Abstract
Acoustic emission monitoring is often used in the diagnosis of electrical and mechanical incipient faults in high voltage apparatus. Partial discharges are a major source of insulation failure in power transformers and the differentiation from other sources of acoustic emissions is of the utmost importance. Also, it is important to give an indication of the PD source location in order to obtain a useful diagnosis. This paper reports the developments in partial discharges source location through the associated acoustic emissions using three different algorithms.

Abstract
Partial discharges are a major source of insulation failure in electric power transformers. Their detection can be achieved through the associated acoustic emissions, and this work reports on the investigation of a fibre laser sensor based on a phase-shifted chirped fibre grating for acoustic emission detection in the power transformer environment. The performance of the sensing head is characterized and compared for different surrounding media: air, water and oil.

Abstract
Incipient fault diagnosis is closely related to isolation condition assessment. There are a great number of methods available for condition monitoring and diagnosis of power transformer isolation systems, but only few of them can take direct measurements inside the transformer. Fibre optic sensors can be applied to incipient fault diagnosis. In special, acoustic sensors are being developed for the detection and location of partial discharges in oil-filled power transformers. Towards such objective, this work reports investigation on the applicability of fibre Fabry-Perot interferometers for acoustic detection both in air and in liquids.

Abstract
This paper reports new results in adopting entropy concepts to the training of mappers such as neural networks to perform wind power prediction as a function of wind characteristics (mainly speed and direction) in wind parks connected to a power grid. Renyi's Entropy is combined with a Parzen Windows estimation of the error pdf to form the basis of three criteria (MEE, MCC and MEEF) under which neural networks are trained. The results are favourably compared with the traditional minimum square error (MSE) criterion. Real case examples for two distinct wind parks are presented.

Abstract
Prediction models for generation from renewables are needed in the context of a power system with a diversified portfolio. The presentation will discuss a new criterion and procedure to develop prediction models based on Renyils Entropy combined with Parzen windows (an approach named Information Theoretic Learning) that is applied to wind prediction and suggested as a better training paradigm for fuzzy or neural systems.

Abstract