2022 Vol.5 Dec.No4

• Title: 3D Forward Mapping of Power Grid Engineering with Integrated Deep Autoencoder
• Name: Adams Kelvin
• Company: International American University,USA
• Abstract:

   In order to improve the 3D forward mapping effect of power grid engineering, a 3D forward mapping method for power grid engineering based on integrated deep autoencoder was designed. Construct the data similarity matrix, use the encoder to extract the feature information from the input data, optimize the learning through the self-supervision mechanism to obtain the joint features of the data, use the deep auto-encoder to cluster the grid information, obtain the position encoding of the data points, and use the self-attention flag. The encoding layer of the relative position is processed, and the code stream is formed after encoding, and then the decoder is decoded at the decoding terminal. The loss function is used to measure the difference between the input data and the output data. After the measurement, the object list is planned and the equipment list is generated. List making model, carry out collaborative design, and realize 3D forward drawing of power grid engineering with integrated deep auto-encoder. The experimental results show that the proposed method can accurately draw power grid engineering images, and the deviation between the number of scenes returned and the actual number of scenes is small, and the drawing efficiency is also high, which effectively improves the three-dimensional forward drawing effect of power grid engineering.

  
  

• Keyword: integrated deep autoencoder; power grid engineering; 3D forward mapping; decoding; labeling; clustering;
• DOI: 10.12250/jpciams2022090516
• Citation form: Adams Kelvin.3D Forward Mapping of Power Grid Engineering with Integrated Deep Autoencoder [J]. Computer Informatization and Mechanical System,2022,Vol.5,pp.68-70

Reference

[1] Tongjia Research on 3D simulation calculation of overhead power line magnetic field based on BIM panoramic visualization [J] High voltage apparatus, 2020, 56 (3): 169-175.

[2] Yang Jiye, Yang Xiaozheng, Liu Ran, et al Visualization reconstruction technology of power grid data combined with graphic analog digital integration of GIS [J] Science and Technology Bulletin, 2020, 36 (4): 7:56-62.

[3] Yu Qun, Liu Qilin Three dimensional visual assessment of power system operation security situation based on L2 norm [J] Science, Technology and Engineering, 2020, 20 (19): 7704-7710.

[4] Kang Zhongjian, Li Changchao, Yu Hongguo, et al A method for identifying key transmission lines in power system [J] Electric power automation equipment, 2020, 40 (4): 63-70.

[5] Zhang Chi, Wu Dong, Wang Wei, et al Transformer fault diagnosis method based on variational self encoder preprocessing depth learning and DGA under unbalanced samples [J] China Southern Power Grid Technology, 2021, 15 (3): 68-74.

[6] Zhu Zhe, Xu Shaohua The neural network of depth convolution process for noise reduction self encoder and its application in time-varying signal classification [J] Computer Application, 2020, 40 (3): 698-703.

[7] Liao Mengke, Fan Bing, Li Zhongzheng, etc Information mining of equipment retirement in distribution network based on improved Apriori algorithm [J] Science, Technology and Engineering, 2021, 21 (24): 10381-10386.

[8] Ling Xiaobo, Ye Kang, Hu Youlin, et al Design of power monitoring data application model based on laser 3D scanning equipment panorama [J] Laser Journal, 2020, 41 (7): 213-217.

[9] Wang Huaiyuan, Chen Qifan Transient stability assessment method based on cost sensitive stacked variational automatic encoder [J] Chinese Journal of Electrical Engineering, 2020, 40 (7): 2213-2220.

[10] Fei Yan, Miao Qianyun, Liu Xuejun A recommendation system attack detection method based on convolutional automatic encoder [J] Mini microcomputer system, 2021, 42 (5): 1088-1092.

[11] Sun Shengzi, Guo Binghui, Yang Xiaobo Embedded consensus automatic encoder for multimodal semantic analysis [J] Computer Science, 2021, 48 (7): 93-98.

[12] Lu Dan, Zhang Zhongqing, Yu Xiaopeng, et al Research on architecture and function of power grid operation risk management and control visualization system [J] Journal of Nanjing University of Science and Technology, 2020, 44 (1): 87-93.

[13] Zhang Shuqing, Duan Xiaoning, Zhang Liguo, et al The application of Tsne reduced dimension visual analysis and moths flame optimization ELM algorithm in power load forecasting [J] Chinese Journal of Electrical Engineering, 2021, 41 (9): 3120-3129.

[14] Yan Qingguo, Ma Shengkun, Chen Li, et al Research on Archiving Management of 3D Design Results of Electric Power Enterprises [J] Archives of China, 2021 (10): 62-63.

[15] Peng Hui, Wu Tao, Shi Haoqiu, et al Multi active data synchronization design and implementation of the analysis and decision center of the new generation power grid regulation system [J] Power System Automation, 2020, 44 (16): 98-104.