauges to components of the transmission, particularly an elastic transmission element having external teeth, and determining the torque based on input data, which is measured by the strain gauges. Such methods are described, for example, in the following scientific publications.

[0004] Hashimoto, Minoru, Yoshihide Kiyosawa, and Richard P. Paul. “A torque sensing technique for robots with harmonic drives.” IEEE Transactions on Robotics and Automation 9.1 (1993): 108 - 116.

[0005] Hashimoto, Minoru, and Yoshihide Kiyosawa. “Experimental study on torque control using Harmonic Drive built-in torque sensors.” Journal of Robotic Systems 15.8 (1998): 435-445.

[0006] Other known methods for determining torque are based on mathematical formulas derived from the physical behavior of the drivetrain. Such a method for determining torque is disclosed, for example, in German Patent Application Publication No. 19963279(B4), entitled "Method for determining a output torque of a drive device and drive device." Here, the output torque is derived by a mathematical formula using the lubrication oil temperature of the transmission device, the rotational speed of the motor, and the output torque of the motor as input data. The use of a torque sensor is not intended here.

[0007] While the above approach allows the torque of the drivetrain to be determined at least as a rough approximation, there are various interfering variables acting on the drivetrain, such as inertial and temperature effects, which are not explained by known methods and lead to inaccurate torque determination. [Overview of the project] [Problems that the invention aims to solve]

[0008] Therefore, an object of the present invention is to provide an improved method for determining the torque of a drive train, thereby overcoming, at least partially, the aforementioned drawbacks of the prior art. A further object of the present invention is to provide an improved mathematical model for determining torque. [Means for solving the problem]

[0009] These objectives are achieved by the features of the independent claims. In its most common form, the present invention relates to a method for determining the torque of a driven device, particularly a drive train. In this regard, the method may include the acquisition of input data. The input data may include a voltage measured using a torque sensor. The input data may also include at least one signal value of a motor controller. Furthermore, the method may include determining the torque by a mathematical model based on the voltage and at least one signal value.

[0010] The drive train is preferably part of a vehicle or robot and may comprise a motor having a motor shaft, a motor controller, a torque sensor having a microcontroller, and a transmission device having an output shaft. The motor may be an internal combustion engine, an electric motor, a fuel cell, a hybrid drive system, or another type of energy converter.

[0011] Here, the torque of a drivetrain is understood to be the torque available to drive a vehicle, robot, or the manipulator elements of a robot. The term "torque" is understood by those skilled in the art to refer to the torque applied to the output shaft of a drivetrain. Thus, the torque of a drivetrain is the output torque of the transmission. For example, the torque of a drivetrain can be transmitted directly to the wheels of a vehicle.

[0012] "Determination of torque by mathematical modeling" is typically understood by those skilled in the art as any kind of verification and / or calculation in a mathematical sense. For this purpose, any type of mathematical operation, in particular iterative methods or methods for solving differential equations, can be used. Readings from a table can also be applied to determine the torque.

[0013] Some or all of the method steps can be performed by (or using) a hardware device such as a microcontroller for the torque sensor. The hardware device may also include a processor, microprocessor, programmable computer, or electronic circuitry. In some exemplary embodiments, one or more of the key method steps can be performed by such a device.

[0014] Naturally, the method can be fully automated. As is common in the field of motor technology, it is also possible to execute the method continuously in real time.

[0015] Typically, a person skilled in the art would understand that the input data is data that is made available for a mathematical model to determine torque.

[0016] Motor controllers are typically used for open-loop and / or closed-loop control of motors. In this regard, motor controllers can read, measure, and / or store all signal values ​​related to the motor. Motor controllers may have means for reading, measuring, and / or storing signal values. Signal values ​​can be electrical signals such as voltage and / or current. Signal values ​​can also be pressure, temperature, rotational speed, acceleration, and / or velocity. Depending on the application, motor controllers may have corresponding access to sensors such as temperature sensors and / or pressure sensors, or they may be able to transmit signal values ​​from sensors to the motor controller. It is also possible for a motor controller to measure multiple signal values ​​simultaneously and transmit them to other components of the drivetrain.

