The utilisation of conventional industrial converters for development of doubly‐fed induction generator (DFIG) test facilities poses an attractive prospect as it would provide proprietary commercial protection and functionality. However, standard commercial converters present significant challenges in attainable DFIG operational capability. This is due to the fact that they are designed for execution of a limited set of pre‐programmed common control modes. They typically do not cater for execution of complicated stator flux‐oriented vector control (SFOC) schemes required for DFIG drive control. The research work presented in this study reports a methodology that enables effective implementation of SFOC on industrial converters through a dedicated external real‐time platform and a velocity/position communication module. The reported scheme is validated in laboratory experiments on an experimental DFIG test‐rig facility. The presented principles are general and are therefore applicable to conventional DFIG drive architectures utilising standard industrial converters.

this study explores the potential for using FBG strain sensing to enable recognition of the shaft misalignment condition in electric machine drivetrains through observation of machine frame distributed relative strain. The sensing principles, design and installation methods of the proposed technique are detailed in the paper. The scheme was applied on a purpose built wind turbine generator representative laboratory test rig and its performance evaluated in an extensive experimental study involving a range of healthy and misaligned shaft operating conditions. The obtained experimental data demonstrate the reported method’s capability to enable recognition of generator shaft misalignment conditions and thus its health monitoring. Finally, it is shown that the thermal variation of the generator frame structure inherent to its operation, combined with the FBG sensor intrinsic thermo-mechanical cross sensitivity, has no detrimental impact on the fidelity and usability of the observed strain measurements.

With a continued strong increase in wind generator applications, the condition monitoring of wind turbine systems has become ever more important in ensuring the availability and reduced cost of produced power. One of the key turbine conditions requiring constant monitoring is the generator shaft alignment, which if compromised and untreated can lead to catastrophic system failures. This study explores the possibility of employing supervised machine learning methods on the readily available generator controller loop signals to achieve detection of shaft misalignment condition. This could provide a highly noninvasive and low-cost solution for misalignment monitoring in comparison with the current misalignment monitoring field practice that relies on invasive and costly drivetrain vibration analysis. The study utilises signal datasets measured on a dedicated doubly fed induction generator test rig to demonstrate that high consistency and accuracy recognition of shaft angular misalignment can be achieved through the application of supervised machine learning on controller loop signals. The average recognition accuracy rate of up to 98.8% is shown to be attainable through analysis of a key feature subset of the stator flux-oriented controller signals in a range of operating speeds and loads.