With the rapid advancement of Internet of Things (IoT) technology, the volume of sensor data collection has increased significantly. These data are typically presented in the form of time series, gradually becoming a crucial component of big data. Traditional time series analysis methods struggle with complex patterns and long-term dependencies, whereas deep learning technologies offer new solutions. This study introduces the U-TSS, a U-net-based sequence-to-sequence fully convolutional network, specifically designed for one-dimensional time series segmentation tasks. U-TSS maps input sequences of arbitrary length to corresponding sequences of class labels across different temporal scales. This is achieved by implicitly classifying each individual time point in the input time series and then aggregating these classifications over varying intervals to form the final prediction. This enables precise segmentation at each time step, ensuring both global sequence awareness and accurate classification of complex time series data. We applied U-TSS to geomagnetic field observation data for the detection of high-voltage direct current (HVDC) interference events. In experiments, U-TSS achieved superior performance in detecting HVDC interference events, with accuracies of 99.42%, 94.61%, and 95.54% on the training, validation, and test sets, respectively, outperforming state-of-the-art models in accuracy, precision, recall, F1-score, and AUC. Our code can be accessed openly in the GitHub repository at https://github.com/wangmengyu1/U-TSS.

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.