[0017] A motor controller can also be configured to control the motor and / or other components of the device being driven. In this regard, a motor controller can, for example, control the speed of a vehicle. This type of closed-loop control can be implemented here using a control loop, which is carried out as an algorithm.

[0018] The torque sensor preferably incorporates a microcontroller. In this regard, the mathematical model or at least a part of the mathematical model can be implemented on the microcontroller.

[0019] The transmission device or gear used may be a spur gear, bevel gear, helical gear, planetary gear, or harmonic drive transmission device.

[0020] The method according to the present invention advantageously provides an improvement to the measurement method performed by the torque sensor. In addition to the voltage measured by the torque sensor, additional data from the motor controller can be made available to the method to more accurately determine the torque of the drivetrain. Furthermore, the method according to the present invention has the advantage that input data from various components of the drivetrain, particularly the motor controller and the torque sensor, can be made available to the mathematical model simultaneously. In other words, measured signal values ​​from different sensors can be merged (multi-sensor fusion) and further processed by the mathematical model.

[0021] In a further aspect of the present invention, at least one signal value of the motor controller includes the motor position and / or direction of rotation. In this regard, the motor position refers to the rotation angle of the motor shaft extending from the motor. For example, the motor shaft may initially have a rotation angle of about 0°. After half a rotation of the motor, the rotation angle is essentially 180°. In this regard, the direction of rotation refers to the direction of rotation of the motor shaft. The direction of rotation may be clockwise or counterclockwise. The motor position and direction of rotation have the advantage that they are preferably available as data stored in the motor controller or measured by the motor controller.

[0022] In a further embodiment, the input data includes temperature. In this regard, the temperature may be the lubricating oil temperature of the transmission or the temperature measured within the motor. Advantageously, the method can thereby detect any temperature effects that may be acting on the torque of the drivetrain.

[0023] In further embodiments, the mathematical model includes a finite element model. The finite element model has the advantage that it can represent any complex geometric shape of the drive train and its physical behavior based on differential equations and continuum theory. Nonlinearities relating to the material and / or geometric shape can also be easily represented.

[0024] In a further aspect, mathematical models include machine learning models. In this regard, machine learning models may be, in particular, artificial neural networks.

[0025] An artificial neural network (ANN) is a system inspired by biological neural networks, such as those found in the retina or brain. An ANN consists of multiple interconnected nodes and multiple connections between nodes, known as edges. Typically, there are three types of nodes: input nodes that receive input values, hidden nodes that are connected (only) to other nodes, and output nodes that provide output values. All nodes can represent artificial neurons. All edges can transmit information from one node to another. The output of a node can be defined as a (nonlinear) function of its inputs (e.g., the sum of its inputs). The inputs of a node can be used in a function based on the "weights" of the edges or nodes that provide the inputs. The weights of nodes and / or edges can be adjusted as part of the learning process. In other words, training an artificial neural network can involve adjusting the weights of the nodes and / or edges of the artificial neural network, i.e., achieving a desired output for a particular input.

[0026] Alternatively, the machine learning model can be a support vector machine, a random forest model, or a gradient boosting model. A support vector machine (i.e., support vector network) is a supervised learning model with an associated learning algorithm that can be used to analyze data (e.g., in classification or regression analysis). A support vector machine can be trained by providing a plurality of training input values belonging to one of two categories as input. The support vector machine can be trained to assign new input values to one of two categories. Alternatively, the machine learning model can be a Bayesian network, which is a probabilistic directed acyclic graphical model. A Bayesian network can use a directed acyclic graph to represent a set of probabilistic variables and their conditional dependencies. Alternatively, the machine learning model can be based on a genetic algorithm, which is a search algorithm and heuristic technique that mimics the process of natural selection.

[0027] In a further aspect, the machine learning model is trained using at least one training data set. The at least one training data set can include a voltage measured using a torque sensor, at least one signal value of a motor controller, and a reference torque.

