HVDC-DNN-MFO: Classifying High-Voltage Direct Current Interference Events in Geomagnetic Field Observation Data Using Deep Neural Network and Moth-Flame Optimization Algorithm

Abstract

Geomagnetic field observation data are valuable resources for seismic geomagnetic research. However, the construction of subways, light railroads, and high-voltage direct current transmission lines in recent years has seriously affected the output data of geomagnetic field observation instruments. To accurately and efficiently classify high-voltage direct current interference events in geomagnetic field observation data, this paper proposed a novel model named HVDC-DNN-MFO. This model integrated convolutional neural network, convolutional block attention module, and the gated recurrent unit, a variant of recurrent neural network, to automatically extract fine features of high-voltage direct current interference events. Additionally, the moth-flame optimization algorithm was introduced to optimize the model’s hyperparameters. This study used manually pre-processed records of high-voltage direct current interference events and the z-component second data of geomagnetic field observation data from January 1, 2014, to January 1, 2019, to make samples, and the homothetic transformation method was applied to unify the length of high-voltage direct current samples with different duration events to 7200s. The experimental results demonstrated that the F1-score, accuracy rate, and recall rate of the HVDC-DNN-MFO model proposed in this study reached 0.99, 99.05%, and 98.59%, respectively, outperforming the state-of-the-art methods.

Keywords

• High-voltage direct current interference events
• time series classification
• deep neural network
• moth-flame optimization