PAGE CONTENTS
Objectives
As of today, performances of antenna systems are evaluated analysing both measured and modelled data. If an anomaly occurs, an iterative process is made to determine the root cause. The goal of this project is to develop and validate AIDA (Artificial-Intelligence-Assisted Performance and Anomaly Detection and Diagnostic), a machine-learning-based software for the detection of RF anomalies and the identification of the associated root causes.
AIDA intends to contribute to the antenna experts analysis and to reduce the diagnosis time by implementing the following software capabilities:
-
Early identification of antenna system anomalies, using an AI approach to classify patterns data, implementing generalization strategies in order to foster re-use of a trained model for different antennas under test (AUTs).
-
Accurate anomaly quantification, thanks to a wide labelled database which is used for this purpose.
-
Verification of the anomaly classification and quantification output, comparing the measured patterns with the EM model data updated with the AIDA diagnostic output.
Challenges
The key challenges are the following:
-
Exploit artificial intelligence techniques (e.g. supervised machine learning) for diagnosing RF anomalies
-
Implement generalization techniques to foster re-use of the trained AI model for antennas having different dimensions or operating at different frequency bands with respect to the dataset used for the training
-
Use of real or simulated data with known output labels for training the AI model
-
Reduce the diagnosis time by a factor of 10/100 (i.e. from two weeks up to one day or less).
-
Develop a software framework for testing the AI model, and for execute comparison analyses between data.
System Architecture
AIDA is characterised by a typical three tier architecture composed by:
-
The AIDA database, which collects all the antennas patterns uploaded into the system (training and test data);
-
The AIDA Diagnostic SW, which executes the anomaly classification and quantification, and it contains the function usable for the computation of the reconstruction error; the AIDA Diagnostic SW functionalities can be accessed both from the command terminal and from the developed AIDA Front-end SW.
-
The AIDA Front-end SW, which is a web-based application from which all the features of the AIDA Diagnostic SW can be reached. Moreover, this software allows the user to investigate data from the database, plotting patterns and investigating diagnostic results.
The AIDA Training SW is an external module, which is responsible for the training of an AI algorithm, either imposing the training hyper-parameters, or using an hyper-parameter optimization; in the current version implemented, the AIDA Training SW functionalities can be accessed from the command terminal.
Plan
The project comprises the following working packages:
- WP100: identify state-of-the-art AI methods suitable for the diagnostic system to be developed, defining a technical specification of the proposed solution, and demonstrating its feasibility.
- WP200: prepare a preliminary training dataset for the selection of the candidate AI methodologies, and operate the trade-off analysis for the selection of the algorithm to be implemented.
- WP300: prepare the final training dataset to be used for the training of the selected AI algorithm, implement the diagnostic strategy and implement the framework of the front-end software.
- WP400: demonstrate the functionalities of the diagnostic solution, operating a test campaign.
- WP500: summarise the results achieved during the project, identifying future developments points, and pointing out the most important lessons learnt.
Current Status
The AIDA diagnostic solution has been tested with data of reflector and phased array antennas. Performances have been proved satisfying If the input is composed of antennas having the same operative conditions as the training dataset. If the operative conditions differ from the training dataset, the classification accuracy depends from the anomaly class considered. Possible improvement points have been addressed as particularly important to attain performance levels suitable for the market needs and future RF technologies.