[0028] The training data set can be created, for example, on a test bench. In this regard, the voltage measured using a torque sensor, at least one signal value of a motor controller, and the reference torque are measured on the test bench in various operating states of the drive train.

[0029] For example, supervised learning can be used as a learning method for a machine learning model. In supervised learning, the machine learning model is trained using a plurality of training sample values, and each sample value can include a plurality of input data values and a plurality of desired output values, that is, each training sample value is associated with a desired output value. By specifying both the training sample value and the desired output value (here, the above-mentioned reference torque), based on the input sample values similar to the sample values provided as part of the training, the machine learning model "learns" which output value should be provided. In addition to supervised learning, semi-supervised learning can also be used. In semi-supervised learning, some of the training sample values lack the desired output values. Supervised learning can be based on a supervised learning algorithm (for example, a classification algorithm, a regression algorithm, or a similarity learning algorithm). The classification algorithm can be used when the output is restricted to a set of limited values (categorical variables), that is, when the input is classified as one of a set of limited values. The regression algorithm can be used when the output indicates any numerical value (within a range). The similarity learning algorithm can be similar to both the classification algorithm and the regression algorithm, but is based on learning from samples using a similarity function that measures how similar or related two objects are. In addition to supervised learning or semi-supervised learning, unsupervised learning can be used to train the machine learning model. In unsupervised learning, only the input data may be provided, and an unsupervised learning algorithm can be used to find the structure within the input data (for example, by grouping or clustering the input data and finding commonalities within the data). Clustering is to assign the input data including a plurality of input values to subsets (clusters) such that the input values within the same cluster are similar according to one or more (predetermined) similarity criteria, but are not similar to the input values included in other clusters.

[0030] In a further embodiment, the mathematical model is implemented on the microcontroller of the torque sensor. One advantage of this embodiment is that determining the torque by the mathematical model can be done entirely on the microcontroller, and no additional components are required to implement the mathematical model.

[0031] In a further embodiment, the torque determined by a mathematical model is transmitted to a control loop. In this regard, the control loop can be provided to control the motor current and / or speed. Advantageously, closed-loop control based on the control loop can thus be improved.

[0032] In a further embodiment, the validation method has further method steps. In this regard, in the further step, the estimated torque can be confirmed based on the motor current. Furthermore, the upper and / or lower torque limits can be confirmed based on the estimated torque. Subsequently, the torque determined by the mathematical model can be evaluated based on the upper and / or lower torque limits. Here, the motor current can be read out as a signal value by the motor controller.

[0033] The estimated torque can be confirmed using, for example, the following formula, and the torque constant and the transmission ratio of the transmission device have been confirmed in advance by the motor controller.

[0034] Estimated torque = Motor current * Torque constant * Transmission ratio of the transmission device

[0035] The evaluation of torque determined by a mathematical model can be checked, for example, by the following conditions:

[0036] Estimated torque -Δ < Torque determined by mathematical model < Estimated torque +Δ

[0037] Here, Δ is a calibration parameter that takes into account the current accuracy level of the estimated torque. The parameter Δ is predefined and can be stored in the torque sensor's microcontroller. As long as the torque determined by the mathematical model is within the range of "estimated torque (current-based) ± Δ", it is possible to evaluate whether the torque determined by the mathematical model is valid. If the torque determined by the mathematical model is outside the range, an "error" state is output as the diagnostic state or status.

[0038] In a further embodiment, an apparatus is provided for data processing, in particular a microcontroller for a torque sensor, which includes means for performing one of the methods described herein.

[0039] A device for data processing may include a storage medium (or data carrier or computer-readable medium) that stores a computer program for performing one of the methods described herein when executed by a processor. The data carrier, digital storage medium, or recording medium is typically tangible and / or non-transient. A further exemplary embodiment of the present invention is a device described herein comprising a processor and a storage medium.

[0040] In a further embodiment, the present invention provides a computer program including a command, the command causing the computer to perform one of the methods described herein when the program is executed by the computer.

