Although linear filters are useful in a various applications in the context of speech processing, there are several evidences for existence of nonlinearity in speech signals. Our main aim is to launch a comprehensive investigation into the exploitation of nonlinear Volterra filters in the context of the ADPCM-based speech coding technique, using two methods of forward prediction, based on the LS criterion, and backward prediction, based on both LMS and RLS adaptation algorithms. In any case, after solving some innate problems, for example, ill-conditioning and instability, schemes for optimum exploitation of nonlinear prediction are developed and simulation results are provided, tested with several performance criteria. With forward prediction a scheme is developed to detect and flag those frames for which, after stabilizing, including the quadratic predictor is beneficial. Scalar and vector quantisation methods are used for quantising the residual signal and the filter parameters, respectively. The results show that using this scheme a negligible improvement (up to 0.62 dB in the SNR) can be achieved, in spite of the increase in bit rate and complexity. With backward prediction two frame-based schemes are developed in which for each frame, after examining a set of quadratic filters, the best filter in the sense of the best quality of the reconstructed speech is selected. The ultimate schemes result in an improvement of up to 1.5 dB in the overall SNR of the reconstructed speech at the cost of a slight increase in the bit-rate, a short delay and a demanding increase in the complexity.

No abstract

Wind turbines are increasingly expanding worldwide and Doubly‐Fed Induction Generator (DFIG) is a key component of most of them. Stator winding fault is a major fault in this equipment and its incipient detection is of vital importance. However, there is a paucity of research in this field. In this study, a novel machine learning‐based method is proposed for incipient detection of inter‐turn short‐circuit fault (ITF) in the DFIG stator based on the current signals of the stator. The proposed method makes use of state‐of‐the‐art deep learning methods along with conventional signal processing tools and general machine learning techniques. More specifically, the incipient fault detection problem is regarded as a multi‐class classification problem and a Long Short‐Term Memory network, which is more appropriate for time‐series data is utilised for inference. Furthermore, a variant of the celebrated Empirical mode Decomposition analysis tool is used to extract some well‐known statistical features among which the most informative ones are selected using a new feature selection method. Our tests using experimental data in steady‐state conditions show that the proposed method can accurately detect ITF fault at its initial stage when only one turn is shorted. Moreover, its performance is considerably higher than that of a variety of machine learning‐based methods.

No abstract

No abstract