Deep Neural Network-Based Temperature Mapping Technique for Heat Sink on Electronic Devices Using Local Thermocouple Sensors

Abstract

Heat generated by electronic devices can lead to thermal deformation, damage, and fatigue failure, underscoring the importance of monitoring heat distribution. This study introduces an artificial neural network using two thermocouples for cost-effective temperature distribution prediction. Experimental data from heated systems on chip with attached heat sinks were used for training and validation, integrating thermocouple measurements and infrared camera data. The method’s applicability was verified across four different heat sinks. Additionally, finite element analysis compared stress and strain based on predicted and actual temperature distributions, addressing conventional limitations that focus solely on temperature validation. Furthermore, the temperature of any coordinate could be output by including the coordinate as an input of neural networks, eliminating the hassle of re-constructing or learning the DNN to obtain the temperature of the desired coordinate. Results showed that the temperature distribution could be predicted with high accuracy (over 0.95), and the maximum error rate for stress and strain predictions was 7% in the worst case. This confirmed the feasibility of artificial neural networks to predict the temperature distribution using a minimal number of sensors and ensure robust performance even if the heat sink changes.