[0041] The present invention also provides a machine learning model for determining the torque of a drive train. In this regard, the machine learning model may have input means for receiving a voltage measured using a torque sensor and at least one signal value of a motor controller. Furthermore, the machine learning model may have means for determining the torque based on the voltage and at least one signal value.

[0042] A machine learning model can refer to algorithms and statistical models that a computer system can use to perform a particular task without using explicit instructions, rather than relying on models and inference. In machine learning, for example, instead of rule-based data transformations, data transformations that can be derived from the analysis of historical data and / or training data can be used. For example, the physical behavior of a drive train can be analyzed using a machine learning model or a machine learning algorithm. To enable a machine learning model to analyze the physical behavior of a drive train, the machine learning model can be trained using a training dataset as input and training content information as output. By training a machine learning model with a large number of training datasets and / or training sequences (e.g., signal values) and associated training content information (e.g., labels or annotations), the machine learning model "learns" to recognize the physical behavior of a drive train so that it can be used to predict physical behavior not included in the training data. The same principle can be used for other types of sensor data. By training a machine learning model with training sensor data and a desired output, the machine learning model "learns" a transformation between sensor data and output, which can then be used to provide an output based on untrained sensor data provided to the machine learning model. The provided data (e.g., sensor data and / or metadata) can be preprocessed to obtain feature vectors, which are then used as input to a machine learning model.

[0043] In further embodiments, the present invention provides a training dataset for training a machine learning model. In this regard, at least one training dataset may include a voltage measured using a torque sensor, at least one signal value from a motor controller, and a reference torque.

[0044] Preferred embodiments of this disclosure are described below with reference to the following figures. [Brief explanation of the drawing]

[0045] [Figure 1] This shows a drive train 1 according to an embodiment of the present invention. [Figure 2] This document outlines the method according to embodiments of the present invention. [Figure 3A] A mathematical model 9 according to an embodiment of the present invention is shown. [Figure 3B] The motor controller 4 and torque sensor 5 according to embodiments of the present invention are shown. [Figure 4] A method for validating embodiments of the present invention is shown. [Modes for carrying out the invention]

[0046] The following describes embodiments of the present invention in which a method for determining the torque of a drivetrain is used to make the drivetrain particularly efficient.

[0047] Figure 1 shows a drive train 1 according to one embodiment of the present invention. In the illustrated embodiment, the drive train 1 is used in a passenger car and comprises a motor 2 having a motor shaft 3, a motor controller 4, a torque sensor 5 having a microcontroller, a data transmission system 6, and a transmission device 7 having an output shaft 8. The motor shaft 3 of the motor 2 is connected to the transmission device 7, thereby transmitting the motor torque generated by the motor 2 to the transmission device 7. The transmission device 7 is a harmonic drive transmission device having an elastic transmission element characterized by a high transmission ratio and rigidity. The elastic transmission element is also called a flex spline. The transmission device 7 further has an output shaft 8, and the torque of the output shaft 8 is transmitted to the wheels of the passenger car.

[0048] The torque sensor 5 is equipped with a strain gauge, which is made of semiconductor material and measures the voltage applied to the resistor based on the piezoresistive effect. Here, changes in resistance and voltage are caused by the deformation of the strain gauge. Compared with conventional metal strain gauges, the advantage of the strain gauge used is its high sensitivity.

[0049] The strain gauge of the torque sensor 5 is positioned on the elastic transmission element of the transmission device 7. This integrates the torque sensor 5 into the transmission device 7. The torque sensor 5 is connected to the motor controller 4 via a data transmission system 6. The motor controller 4 measures the signal value related to the motor 2 and transmits this signal value to the torque sensor 5.

[0050] The method for determining the torque is implemented in the form of a computer program on the microcontroller of the torque sensor 5. Once the torque is determined, it is transmitted to the motor controller 4 via the data transmission system 6.

[0051] Figure 2 schematically illustrates a method according to one embodiment of the present invention. The method according to this embodiment includes the following steps.

