Simulative investigation of wind turbine gearbox loads during power converter fault

Three phase short circuit power converter faults in wind turbines (WT) result in highly dynamic generator torque reversals, which lead to load reversals within the drivetrain. Dynamic load reversals in combination with changing rotational speeds are, for example, critical for smearing within roller bearings. Therefore, an investigation of the correlation between three phase short circuit converter faults and drivetrain component failures is necessary.Due to the risk of damage and the resulting costs, it is not economically feasible to extensively investigate three phase short circuit converter faults on test benches. Valid WT drivetrain models can be used instead. A WT drivetrain model, which has been developed and validated in a national project at the CWD, is used and a three phase short circuit converter fault is implemented. In this paper, the resulting torque load on the drivetrain for a three phase short circuit converter fault in rated power production is presented. This converter fault leads to a highly dynamic reversing electromagnetic torque which exceeds the rated torque by a factor of three. As a result the load on the rotor side high speed shaft (HSS) bearing oscillates and increases by around 15 per cent compared to rated power production. Simultaneously the rotational velocity of the HSS oscillates with an amplitude of 10 rpm. Therefore an increase in the risk of smearing is expected.

Learning Dynamic Generator Model by Alternating Back-Propagation through Time

This paper studies the dynamic generator model for spatialtemporal processes such as dynamic textures and action sequences in video data. In this model, each time frame of the video sequence is generated by a generator model, which is a non-linear transformation of a latent state vector, where the non-linear transformation is parametrized by a top-down neural network. The sequence of latent state vectors follows a non-linear auto-regressive model, where the state vector of the next frame is a non-linear transformation of the state vector of the current frame as well as an independent noise vector that provides randomness in the transition. The non-linear transformation of this transition model can be parametrized by a feedforward neural network. We show that this model can be learned by an alternating back-propagation through time algorithm that iteratively samples the noise vectors and updates the parameters in the transition model and the generator model. We show that our training method can learn realistic models for dynamic textures and action patterns.

Feature Adaptive and Cyclic Dynamic Learning Based on Infinite Term Memory Extreme Learning Machine

Online learning is the capability of a machine-learning model to update knowledge without retraining the system when new, labeled data becomes available. Good online learning performance can be achieved through the ability to handle changing features and preserve existing knowledge for future use. This can occur in different real world applications such as Wi-Fi localization and intrusion detection. In this study, we generated a cyclic dynamic generator (CDG), which we used to convert an existing dataset into a time series dataset with cyclic and changing features. Furthermore, we developed the infinite-term memory online sequential extreme learning machine (ITM-OSELM) on the basis of the feature-adaptive online sequential extreme learning machine (FA-OSELM) transfer learning, which incorporates an external memory to preserve old knowledge. This model was compared to the FA-OSELM and online sequential extreme learning machine (OSELM) on the basis of data generated from the CDG using three datasets: UJIndoorLoc, TampereU, and KDD 99. Results corroborate that the ITM-OSELM is superior to the FA-OSELM and OSELM using a statistical t-test. In addition, the accuracy of ITM-OSELM was 91.69% while the accuracy of FA-OSELM and OSELM was 24.39% and 19.56%, respectively.