N-BIR: A NUMERIC OPTIMIZATION APPROACH FOR POWER ELECTRONIC CONVERTER BURN-IN TESTING TIME REDUCTION

Abstract

Burn-in testing is an effective method for detecting early faults in electronic products before they reach the market. This test has a high cost due to lengthy test time on a test bench. In this paper, we propose N-BIR (Numeric optimization approach for power electronic Burn-In testing time Reduction), an algorithm capable of predicting the burn-in (BI) test temperature of power electronic converters, intending to shorten the duration of such tests. This algorithm optimizes by least squares a theoretical model of the system, using as data a fraction of the total burn-in test. Moreover, not only is it capable of making accurate predictions, but it also accompanies them with a prediction interval (PI), so that the algorithm itself can quantify how confident it is of its predictions. We show that using 40% of a conventional rolling test total, our algorithm outperforms several of today's most common Machine Learning (ML) algorithms. Furthermore, we show that it can reduce burning time by 50% to 60% by making accurate predictions, which makes it possible to identify a significant portion of converters that don't require full testing, ultimately lowering costs and boosting productivity. Keywords: Burn-in temperature prediction, Burn-in time reduction, Levelized Cost of Energy, Machine Learning, Electronic Power Converter, Reliability.