Temperature hotspot detection on printed circuit boards (pcbs) using ultrasonic guided waves—a machine learning approach

Abstract

This paper addresses the challenging issue of achieving high spatial resolution in temperature monitoring of printed circuit boards (PCBs) without compromising the operation of electronic components. Traditional methods involving numerous dedicated sensors such as thermocouples are often intrusive and can impact electronic functionality. To overcome this, this study explores the application of ultrasonic guided waves, specifically utilising a limited number of cost-effective and unobtrusive Piezoelectric Wafer Active Sensors (PWAS). Employing COMSOL multiphysics, wave propagation is simulated through a simplified PCB while systematically varying the temperature of both components and the board itself. Machine learning algorithms are used to identify hotspots at component positions using a minimal number of sensors. An accuracy of 97.6% is achieved with four sensors, decreasing to 88.1% when utilizing a single sensor in a pulse–echo configuration. The proposed methodology not only provides sufficient spatial resolution to identify hotspots but also offers a non-invasive and efficient solution. Such advancements are important for the future electrification of the aerospace and automotive industries in particular, as they contribute to condition-monitoring technologies that are essential for ensuring the reliability and safety of electronic systems.