A Variational Quantum Classifier for predictive analysis in industrial production

Abstract

Quantum Computing (QC) is a novel and disruptive paradigm of computation that leverages the properties of quantum mechanical systems to represent and process information. The interest in this emerging technology and its applications has been growing in recent years, especially regarding Quantum Machine Learning (QML). In QML, QC and Machine Learning (ML) techniques are combined to build more powerful and accurate learning models. Industries and research centers worldwide have been devoting significant efforts to find use cases of practical interest for which QML may be a suitable approach. In this work, one of the most common QML algorithms, namely a Variational Quantum Classifier (VQC), has been adopted for a supervised classification task in defence industry. The goal is to predict the failures that may happen during the final acceptance test of a finished product, based on the knowledge of test data related to its subassemblies. The test data have been collected using advanced IoT systems and the prediction has been made before the final product was assembled, so to improve the efficiency in the testing process. The VQC has been applied to a problem already approached with classical ML techniques, and then the classical and quantum performances have been compared. The results indicate promising performances and highlight the potential of QML algorithms in the industrial sector for predictive analysis use.