A New Data-Driven Approach for Power IGBT Remaining Useful Life Estimation Based On Feature Reduction Technique and Neural Network

Abstract

The insulated gate bipolar transistor (IGBT) is a crucial component of power converters (PCVs) and is commonly used in several PCVs topologies. On the other hand, the investigation and the study of the IGBT component show several changes within its behavior and lifetime, while this component is highly influenced by the operating conditions. Indeed, the monitoring of this component is necessary to minimize unexpected downtime of the wind energy system (WES). However, an accurate prediction of IGBTs remaining useful life (RUL) is the key enabler for life-time-optimized operation. Consequently, this work proposes a new prognostic approach for online IGBTs monitoring that adopts the time-domain analysis to extract useful information that is used as an input in the generation of the health indicator. Moreover, this approach is based on combining both of principal component analysis (PCA) technique and the feedforward neural network (FFNN) technique. PCA is used to reduce features extracted from IGBTs and the FFNN is implemented to achieve online regression of the trend parameter obtained from the PCA technique. To investigate and evaluate the performance of our idea we used the NASA Ames Laboratory Prognostics Center of Excellence IGBTs accelerated aging database. Finally, the achieved results clearly show the strength of the new trend parameter for IGBTs RUL prediction. The most notable strong correlation within the proposed approach is in relation to accuracy value, with an acceptable average accuracy rate of 60.4%.

An Integrated Cost-Aware Dual Monitoring Framework for SMPS Switching Device Diagnosis

“…Often, time-domain and frequency-domain signal processing techniques provide underlying features that can be linked to varying component conditions. The frequencydomain outputs-spectra (or electrical fingerprints) often present component conditions in a range of characteristic frequencies with different magnitudes which change as the component condition changes [26]; however, a major setback of this technique is that it functions on the assumption that the signals are stationary and requires a short period (a less than a second) of a signal for reliable analyses. These limitations render it less optimal for cases where fluctuations are witnessed in the electrical signals (high nonstationarity).…”

A Comparison of Modern Heating Methods to Reduce a Heat Treater’s CO2 Carbon Footprint

“…IGBTs are also used in power converters used in wind turbines and have been studied extensively due to reliability issues [7]. As a result, there is currently significant investment in analytics to help identify the remaining useful life of these items to enable timely replacement and avoid turbine shutdowns for excessive periods.…”

Lifetime prediction of IGBT based on empirical wavelet transform combined with long short term memory network model

“…The prediction idea is simple, and the implementation process is easy. Ismail et al [10,11] used V CE as characteristic information for IGBT lifetime prediction and calculated nine time-domain characteristic information such as the average value, standard deviation, and peak value of V CE . The principal component analysis method is used to reduce the dimension of the characteristic information, and the reduced data is used as the prediction data for IGBT remaining useful life, using neural networks to predict its lifespan.…”