Automated Antenna Testing Using Encoder-Decoder-based Anomaly Detection

TL;DR

This paper introduces an AI-based method using encoder-decoder models to detect faults in antenna arrays by analyzing thermal image sequences, significantly improving classification accuracy over traditional approaches.

Contribution

The study presents a novel anomaly detection approach for antenna testing using a conditional encoder-decoder model and contour-based anomaly scoring, outperforming variational autoencoders with learned observation noise.

Findings

Increased F-measure by up to 46% in fault classification.

Lower observation noise assumption in VAE yields 11.83% higher ROC AUC.

Effective detection of low-level thermal pattern anomalies.

Abstract

We propose a new method for testing antenna arrays that records the radiating electromagnetic (EM) field using an absorbing material and evaluating the resulting thermal image series through an AI using a conditional encoder-decoder model. Given the power and phase of the signals fed into each array element, we are able to reconstruct normal sequences through our trained model and compare it to the real sequences observed by a thermal camera. These thermograms only contain low-level patterns such as blobs of various shapes. A contour-based anomaly detector can then map the reconstruction error matrix to an anomaly score to identify faulty antenna arrays and increase the classification F-measure (F-M) by up to 46%. We show our approach on the time series thermograms collected by our antenna testing system. Conventionally, a variational autoencoder (VAE) learning observation noise may yield better results than a VAE with a constant noise assumption. However, we demonstrate that this is not the case for anomaly detection on such low-level patterns for two reasons. First, the baseline metric reconstruction probability, which incorporates the learned observation noise, fails to differentiate anomalous patterns. Second, the area under the receiver operating characteristic (ROC) curve of a VAE with a lower observation noise assumption achieves 11.83% higher than that of a VAE with learned noise.