Fault Diagnosis of Advanced Wind Turbine Benchmark using Interval-based ARRs and Observers

Abstract

Abstract-This paper proposes a model-based fault diagnosis approach for wind turbines and its application to a realistic wind turbine fault diagnosis benchmark. The proposed fault diagnosis approach combines the use of analytical redundancy relations (ARRs) and interval observers. Interval observers consider an unknown but bounded description of the model parametric uncertainty and noise using the the so-called set-membership approach. This approach leads to formulate the fault detection test by means of checking if the measurements fall inside the estimated output interval, obtained from the mathematical model of the wind turbine and noise/parameter uncertainty bounds. Fault isolation is based on considering a set of ARRs obtained from structural analysis of the wind turbine model and a fault signature matrix that considers the relation of ARRs and faults. The proposed fault diagnosis approach has been validated on a 5MW wind turbine using the NREL FAST simulator. The obtained results are presented and compared with other approaches proposed in the literature.Index Terms-Analytical redundant relations, interval-based observers, model-based fault diagnosis, wind turbines.

A deep learning-based intelligent online warning method for gear wear damage based on oil vibration

“…This section introduces the long and STM-based neural network, which is utilized to extract features from the vibration signal raw data collected from the gear full-life acceleration experiment [3]. In response to the traditional feature extraction method that relies on personnel's professional knowledge and manually extracts features from the raw data, which is difficult to handle complex fault information, this article uses CNN to extract features from the vibration raw data and input them into LSTM for calculation [4]. From a data perspective, automatic learning of data features eliminates the impact of noise on the data and improves the impact of manual feature extraction on the results in traditional feature extraction methods.…”