Search

An interpretable convolutional neural network model is proposed for the classification of very low frequency and low frequency lightning electric field waveforms. This model adopts multi‐scale convolutional kernels and shortcut connections to enhance the ability of lightning waveform classification. Based on the data recorded from five provinces in China, the proposed model achieves an accuracy of 98.56% for a four‐type classification task including return strokes, the intra‐cloud lightning, preliminary breakdown, and narrow bipolar events. The proposed model is validated with another open‐source data set from Argentina with an accuracy of 98.45%, which shows good robustness. To ensure the classification, the features learned by the model are visualized. The class activation mapping (CAM) method is adopted to visualize the class‐specific contribution of different waveform parts by using the feature maps of the final convolutional layer. It is highlighted by the CAM method that the proposed model focuses on waveform parts that align with those areas of interests identified by human experts. The high‐contribution waveform parts are furtherly analyzed, which indicate that the proposed model possesses the capability to associate waveform features with the corresponding lightning discharge processes. Plain Language Summary: Electromagnetic waveforms in very low frequency and low frequency bands are usually used to detect and locate lightning activities. Traditional waveform classification methods have difficulties in distinguishing multiple types of lightning waveforms. Although machine learning models have great potential in multi‐type waveform classification tasks, these models rely on the features proposed by human experts and cannot capture the features of different scales in lightning waveforms. To this end, this paper proposes an improved convolution neural network model, which incorporates modifications to the model structure to better suit the lightning waveform classification task. The data set for model training comes from five provinces in China and contains different meteorological conditions. The proposed model achieves a classification accuracy of 98.56% on this data set and 98.45% on an open‐source data set from Argentina. Meanwhile, the classification process is interpretable by visualizing the convolution outputs. The analysis of the visualization results shows that the high performance of the proposed model is reliable for its ability to focus on waveform parts that align with areas of interests identified by human experts. A closer inspection of these waveform parts suggest that the proposed model possesses the capability to associate waveform features with the corresponding lightning discharge processes. Key Points: The proposed model achieves an accuracy of 98.56% for a four‐type lightning waveform classification task and shows good robustnessThe model is interpretable by visualizing the contribution of different waveform parts to the classification resultsThe proposed model aligns with human‐expert classifications and suggests potential to link waveform features with lightning processes [ABSTRACT FROM AUTHOR]

We provide the clearest experimental evidence to date that positive leader velocity decreases with the decline of air density in the troposphere. The experiments are conducted at altitudes of 4,300 m in Tibet and 53 m in Beijing using the long air gap discharge technique. Rigorous comparative studies are performed using synchronized measurement of positive leader velocity and current under different air densities and similar temperature and humidity conditions. The effect of reduced air density on positive leader velocity is analyzed with a detailed thermal‐hydrodynamic model. It is found that the widely used similarity law setting initial leader radius inversely proportional to air density does not hold in estimating positive leader speeds in the troposphere. Plain Language Summary: The effect of reduced air density on leader discharge is a fundamental concern in several subjects such as lightning physics, atmospheric electricity, and electrical engineering. Increasing observation results have shown that lightning leaders seem to propagate slower at higher altitudes. To rigorously investigate the effect of reduced air density on positive leader velocity, electrical discharge experiments were performed at an altitude of 4,300 m in Tibet under the basis of excluding other influencing factors, such as discharge current and other atmospheric conditions. By comparing measurements near sea level and at high altitudes under similar temperature and humidity conditions, we provide reliable evidence to confirm that the positive leader velocity decreases with the decline of air density. Based on a thermal‐hydrodynamic model, it is found that the leader velocity calculated with the use of similarity law deviates significantly from the experimental measurements. A revised scaling formula for the initial conditions of leader stem at reduced air density is proposed. Our work can motivate scientists to revisit the use of similarity law in analyzing lightning discharges and upper‐atmospheric discharges such as gigantic jets. Key Points: We report a rigorous experimental study confirming that positive leaders propagate slower at higher altitudesBased on an improved thermal‐hydrodynamic model, the effect of air density on leader velocity is discussedOur study indicates that the similarity law for leader radius needs to be revised for electrical discharges in the troposphere [ABSTRACT FROM AUTHOR]

The unified power flow controller (UPFC) is the third generation of flexible AC transmission systems. It can control the power flow and voltage of the power system quickly and flexibly that has an advantage in compensating the AC transmission system in real time. The world's first 500 kV UPFC project is under construction in Jiangsu Province of China. On the paralleled converter side, it is connected to the 500 kV Mudu substation by using a gas insulated transmission line, and the series converter side is connected to the 500 kV Meili substation through a 500 kV double-circuit overhead transmission line. In order to optimise insulation design of the UPFC system and ensure the safety operation of the power system, it is essential to analyse the characteristics of lightning overvoltage. Considering the invaded path of lightning surges in the UPFC system, a detailed model was established by using Electro-Magnetic Transient Program/Alternative Transients Program in this study. The lightning overvoltage level at key nodes of the UPFC system was presented. The check calculation for the configuration and protection level of ZnO arresters were also carried out. The obtained results can provide a reference for insulation coordination design of the 500 kV UPFC project. [ABSTRACT FROM AUTHOR]

The ±1100 kV Zhundong–Wannan ultra high-voltage direct current (UHVDC) transmission project is under construction in China, which has the highest operating voltage in the world. The length of the UHVDC overhead transmission line is greater than 3000 km. The electromagnetic transient process caused by grounding faults might have significantly impact on the overvoltage level of DC transmission line, which is crucial for the external insulation configuration of the overhead transmission line. This paper presents a detailed electromagnetic transient simulation model for the UHVDC transmission system using an open-loop extinction angle control principle. The simulation results demonstrate that the single pole grounding fault into a bipolar system causes the most serious damage. The maximum overvoltage is 1.628 p.u. and the 2% statistic overvoltage is 1.635 p.u., while the reference value is 1122 kV. The influence of DC filters for line overvoltage is also analysed here. Furthermore, results show that adding a no gap line arrester at the midpoint of transmission line can suppress line overvoltage, while the maximum overvoltage reduces by 0.138 p.u. The results obtained provides a reference for the optimisation of the external insulation configuration. [ABSTRACT FROM AUTHOR]