Method and device for detecting and localizing faults in an antenna array, and test system

Patent metadata

Field	Value
Publication number	US-12457047-B2
Application number	US-202318166559-A
Country	US
Kind code	B2
Filing date	Feb 9, 2023
Priority date	Feb 9, 2023
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

A computer-implemented method for detecting and localizing faults in an antenna array comprises performing fault detection on the antenna array to identify the presence of at least one faulty antenna element of the antenna array. The fault detection is performed using a machine learning technique. It is determined whether the antenna array is faulty or non-faulty, based on a result of the performed fault detection. The at least one faulty antenna element is localized if the antenna array is determined to be faulty, using a machine learning technique.

First claim

The invention claimed is:

1. A computer-implemented method for detecting and localizing faults in an antenna array, comprising the steps:
performing fault detection on the antenna array to identify the presence of at least one faulty antenna element of the antenna array, wherein the fault detection is performed using a machine learning technique;
determining whether the antenna array is faulty or non-faulty, based on a result of the performed fault detection; and
localizing the at least one faulty antenna element if the antenna array is determined to be faulty, using a machine learning technique;
wherein the steps of performing fault detection and of localizing the at least one faulty antenna element are based on over-the-air measurement data generated by at least one measurement antenna positioned at multiple sampling points around the antenna array; and
wherein the machine learning technique used for performing fault detection and the machine learning technique used for localizing the at least one faulty antenna element comprise at least one pre-trained deep neural network model outputting fault detection and localization results used to adjust antenna element weights to restore a target radiation pattern.

2. The method according to claim 1 , further comprising the step of displaying the at least one localized faulty antenna element in a representation of the antenna array on a display.

3. The method according to claim 1 , wherein a number of the sampling measurement points is optimized, using variance methods and/or stochastic methods.

4. The method according to claim 1 , wherein the weights of the identified at least one faulty antenna element are adjusted.

5. The method according to claim 1 , wherein the weights of an antenna element which is not identified to be faulty are adjusted.

6. The method according to claim 1 , wherein the weights are adjusted using a recursive feedback loop.

7. The method according to claim 1 , wherein the method is carried out during operation of the antenna array in an intended application.

8. The method according to claim 1 , further comprising the step of training a machine learning model being used for the fault detection and/or localizing of the at least one faulty antenna element.

9. The method according to claim 1 , wherein a single machine learning model is used for performing fault detection and for localizing the faulty antenna element.

10. The method according to claim 1 , wherein two separate machine learning models are used for performing fault detection and for localizing the faulty antenna element.

11. The method according to claim 1 , wherein a fault type of the localized at least one faulty antenna element is determined, using a machine learning technique.

12. A device for detecting and localizing faults in an antenna array, comprising:
at least one processor; and
a memory storing computer-executable instructions that, when executed by the at least one processor, cause the at least one processor to:
perform fault detection on the antenna array to identify the presence of at least one faulty antenna element of the antenna array, wherein the fault detection is performed using a machine learning technique,
determine whether the antenna array is faulty or non-faulty, based on a result of the performed fault detection, and
localize the at least one faulty antenna element if the antenna array is determined to be faulty, using a machine learning technique;
wherein the processor is configured to perform fault detection and to localize the at least one faulty antenna element based on over-the-air measurement data generated by at least one measurement antenna positioned at multiple sampling points around the antenna array; and
wherein the machine learning technique used for performing fault detection and the machine learning technique used for localizing the at least one faulty antenna element comprise at least one pre-trained deep neural network model outputting fault detection and localization results for adjusting antenna element weights to restore a target radiation pattern.

13. A test system for testing antenna arrays, comprising:
at least one measurement antenna configured to generate measurement data by measuring radiation from an antenna array at sampling measurement points; and
the device according to claim 12 for detecting and localizing faults in the antenna array, using the measurement data generated by the at least one measurement antenna.

Assignees

• Rohde & Schwarz

Inventors

• Sai Marwa
• Schaefer Andrew
• Derat Benoit
• Tankielun Adam

Classifications

• H01Q21/24

  Combinations of antenna units polarised in different directions for transmitting or receiving circularly and elliptically polarised waves or waves linearly polarised in any direction {(circularly polarised patch antennas H01Q9/0428; circularly polarised horns H01Q13/0241; cross-polarised horns H01Q13/0258; polarisation converters H01Q15/242; cross-polarised rear feeds H01Q19/136; crossed polarisation dual antenna H01Q25/001)} · CPC title

• H01Q1/246

  specially adapted for base stations · CPC title

• H01Q3/267

  Phased-array testing or checking devices · CPC title

• H04B17/17 Primary

  Detection of non-compliance or faulty performance, e.g. response deviations (H04B17/18 takes precedence) · CPC title