EP-4439094-B1 - METHOD AND APPARATUS FOR DETECTING ANOMALIES IN AN OPERATION BEHAVIOR OF A DEVICE UNDER TEST

EP4439094B1EP 4439094 B1EP4439094 B1EP 4439094B1EP-4439094-B1

Inventors

SCHWARZ, GEORG
AHMED, Rafid
GOETZ, REINER
BARTKO, HENDRIK

Dates

Publication Date: 20260506
Application Date: 20230329

Claims (13)

A method for detecting anomalies in an operation behavior of a device under test, DUT, the method comprising: monitoring (S1) the device under test, DUT, arranged in a test environment to generate a first set of observation data without subjecting the device under test, DUT, to disturbances; training (S2) an artificial intelligence, AI, algorithm with the generated first set of observation data; monitoring (S3) at least one device under test, DUT, arranged in the test environment to generate a second set of observation data while subjecting the device under test, DUT, to disturbances; and processing (S4) the second set of observation data by the trained artificial , AI, algorithm to detect anomalies in the operation behavior of the device under test, DUT, while being subjected to the disturbances; and reporting (S5) detected anomalies in the operation behavior of the device under test, DUT, wherein the test environment comprises a test chamber into which the device under test, DUT, is placed.
The method according to any of the preceding claims, wherein the detected anomalies in the operation behavior of the device under test, DUT, detected by the trained artificial intelligence, AI, algorithm are automatically reported in a notification report.
The method according to claim 2, wherein the notification report provides a rating of a significance of a detected anomaly in the operation behavior of the device under test, DUT.
The method according to any of the preceding claims, wherein the trained artificial intelligence algorithm determines a probability that the detected anomalies in the operational behavior of the device under test, DUT, go beyond changes of the operational behavior of the device under test, DUT, to be expected due to disturbances.
The method according to any of the preceding claims, wherein the notification report provides information where an anomaly in the operation behavior of the device under test, DUT, has been detected by the trained artificial intelligence, AI, algorithm.
The method according to any of the preceding claims, wherein the disturbances to which the device under test, DUT, is subjected to generate the second set of observation data comprise: - electromagnetic disturbances, in particular electromagnetic radiation generated by an antenna (9), and/or - mechanical disturbances, in particular vibrations applied by a plate (6) , and/or - environmental disturbances, in particular humidity, dust, temperature variations, pressure variations.
The method according to any of the preceding claims, wherein the observation data comprises image data generated by at least one camera (7) provided in the test environment.
The method according to any of the preceding claims, wherein the observation data comprises audio data generated by at least one microphone (8) provided in the test environment.
The method according to any of the preceding claims, wherein the notification report is announced via a warning message, an alarm signal or via a log-file.
The method according to any of the preceding claims, wherein the method is stopped automatically once a significant anomaly in the operation behavior of the device under test, DUT, has been detected by the trained artificial intelligence, AI, algorithm.
A test apparatus (1) for detecting anomalies in an operation behavior of a device under test (DUT) arranged in a test environment of said test apparatus (1), the test apparatus (1) comprising: a monitoring unit (2) adapted to generate a first set of observation data of the operation behavior of a device under test (DUT) while the device under test (DUT) is not subjected to disturbances and adapted to generate a second set of observation data of the operation behavior of a device under test (DUT) while the device under test (DUT) is subjected to disturbances; an artificial intelligence, AI, module (3) trained with the first set of observation data generated by the monitoring unit and adapted to process the second set of observation data to detect anomalies in the operation behavior of the device under test (DUT) while being subjected to the disturbances; and a reporting unit (4) adapted to reporting anomalies in the operation behavior of the device under test (DUT) detected by the artificial intelligence, AI, module (3), wherein the test environment of the test apparatus comprises a test chamber used to receive the device under test (DUT).
The test apparatus according to claim 11, further comprising at least one camera (7) adapted to provide image data and/or at least one microphone (8) adapted to provide audio data stored as observation data in a data memory of the test apparatus (1).
A test software, which is adapted to control the test apparatus of any one of claims 11 and 12 to perform the method according to any of the preceding claims 1 to 10.

Description

FIELD OF THE INVENTION The present invention relates to a method and an apparatus for detecting anomalies in an operation behavior of a device under test (DUT), in particular during electromagnetic susceptibility (EMS) measurements. TECHNICAL BACKGROUND A test software can be used to control complete Electromagnetic Compatibility (EMC) test systems to perform automated or interactive electromagnetic interference (EMI) and electromagnetic susceptibility (EMS) measurements on a device under test (DUT) to verify its compliance with relevant standards. Electromagnetic susceptibility (EMS) is the degree to which an electronic device malfunctions or breaks down when subjected to varying levels of EMI. Electromagnetic Interference and Electromagnetic Susceptibility include both radiated and conducted emissions. Testing is mostly performed to detect anomalies or failures in an operation behavior of a device under test DUT. In a conventional test system this requires that a user defines manually regions of interest where to look for anomalies in the operation behavior of the investigated device under test, DUT. However, a manual definition of regions of interest by a user is a subjective and error prone. Moreover only known types of errors or failures can be detected in this way. Medico Roberto et al. "Machine-Learning-Based Error Detection and Design Optimization in Signal Integrity Applications" discloses a machine learning based framework for automated assessment of errors for SI applications, which can be easily integrated in the design phase. Medico Roberto et al. "Machine Learning Based Error Detection in Transient Susceptibility Tests" discloses a novel machine learning based approach for error detection in transient susceptibility tests. DE 10 2020 208306 A1 discloses a method for testing a component in a series of component tests. US 2021/0365796 A1 discloses a method for detecting anomalies in a spectrogram, spectrum or signal using a detection module having a first machine learning submodule, a second machine learning submodule and a comparison submodule. US 2023/086626 A1 discloses a test and measurement device that has an interface, one or more connectors, each connector to allow the test and measurement device to connect to a test and measurement instrument, and one or more processors, the one or more processors configured to execute code to cause the one or more processors to: receive one or more user inputs through the interface identifying one or more tests to perform on a device under test (DUT); form a connection through one of the one or more connectors to the DUT to perform the one or more tests and receive test result data; apply one or more machine learning models to the test result data to identify potentially anomalous test results; and generate and present a representation of the test result data and the potentially anomalous test results. US 2023/086626 A1 further discloses a method of analyzing test data includes receiving one or more user inputs through an interface identifying one or more test to perform on a device under test (DUT), forming a connection to at least one test and measurement instrument, directing the test and measurement instrument to perform one or more tests on the DUT and receive test result data, applying one or more machine learning models to the test result data to identify potentially anomalous test results, and generating and presenting a representation of the test result data and the potentially anomalous test results. SUMMARY OF THE INVENTION Against this background, the object of the present invention is to provide a method and an apparatus which allow to detect automatically anomalies in an operation behavior of a device under test DUT without the need to define manually regions of interest by a user. This problem is solved according to the invention by a method and an apparatus having the features of the independent claims. According thereto, the following is provided: A method for detecting anomalies in an operation behavior of a device under test, DUT, comprising the steps of: monitoring the device under test, DUT, arranged in a test environment to generate a first set of observation data without subjecting the device under test, DUT, to disturbances; training an artificial intelligence, AI, algorithm with the generated first set of observation data; monitoring the at least one device under test, DUT, arranged in the test environment to generate a second set of observation data while subjecting the device under test, DUT, to disturbances; processing the second set of observation data by the trained artificial intelligence, AI, algorithm to detect anomalies in the operation behavior of the device under test, DUT, while being subjected to the disturbances; and reporting detected anomalies in the operation behavior of the device under test, DUT.A test apparatus for detecting anomalies in an operation behavior of a device under test (DUT) arranged in a test en