Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. A significant part of generator diagnosis relies on Partial Discharge (PD) measurements, because the main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. A study of all stator failure mechanisms reveals that more than 85 % of them involve the presence of PD activity. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Québec has been collecting more than 33 000 unlabeled PD measurement files over the last decades. Up to now, this diagnostic technique has been quantified based on global PD amplitudes and integrated PD energy irrespective of the source of the PD signal. Several PD sources exist and they all have different relative risk, but in order to recognize the nature of the PD, or its source, the judgement of experts is required. In this paper, we propose a new method based on visual data analysis to build a PD source classifier with a minimum of labeled data. A convolutional variational autoencoder has been used to help experts to visually select the best training data set in order to improve the performances of the PD source classifier.

The exploration/exploitation balance is a major concern in the control of evolutionary algorithms (EAs) performance. Exploration is associated with the distribution of individuals on a landscape, and can be estimated by a genotypic diversity measure (GDM). In contrast, exploitation is related to individual responses, which can be described with a phenotypic diversity measure. Many diversity measures have been proposed in the literature without a comprehensive study of their differences. This paper looks at surveys of GDMs published over the years for real-coded representations, and compares them based on a new benchmark, one that allows a better description of their behavior. The results demonstrate that none of the available GDMs is able to reflect the true diversity of all search processes. Nonetheless, the normalized pairwise diversity measurement proves to be the best genotypic diversity measurement for standard EAs, as it shows nondominated behavior with respect to the desired GDM requirements.