Search

Advances in technology have facilitated the development of lightning research and data processing. The electromagnetic pulse signals emitted by lightning (LEMP) can be collected by very low frequency (VLF)/low frequency (LF) instruments in real time. The storage and transmission of the obtained data is a crucial link, and a good compression method can improve the efficiency of this process. In this paper, a lightning convolutional stack autoencoder (LCSAE) model for compressing LEMP data was designed, which converts the data into low-dimensional feature vectors through the encoder part and reconstructs the waveform through the decoder part. Finally, we investigated the compression performance of the LCSAE model for LEMP waveform data under different compression ratios. The results show that the compression performance is positively correlated with the minimum feature of the neural network extraction model. When the compressed minimum feature is 64, the average coefficient of determination R 2 of the reconstructed waveform and the original waveform can reach 96.7%. It can effectively solve the problem regarding the compression of LEMP signals collected by the lightning sensor and improve the efficiency of remote data transmission. [ABSTRACT FROM AUTHOR]

With the increase of complexity of Computer-Aided Engineering (CAE) models and practical problems, the evaluation cost of sheet forming simulation is commonly expensive. Surrogate models have been employed for efficient evaluations but trouble the problem of inverse scattering. Moreover, the accuracy of the forming evaluation based on the widely used Forming Limit Diagram (FLD) is influenced by the non-working regions. In this study, image-processing techniques are employed. Simultaneously, two novel image-driven Generative Inverse Networks (GINs) are proposed to improve the sheet-forming design's efficiency and accuracy. Through validations, GIN Version d (GIN-Vd) is more efficient and can obtain higher accuracy. However, because the desired optimum should be given in advance, such applications might be limited. In comparison, the GIN Version g (GIN-Vg) is more flexible. [ABSTRACT FROM AUTHOR]

• A novel lightning geolocation method for single-site is proposed. • The SLL-ResNet including three feature extraction branches and a feature fusion network is employed to locate lightning. • The model achieves a prediction error of 2.75–13.08% for the propagation distance of LEMP within a range of 1000 km. • The SLL-ResNet is available for all types of LEMP signals. A single-site lightning electromagnetic pulse (LEMP) localization approach based on deep learning was proposed and practiced. The approach was based on a large amount of ground-based lightning location and waveform data in the VLF/LF frequency band. A model for predicting the propagation distance of LEMP based on a deep learning method was proposed. The model used multiple types of LEMP waveform data as well as location data for parameter learning. The new model for detecting lightning activity has been validated against ADTD systems. The verification results for thunderstorms in the range of 1000 km show that the relative error of the model for the prediction of signal propagation distance was 2.75–13.08%. Affected by the azimuth calculation error, the relative error of single-site geolocation was 4.91–15.26%. [ABSTRACT FROM AUTHOR]

Lightning waveform plays an important role in lightning observation, location, and lightning disaster investigation. Based on a large amount of lightning waveform data provided by existing real-time very low frequency/low frequency (VLF/LF) lightning waveform acquisition equipment, an automatic and accurate lightning waveform classification method becomes extremely important. With the widespread application of deep learning in image and speech recognition, it becomes possible to use deep learning to classify lightning waveforms. In this study, 50,000 lightning waveform samples were collected. The data was divided into the following categories: positive cloud ground flash, negative cloud ground flash, cloud ground flash with ionosphere reflection signal, positive narrow bipolar event, negative narrow bipolar event, positive pre-breakdown process, negative pre-breakdown process, continuous multi-pulse cloud flash, bipolar pulse, skywave. A multi-layer one-dimensional convolutional neural network (1D-CNN) was designed to automatically extract VLF/LF lightning waveform features and distinguish lightning waveforms. The model achieved an overall accuracy of 99.11% in the lightning dataset and overall accuracy of 97.55% in a thunderstorm process. Considering its excellent performance, this model could be used in lightning sensors to assist in lightning monitoring and positioning. [ABSTRACT FROM AUTHOR]