Swin-RGC: Swin-Transformer with Recursive Gated Convolution for substation equipment non-rigid defect detection

Gated Recurrent Convolution Neural Network for OCR

Optical Character Recognition (OCR) aims to recognize text in natural images. Inspired by a recently proposed model for general image classification, Recurrent Convolution Neural Network (RCNN), we propose a new architecture named Gated RCNN (GRCNN) for solving this problem. Its critical component, Gated Recurrent Convolution Layer (GRCL), is constructed by adding a gate to the Recurrent Convol...

Using Evidence Combination for Transformer Defect Diagnosis

This paper describes a number of methods of evidence combination, and their applicability to the domain of transformer defect diagnosis. It explains how evidence combination fits into an on-line and implemented agent-based condition monitoring system, and the benefits of giving selected agents reflective abilities. Reflection has not previously been deployed in an industrial setting, and theore...

Power-frequency magnetic field calculation around an indoor transformer substation

The authors propose a full three-dimensional (3D) calculation model based on a multipole technique able to predict the magnetic field pollution outside of indoor medium voltage/low voltage (MV/LV) transformer substations. The authors demonstrate that the proposed model may be advantageously used in all problems related to the characterization of the electromagnetic environment around a MV/LV tr...

Rotating Equipment Defect Detection Using the Algorithm of Mode Isolation

Non-Rigid Summing of Gated PET Via Optical Flow

A method for summing together datasets from gated cardiac PET acquisitions is described. Optical flow techniques are used to accurately model non-rigid motion present during the cardiac cycle so that a one-to-one mapping is found between each voxel of two gated volumes. Using this mapping, image summing can take place, producing a composite dataset with improved statistics and reduced motion-in...