Full
Outline
We propose an outlier detection method for dam deformation based on ensemble empirical mode decomposition (EEMD) high-frequency differential conversion and gated recurrent unit (GRU) analysis. First, the EEMD technology is employed to decompose the original deformation monitoring data, yielding deformation components at different frequencies. Then, high-frequency components containing abnormal deformation information can be extracted for differential sequence conversion, and identification criteria for abnormal single-jump points are proposed. Finally, a high-frequency component time series model is established by GRU neural networks, which is then combined with the abnormal single-jump point identification pattern to recognize outliers. The results show that EEMD technology and high-frequency sequence differential conversion can effectively isolate deformation anomaly information. The proposed single-jump point detection model aligns with the characteristics of dam deformation anomalies. Combining GRU and the 3σ criterion for time series modeling analysis of differential sequences, all deformation anomalies can be accurately identified, and achieve higher accuracy than traditional methods.
26
10
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
