Three-phase fault direction identification method for outgoing transmission line of DFIG-based wind farms

Doubly-fed induction generator(DFIG)-based wind farm has the characteristic of transient fault with low voltage ride through(LVRT)capability.A new three-phase fault direction identification method for the outgoing transmission line of the wind farm is presented.The ability of the new directional relay to differentiate between a three-phase fault in one direction or the other is obtained by using the increment of phase angle difference between the memory voltage signal and the fault current signal within a certain time,and using the amplitude variation of the fault current.It can be inferred that the fault current is supplied by the wind farm whether the phase angle differs or the current amplitude varies considerably.Different fault locations at the outgoing transmission line have been simulated by PSCAD/EMTDC to evaluate the reliability and sensitivity of the proposed technique.Results show that the new directional relay is of faster response when a three-phase fault occurs at the outgoing transmission line of a DFIG-based wind farm.

A Computer Graphics-Based Framework for 3D Pose Estimation of Pedestrians

In pedestrian-to-vehicle collision accidents,adapting safety measures ahead of time based on actual pose of pedestrians is one of the core objectives for integrated safety.It can significantly enhance the performance of passive safety system when active safety maneuvers fail to avoid accidents.This study proposes a deep learning model to estimate 3D pose of pedestrians from images.Since conventional pedestrian image datasets do not have available pose features to work with,a computer graphics-based(CG)framework is established to train the system with synthetic images.Biofidelic 3D meshes of standing males are first transformed into several walking poses,and then rendered as images from multiple view angles.Subsequently,a matrix of 50 anthropometries,10 gaits and 12 views is built,in total of 6000 images.A two-branch convolutional neural network(CNN)was trained on the synthetic dataset.The model can simultaneously predict 16 joint landmarks and 14 joint angles of pedestrian for each image with high accuracy.Mean errors of the predictions are 0.54 pixels and−0.06°,respectively.Any specific pose can then be completely reconstructed from the outputs.Overall,the current study has established a CG-based pipeline to generate photorealistic images with desired features for the training;it demonstrates the feasibility of leveraging CNN to estimate the pose of a walking pedestrian from synthesized images.The proposed framework provides a starting point for vehicles to infer pedestrian poses and then adapt protection measures accordingly for imminent impact to minimize pedestrian injuries.