Search

Condition monitoring of electrical insulation of high voltage apparatus is of much importance for the reliable operation of electric power systems. An effective way to monitor the health of such systems is the measurement of partial discharges (PDs) in the insulation material. In order to prevent the PD from progressing in the insulation material, the source of PD should be known. The PD classification problem in high voltage systems changes from a single-class to a multi-class and multi-label classification problem when PD sources take place simultaneously in real-life systems. Regardless of being single-label or multi-label, supervised learning has been employed for PD source classification by academics and researchers where labelled data and the number of PD sources are two prerequisites for the training process. What makes PD classification more complicated in real life scenarios is that the number of PD sources in an insulation system is unknown. This makes the problem of PD classification an unsupervised one, where there is no prior knowledge of the number of PD sources. Machine learning techniques offer a solution for PD classification by allowing to train models based on extracted features. The performance of such algorithms heavily depends on the choice of features. This can be overcome by using deep learning where feature extraction is done automatically by the algorithm, and the input to such an algorithm is the raw input data. This research is focused on developing deep learning models for the classification of PD sources in the insulation of high voltage systems. The developed models include: model for classifying multi-source PDs and single-source PDs without introducing multi-source PDs in the training stage, interpretable attention based model that propose non linear filters that are capable of differentiating between PD signals that look alike, and an unsupervised deep learning model for predicting the number of partial discharge sources. These mode

The ambitious goals of increasing the efficiency, performance and power densities of transportation drives cannot be met with compromises in the motor reliability. For the insulation specialists the challenge will be critical as the use of wide-bandgap converters (WBG, based on SiC and GaN switches) and the higher operating voltages expected for the next generation drives will enhance the electrical stresses to unprecedented levels. It is expected for the DC bus in aircrafts to reach 800 V (split +/-400 V) and beyond, driven by the urban air mobility sector and the need for electrification of electro-mechanical/electro-hydraulic actuators (an essential part of the "More Electric Aircraft" concept). Simultaneously the DC bus in electric vehicles (EV) traction motors is anticipated to increase up to 1200 V very soon. The electrical insulation system is one of the most delicate part of the machine in terms of failure probability. In particular, the appearance of partial discharges (PD) is disruptive on the reliability of the drive, especially under fast repetitive transients. Extensive experimental activity has been performed to extend the body of knowledge on PD inception, endurance under PD activity, and explore and identify new phenomena undermining the reliability. The focus has been concentrated on the impact of the WGB-converter produced waveforms and the environmental conditions typical of the aeronautical sector on insulation models. Particular effort was put in the analysis at the reduced pressures typical of aircraft cruise altitude operation. The results obtained, after a critical discussion, have been used to suggest a coordination between the insulation PD inception voltage with the converter stresses and to propose an improved qualification procedure based on the existing IEC 60034-18-41 standard., Gli obiettivi ambiziosi di aumentare l'efficienza, le prestazioni e le densità di potenza degli azionamenti per il trasporto non possono essere raggiunti con compromessi sulla affidabilità dei motori. Per gli specialisti dell'isolamento la sfida sarà cruciale, poiché sia l'uso di convertitori a wide-bandgap (WBG) basati su semiconduttori SiC e GaN, sia le tensioni operative più elevate previste per i prossimi azionamenti, aumenteranno gli stress elettrici a livelli senza precedenti. Si prevede che il bus DC negli aeromobili raggiunga gli 800 V (split +/-400 V) e oltre, sotto la spinta del settore della mobilità aerea urbana e dalla necessità di elettrificare gli attuatori elettromeccanici/elettroidraulici (parte essenziale del concetto di "More Electric Aircraft"). Contemporaneamente, si stima che presto nei motori per trazione di veicoli elettrici il DC bus aumenterà fino a 1200 V. Il sistema di isolamento elettrico è una delle parti più delicate di una macchina elettrica in termini di probabilità di guasto. In particolare, la comparsa di scariche parziali (PD) è deleteria per l'affidabilità dell'azionamento, soprattutto in presenza di transitori veloci e ripetitivi. In questa tesi è stata condotta un'ampia attività sperimentale per ampliare le conoscenze sull'innesco di PD, sulla resistenza dei materiali in loro presenza e per identificare nuovi fenomeni che compromettono l'affidabilità dell'isolante. L'attenzione si è concentrata sull'impatto che hanno le forme d'onda prodotte da convertitori WGB e le condizioni ambientali tipiche del settore trasporti su modelli di isolamento. Particolare impegno è stato profuso nell'analisi alle pressioni ridotte tipiche del funzionamento alle quote di crociera degli aerei di linea. I risultati ottenuti, dopo una discussione critica, sono stati utilizzati per suggerire un coordinamento tra le tensione di innesco di scarica e gli stress del convertitore, al fine di proporre una procedura di qualificazione migliorata basata sulla