Open Access

Multi-scale spatio-temporal data modelling and brain-like intelligent optimisation strategies in power equipment operation and inspection

Guoliang Zhang

Guoliang Zhang

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Zhang, Guoliang
, 
Peng Zhang

Peng Zhang

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Zhang, Peng
, 
Fei Zhou

Fei Zhou

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Zhou, Fei
, 
Qingyu Kong

Qingyu Kong

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Kong, Qingyu
, 
Xiaoyu Fan

Xiaoyu Fan

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Fan, Xiaoyu
, 
Zongbo Chu

Zongbo Chu

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Chu, Zongbo
 and 
Weishang Xia

Weishang Xia

China Electric Power Research Institute Co., LtdBeijing, China
Search for this author on
Sciendo|Google Scholar
Xia, Weishang
  
Feb 03, 2025
Multi-scale spatio-temporal data modelling and brain-like intelligent optimisation strategies in power equipment operation and inspection's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Feb 03, 2025
Received: Oct 03, 2024
Accepted: Jan 07, 2025
DOI: https://doi.org/10.2478/amns-2025-0022
Keywords
© 2025 Guoliang Zhang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

The sample distribution of the fusion eigenvalue
The sample distribution of the fusion eigenvalue

Figure 2.

The GPNN generates the fault sample sequence
The GPNN generates the fault sample sequence

Figure 3.

Change of accuracy rate and loss value during training
Change of accuracy rate and loss value during training

Figure 4.

Comparison results of fault diagnosis model
Comparison results of fault diagnosis model

The process data of FID

Type 50 100 200 500 Min value
Nor 263.08 104.23 33.43 37.24 33.43
IR 285.31 112.58 36.04 35.89 35.89
OR 272.64 80.21 51.71 31.27 31.27
Cage 272.11 98.96 39.92 25.35 25.35
IR-OR 301.17 116.64 30.58 32.58 30.58
TCF 248.05 102.42 40.65 21.16 21.16

Partial fusion eigenvectors

Mode No. PCA1 PCA2 PCA3 PCA4 PCA5 PCA6
Nor 1 4218.51 -425.69 469.62 65.24 22.37 -9.58
2 4369.25 -334.14 285.26 158.37 -1.67 -3.67
… … … … … … …
400 4301.48 -438.49 468.04 115.12 22.37 -1.54
IR 1 -1024.74 -1135.24 -421.56 356.37 -2.85 -2.68
2 -1158.37 -1166.34 -357.08 285.47 -28.74 16.76
… … … … … … …
400 -2368.45 -1108.58 148.27 206.54 -29.24 17.51
OR 1 -246.37 -583.24 -390.54 -108.03 -78.51 32.28
2 241.15 -556.13 -198.47 -283.51 -62.35 -1.19
… … … … … … …
400 -438.24 -250.45 -278.42 -175.42 -81.49 28.94
Cage 1 -1232.74 4538.92 546.84 84.95 -58.51 36.51
2 -22.51 1847.37 -661.52 105.24 -38.42 4.47
… … … … … … …
400 -505.75 2347.78 -88.18 -233.51 -56.43 5.74
IR-OR 1 885.42 -173.27 -685.52 -80.35 48.53 -65.28
2 336.74 -246.81 -473.51 -37.24 135.82 -13.27
… … … … … … …
400 -303.16 312.33 -228.09 -33.08 162.68 -71.18
TCF 1 -2551.34 -1265.67 695.87 -143.27 3.85 -31.33
2 -1247.12 -1431.08 396.76 -31.06 -7.42 -21.04
… … … … … … …
400 -2351.39 -1435.87 485.27 -17.24 7.38 -21.28
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed