AI Anomaly Detection in DUT Behavior During EMS Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting anomalies in a device under test during electromagnetic susceptibility measurements require manual definition of regions of interest, which is subjective and limited to known errors, failing to detect unknown anomalies effectively.
Innovation Solution
A method and apparatus utilizing an artificial intelligence algorithm to automatically detect anomalies by monitoring a device under test in a controlled environment, generating observation data with and without disturbances, and processing these data to identify anomalies using trained AI models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual user-defined regions of interest are used to detect anomalies, then the detection process is simple and straightforward, but the detection is subjective and limited to known errors only
Solution Approach 1:
The system performs preliminary monitoring of the device under test to generate baseline observation data before actual testing. This baseline data is used to train the AI algorithm, enabling it to learn normal operational patterns and detect deviations automatically during subsequent tests without requiring manual definition of regions of interest
Solution Approach 2:
The patent replaces the manual mechanical process of defining regions of interest with an AI-based automated system. The AI algorithm automatically identifies anomalies by comparing observed data against learned patterns, eliminating the need for subjective human input and enabling detection of previously unknown error types
2Device complexity
If manual definition of regions of interest is required, then the system structure remains simple, but automation level is reduced and error-prone
Solution Approach 1:
The system enables the device under test to monitor itself through integrated sensors and the AI algorithm automatically analyzes the collected data. The AI learns from baseline data generated during normal operation and autonomously identifies anomalies without requiring external manual intervention or complex system architecture
Solution Approach 2:
The patent transforms the detection approach by changing from fixed manual parameters (regions of interest) to dynamic AI-learned parameters. The system collects multiple types of operational data and uses the AI algorithm to automatically determine which parameters indicate anomalies, adapting to different device types and failure modes
3Ease of operation
If conventional testing methods are used, then the testing process is straightforward, but only known types of errors can be detected
Solution Approach 1:
The system performs preliminary monitoring to generate baseline observation data that captures normal operational patterns. This baseline is used to train the AI algorithm before actual testing, enabling the system to detect both known and unknown anomalies by comparing test data against the learned baseline without complicating the testing process
Solution Approach 2:
The AI-based detection system is designed to be universal and applicable to multiple device types and failure modes. By training the AI on diverse baseline data and using pattern recognition rather than device-specific rules, the system can detect various types of anomalies across different devices while maintaining ease of operation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
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. The apparatus comprises a monitoring unit adapted to generate a first set of observation data of the operation behavior of a DUT while the DUT is not subjected to disturbances and adapted to generate a second set of observation data of the operation behavior of a DUT while the DUT is subjected to disturbances and comprising an AI module 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 DUT while being subjected to the disturbances and comprising a reporting unit adapted to reporting anomalies in the operation behavior of the DUT detected by the trained AI module.