[0052] First step S1.1: The torque sensor 5 measures the voltage and passes that voltage to the microcontroller.

[0053] Second step S1.2: The motor controller 4 passes the signal value to the microcontroller.

[0054] The third step S1.3: A mathematical model 9 is implemented on the microcontroller to determine the torque based on the voltage and signal values.

[0055] It is understood that the order of steps S1.1, S1.2, and S1.3 mentioned may vary depending on the application. For example, the signal value of the motor controller 4 may be sent to the microcontroller first, and then the voltage may be measured by the torque sensor 5 and sent to the microcontroller. It is also possible to perform the first step S1.1 and the second step S1.2 simultaneously.

[0056] After determining the torque, the torque can be transmitted to the motor controller 4 in further steps not shown in the exemplary embodiments.

[0057] Figure 3A shows a mathematical model 9 according to one embodiment of the present invention. Various signal values ​​are transmitted to the mathematical model 9 as input data E, and in the illustrated embodiment, the input data E are the voltage U measured by the torque sensor 5, the temperature Θ of the transmission device, the position Ω of the motor, and the direction of rotation Ψ of the motor. The mathematical model 9 calculates the torque T of the output shaft 8 of the drive train 1 based on the four signal values ​​U, Θ, Ω, and Ψ. The calculated torque T is provided as a signal value for further use. Here, the mathematical model 9 is an artificial neural network trained with training data before being used in the drive train 1. The calculation of torque T by the artificial neural network and the components of the drive train 1 is optimally tuned to the stringent real-time requirements demanded in the field of motor technology. In this regard, the computation time is within the normal range for the application of the motor controller 4.

[0058] Figure 3B shows a motor controller 4 and torque sensor 5 according to a further embodiment of the present invention. The motor controller 4 and torque sensor 5 are connected to each other via a data transmission system 6 and are therefore able to transmit signal values ​​Ω, Ψ, I, T, and Z to each other. In the illustrated embodiment, the motor controller 4 transmits the motor position Ω, the motor rotation direction Ψ, and the motor current I to the torque sensor 5. The torque sensor 5 transmits the torque T of the output shaft 8 of the drive train 1 and the status Z of the torque sensor 5 to the motor controller 4.

[0059] In the illustrated embodiment, the data transmission system 6 is an EtherCAT system. The data transmission system 6 thus advantageously meets real-time requirements. The motor controller 4 and the torque sensor 5 can transmit signal values ​​Ω, Ψ, I, T, and Z to each other or exchange them in synchronization. Furthermore, the signal values ​​Ω, Ψ, and I can be transmitted from the motor controller 4 to the torque sensor 5, where they can be used directly, for example, to calculate the torque T. The torque T can then be transmitted back directly to the motor controller 4.

[0060] Figure 4 shows a method for validation according to one embodiment of the present invention. In this regard, all method steps S2.1, S2.2, S2.3, S2.4 and S2.5 are performed in the microcontroller belonging to the torque sensor 5.

[0061] In the first step S2.1, the microcontroller receives signal values ​​Ω, Ψ, and I from the motor controller 4 via the data transmission system 6. Here, the signal values ​​include the motor current I. In the second step S2.2, the microcontroller calculates the torque T based on the signal values ​​Ω, Ψ, and I using a mathematical model 9 implemented on the microcontroller. Furthermore, in the second step S2.2, the microcontroller verifies the estimated torque based on the motor current I. The microcontroller also verifies the upper and lower torque limits based on the estimated torque. In the third step S2.3, the microcontroller evaluates the torque T determined by the mathematical model 9 based on the upper and lower torque limits.

[0062] If the torque T, as confirmed by mathematical model 9, is outside the torque limits, i.e., greater than the value defined by the upper torque limit or less than the value defined by the lower torque limit, the microcontroller sets the status Z to "error" in a further step S2.4.

[0063] If the torque T, as confirmed by mathematical model 9, is within the torque limits, i.e., smaller than the value defined by the upper torque limit and simultaneously larger than the value defined by the lower torque limit, the microcontroller sets the status Z to "valid" in a further step S2.5.

