A methodology for microcontroller signal frequency stress prediction

This paper proposes a methodology for analysis and prediction of microcontroller failures due to signal frequency stress. Microcontrollers are constantly under signal frequency stress when controlling external devices. However, signal frequency stress has received relatively little attention in comparison with other sources of stress such as temperature, humidity, and voltage. This study involved the following steps: (1) identifying the highest stress point before failure; (2) dividing signal frequency into different stress levels; (3) characterizing the impact of signal frequency stress on IC functionality; (4) constructing a thermal profile of a microcontroller under signal frequency stress over time; (5) predicting stress levels using regression and neural network methods; and (6) comparing and contrasting performance differences for each method. Results indicated that the average prediction error is about 7.9% for the neural network approach and about 23.8% for the statistical regression approach. This may be due to the neural network modeling approach’s inherent ability to tolerate noise in the data due to factors such as variation in quality due to variations in the manufacturing process. This general methodology has also been utilized with low error rates in failure analysis and stress prediction in operational/power amplifiers (8% error rate), timer oscillator chips (25%) and resistors (30%).