Search

EP-4739988-A1 - COMPUTER-IMPLEMENTED METHOD FOR PROVIDING A TRAINING DATA SET, COMPUTER-IMPLEMENTED METHOD FOR TRAINING AN AI SYSTEM AND USING SUCH A COMPUTER-IMPLEMENTED METHOD, AND TRAINING DATA SET FOR TRAINING AN AI SYSTEM

EP4739988A1EP 4739988 A1EP4739988 A1EP 4739988A1EP-4739988-A1

Abstract

The invention relates to computer-implemented method for providing a training data set for training an AI system, having the following steps: - carrying out a measurement using a sensor, in particular a torque sensor; - providing unaltered sensor data which is measured on the basis of the measurement carried out by the sensor; - generating altered sensor data on the basis of the unaltered sensor data; and - providing the unaltered sensor data and the altered sensor data as part of a training data set for training an AI system.

Inventors

  • HEIM, JENS

Assignees

  • Schaeffler Technologies AG & Co. KG

Dates

Publication Date
20260513
Application Date
20240610

Claims (10)

  1. 1. Computer-implemented method for providing a training data set for training a Kl system (50) comprising the following steps: - carrying out a measurement with a sensor (30), in particular a torque sensor; - Providing unadulterated sensor data that depends on the measurement performed with the sensor; - generating falsified sensor data depending on the unfalsified sensor data; and - Providing the unadulterated sensor data and the adulterated sensor data as part of a training data set for training a CL system (50).
  2. 2. Computer-implemented method according to claim 1, characterized in that as a further part of the training data set, a first classification information associated with the unadulterated sensor data and a second classification information associated with the falsified sensor data are provided, wherein the first and the second classification information differ.
  3. 3. Computer-implemented method according to claim 2, characterized in that the first and second classification information comprises: - an indication of whether the unadulterated or falsified sensor data to which the classification information is assigned are unadulterated or falsified.
  4. 4. Computer-implemented method according to one of claims 2 or 3, characterized in that the unadulterated and adulterated sensor data each comprise several sensor data channels and the first and second classification information comprises: - an indication of how many faulty sensor data channels are present.
  5. 5. Computer-implemented method according to one of claims 2 to 4, characterized in that the unadulterated and adulterated sensor data each comprise several sensor data channels and the first and second classification information comprises: - an indication of which sensor data channel(s) are faulty.
  6. 6. Computer-implemented method according to one of the preceding claims, characterized in that the generation of the falsified sensor data takes place by adding the unfalsified sensor data with an error signal.
  7. 7. Computer-implemented method for training a Kl system (50) for evaluating an integrity of sensor data, comprising the following steps: - Providing unadulterated sensor data and linking the unadulterated sensor data with a first classification information as first training data; - Providing falsified sensor data and linking the falsified sensor data with a second classification information as second training data; - Training the Kl system (50) with the first and second training data.
  8. 8. Computer-implemented method for training a Kl system (50) according to claim 7, characterized by the following steps: - Providing unadulterated sensor data and linking the unadulterated sensor data with a first classification information as first test and/or validation data; - Providing falsified sensor data and linking the falsified sensor data with a second classification information as second test and/or validation data; - testing and/or validating the AI system (50) after training the AI system (50) with the first and second test and/or validation data.
  9. 9. Drive module (100), in particular for a robot arm joint, comprising - a stress wave transmission having an elastic transmission element and a wave generator acting on the elastic transmission element, wherein the elastic transmission element has a sensor (30) with a sensor data channel (32), wherein a sensor data can be measured by means of the sensor (30), and - a control device (40) with a Kl system (50) for evaluating an integrity of sensor data, wherein a plausibility check of the sensor data can be carried out by means of the Kl system (50).
  10. 10. Training data set for training a Kl system (50) for evaluating an integrity of sensor data comprising: - unadulterated sensor data and a first classification information associated with the unadulterated sensor data; - falsified sensor data and a second classification information associated with the falsified sensor data.

Description

Computer-implemented method for providing a training data set, Computer-implemented method for training a Kl system and Using such a computer-implemented method, training data set for training a Kl system The invention relates to a computer-implemented method for providing a training data set for training an artificial intelligence (AI) system. The invention also relates to a computer-implemented method for training an AI system for evaluating the integrity of sensor data and to a use of such a method. The invention also relates to a training data set for training an AI system. The invention can be used, for example, to check the functionality of a sensor and/or the quality of the measured values it provides, i.e. the integrity of the sensor. Such checks are often provided in safety-relevant applications. For example, in drive modules of collaborative robots it may be necessary to check the integrity of the measurement data provided by torque and/or position sensors in order to be able to rule out damage to the people working with the collaborative robots. Such checks are usually very time-consuming and require detailed knowledge of the functionality and structure of the respective sensor. Against this background, the task is to provide a solution that reduces the effort involved in checking the integrity of a sensor and can be used regardless of the functionality and structure of the sensor. The problem is solved by a computer-implemented method for providing a training data set for training a Kl system comprising the following steps: - Carrying out a measurement with a sensor, in particular a torque sensor; - Providing unadulterated sensor data that depends on the measurement performed with the sensor; - generating falsified sensor data depending on the unfalsified sensor data; and - Providing the unadulterated sensor data and the adulterated sensor data as part of a training dataset for training an AI system. According to the invention, a training data set is provided for an artificial intelligence (AI) system, which can be used in a trained state to check the integrity of the sensor. Through training, the AI system can be taught to the respective application, i.e. the respective sensor. Detailed knowledge of the functionality or structure of the sensor to be monitored is not required. According to the invention, the provision of the training data only requires unadulterated sensor data, which can come from a functional sensor, for example. Sensor data from a non-functional sensor is not required. Rather, in the method according to the invention, falsified sensor data is generated depending on the unadulterated sensor data itself. In this way, the effort required to train the AI system is reduced. The provision of the training data set can be carried out, for example, during the calibration of a (still) functional sensor, with the sensor data determined during this being used as unadulterated sensor data for the training data set. Sensor data in the sense of the invention is understood to mean measurement data and/or data derived from the measurement data. Derived data can be, for example, filtered data, angle or torque signals. Furthermore, both generic Kl models and parameterizations can be used for the Kl system, as well as models and/or parameterizations adapted individually to the respective sensor. Transfer learning methods can also be used, for example, to adapt a generic model individually to the respective sensor. According to a preferred embodiment of the invention, it is provided that a first classification information associated with the unadulterated sensor data and a second classification information associated with the falsified sensor data are provided as a further part of the training data set, wherein the first and the second classification information differ. Classification information can also be referred to as a "label", i.e. an output value of the Kl system. An advantageous embodiment of the invention provides that the first and second classification information comprises: - an indication of whether the unadulterated or falsified sensor data to which the classification information is assigned are unadulterated or falsified. Examples of the first classification information are “unadulterated” or “no error detected”. Examples of the second classification information are “adulterated” or “error detected”. According to a preferred embodiment of the invention, it is provided that the unadulterated and falsified sensor data each comprise several sensor data channels and the first and second classification information comprises: - an indication of how many faulty sensor data channels are present. By having information about the number of faulty sensor data channels, the AI system can be provided with a more realistic image of the data. Alternatively or additionally, a severity level of the error or errors can be determined and transmitted to the AI system. An advantageous embodiment of t