[0064] In a further step, status Z and torque T can be transmitted to the motor controller 4 by the data transmission system 6. Thus, the method shown in Figure 4 is used to check the technical validity of torque T, which is verified by mathematical model 9. If status Z is output as "error," torque T is not used for further calculations in the motor controller 4.

[0065] Although embodiments of the present invention are described primarily for use in passenger cars, it should be noted that the principles disclosed herein can nevertheless be implemented in other fields of application, such as heavy-duty transport vehicles, trucks, motorcycles, robotic axis drive systems, and flight simulator drive systems.

[0066] For convenience, the algorithms or computer programs required for the above functions may be implemented in whole or in part in the torque sensor 5, the microcontroller, the motor controller 4, and / or in another computer system connected to these devices. The computer system may be a local computer device (e.g., a personal computer, laptop, tablet computer, or mobile phone) having one or more processors and one or more storage devices, or it may be a distributed computer system (e.g., a cloud computing system having one or more processors or one or more storage devices distributed in various locations, e.g., local clients and / or one or more remote server farms and / or data centers).

[0067] Depending on certain implementation requirements, exemplary embodiments of the present invention may be carried out using hardware or software. Some or all of the method steps may be performed by (or using) hardware devices such as a processor, microprocessor, programmable computer, or electronic circuit.

[0068] While several embodiments have been described in the context of apparatus, it is clear that these embodiments also constitute descriptions of corresponding methods, where a block or apparatus corresponds to a method step or a function of a method step. Similarly, embodiments described in the context of a method step also represent descriptions of the characteristics of a corresponding block or element, or a corresponding apparatus.

Claims

1. A method for determining the torque (T) of a driven device (1), the method comprising the following steps: This involves obtaining the input data (E), A voltage (U) measured using a torque sensor (5) with a microcontroller, To obtain input data (E) including at least one signal value (Ω, Ψ, I) of the motor controller (4), The process includes determining the torque (T) by a mathematical model (9) based on the voltage (U) and the at least one signal value (Ω, Ψ, I), The mathematical model (9) is implemented on the microcontroller of the torque sensor (5). The voltage (U) measured by the torque sensor (5) is passed to the microcontroller. The at least one signal value (Ω, Ψ, I) is transmitted from the motor controller (4) to the microcontroller. The microcontroller uses the mathematical model (9) to determine the torque (T) based on the voltage (U) and the at least one signal value (Ω, Ψ, I), and the determined torque (T) is transmitted to the motor controller (4) to control the motor. To verify the validity of the determined torque (T): To confirm the estimated torque based on the motor current (I), Based on the estimated torque, the upper and lower torque limits are confirmed, A method comprising: evaluating the torque (T) determined by the mathematical model (9) based on the torque upper limit and the torque lower limit, wherein if the torque (T) is greater than the value defined by the torque upper limit or less than the value defined by the torque lower limit, the microcontroller does not use the torque (T) to control the motor.

2. The method according to claim 1, wherein the at least one signal value (Ω, Ψ, I) of the motor controller (4) includes the motor position (Ω) and / or the direction of rotation (Ψ).

3. The method according to claim 1 or 2, wherein the input data (E) further includes temperature (Θ).

4. The method according to claim 1, wherein the mathematical model (9) includes a finite element model.

5. The method according to claim 1, wherein the mathematical model (9) includes a machine learning model.

6. The machine learning model is trained using at least one training dataset, and the at least one training dataset is The voltage (U) measured using the torque sensor (5), At least one signal value (Ω, Ψ, I) from the motor controller, The method according to claim 5, comprising a reference torque.

7. The method according to claim 1, wherein the torque (T) determined by the mathematical model (9) is transmitted to a control loop, and the control loop controls the motor current (I) and / or speed.

8. A microcontroller for a torque sensor (5), comprising means for performing the method described in claim 1.

9. A computer program including a command, wherein the command causes the computer to perform the method according to claim 1 when the program is executed by the computer.

Images