Dissolved gas analysis in oil is an effective method for early fault diagnosis of transformers. Predicting the concentration of future characteristic gases in the transformer can assist operation and maintenance personnel in judging the operation trend of the transformer and ensure stable operation. In order to improve the prediction accuracy of dissolved gas in transformer oil based on a small number of samples, this paper proposes a VMD‐SMA‐LSSVM combined prediction model by using variational modal decomposition and least square support vector machine optimized by slime mold algorithm. First, use variational modal decomposition to decompose the gas signal. For each subsequence, a combined algorithm based on slime mold optimization and least square support vector machine is used to predict separately. Then the prediction results of each sub‐sequence are superimposed and reconstructed to obtain the final prediction value. The research results show that the prediction results obtained based on this method have better prediction effects than other models of machine learning models, other decomposition methods and optimization methods. The proposed method has good fitting characteristics when predicting seven characteristic gases, which verifies the effectiveness. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Cellulose insulation paper is an essential part of the transformer oil-paper insulation system, and many types of nano-modified insulating paper are available. For studying the effects of various nano-modified molecules on cellulose and the differences in performance, the pure cellulose model and polyoctaaminophenylsesquioxane and grafted 3-aminopropyltriethoxysilane (KH550) SiO2 and Al2O3 cellulose models were developed using molecular dynamics methods, and the mechanical properties and thermally stability were calculated and compared. The findings show that, in general, all three nano-modification models improved the thermal stability and mechanical properties, with nano-SiO2-KH550 cellulose having the best overall modification effect. In terms of mechanical properties, the nano-SiO2-KH550 cellulose showed the largest increase in compressive strength, with an 18.1% improvement. In terms of thermal stability, the KH550 grafted nano-silica/cellulose composite model showed the best modification effect, as evidenced by the smaller cohesive energy density and free volume region compressing the space between cellulose molecules, making the modified cellulose more compact internally, thus achieving the effect of inhibiting the movement of cellulose chains.

C4F7N, C5F10O, etc., as new environmental-friendly alternative gases decompose under partial discharge and produce a series of products such as CO, CF4, C2F6, C3F8, CF3CN, C2F5CN, and COF2. Based on the first-principles calculation method of density functional theory (DFT), the adsorption characteristics of intrinsic state graphene and Mo-doped graphene adsorbing SF6 and its substitute gas decomposition products are calculated and analyzed. By comparing the adsorption energy, adsorption distance, density of state, Mulliken charge population, charge transfer amount, and molecular orbital energy for adsorbing different decomposition gases, it can be seen that the system structure is the most stable when Mo is doped at the T site of the graphene surface. The adsorption of Mo-doped graphene on gas molecules is significantly stronger than that of intrinsic graphene, and the order of adsorption is: SO2F2 > H2S > SO2 > CF4. The adsorption of H2S gas molecules by intrinsic state and Mo-doped graphene is n-type adsorption, while the adsorption of SO2F2, CF4, and SO2 gas molecules is p-type adsorption. Mo-doped graphene can be used as a detection device for SO2F2 gas resistance sensors.