Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems

In modern design of power electronic converters, reliability of dc-link capacitors is one of the critical considered aspects. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. However, the existing condition monitoring methodologies are rarely adopted by industry due to shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of new condition monitoring methodologies that are based on advanced software and requires no extra hardware could be more attractive to industry. In this digest, a condition monitoring methodology that estimates the capacitance value of the dc-link capacitor in a three phase Front-End diode bridge motor drive is proposed. The proposed software methodology is based on Artificial Neural Network (ANN) algorithm. The harmonics of the dc-link voltage are used as training data to the Artificial Neural Network. Fast Fourier Transform (FFT) of the dc-link voltage is analysed in order to study the impact of capacitance variation on the harmonics order. Laboratory experiments are conducted to validate the proposed methodology and the error analysis of the estimated results is also studied.