Operating characteristic information extraction of flood discharge structure based on complete ensemble empirical mode decomposition with adaptive noise and permutation entropy

Abstract

It remains a major issue to assess health condition and degree of vibration damage of flood discharge structure by working features in recent years. In the process of acquisition and transmission, because vibration signals are susceptible to interference from high-frequency white noise and low-frequency water flow noise, they are usually shown in the form of nonstationary random signals with low signal to noise ratio. Modal information is hard to be precisely recognized as the character of structural vibration is drowned into the strong noise. In order to remove the noise and preserve structural characteristic information, a new characteristic information extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) entropy (CEEMDAN-PE) is proposed. Firstly, the vibration signal is decomposed into a series of intrinsic mode functions (IMFs) by CEEMDAN, and then low-frequency water flow noise can be filtered out through spectrum analysis of each IMF component. Secondly, the noise degree of each IMF is determined by permutation entropy and high-frequency noise in IMFs is filtered out by singular value decomposition. Finally, the noise elimination IMFs are reconstructed to obtain the operating characteristic information of flood discharge structure. The effectiveness of the proposed method on characteristic information extraction is validated by a simulation experiment. Furthermore, the proposed method was applied to the 5th overflow section of Three Gorges Dam and the analysis results show that the CEEMDAN-PE method can effectively remove the noise and extract dominant frequencies of flood discharge structure, which provides foundation for health monitoring and damage identification of flood discharge structure with a strong engineering practicability.

Flood Prediction Using Machine Learning Models: Literature Review

“…Ouyang et al [145] and Zhang et al [146] presented a review of the applications of ensemble ML methods used for floods. EPSs were demonstrated to have the capability for improving model accuracy in flood modeling [140][141][142][143][144][145][146] To improve the accuracy of import data and to achieve better dataset management, the ensemble mean was proposed as a powerful approach coupled with ML methods [140,141]. Empirical mode decomposition (EMD) [142], and ensemble EMD (EEMD) [143] are widely used for flood prediction [144].…”

“…Nevertheless, EMD-based forecast models are also subject to a number of drawbacks [145]. The literature includes numerous studies on improving the performance of decomposition and prediction models in terms of additivity and generalization ability [146].…”

Flood Prediction Using Machine Learning, Literature Review

“…Ouyang et al [145] and Zhang et al [146] presented a review of the applications of ensemble ML methods used for floods. EPSs were demonstrated to have the capability for improving model accuracy in flood modeling [140][141][142][143][144][145][146] To improve the accuracy of import data and to achieve better dataset management, the ensemble mean was proposed as a powerful approach coupled with ML methods [140,141]. Empirical mode decomposition (EMD) [142], and ensemble EMD (EEMD) [143] are widely used for flood prediction [144,145].…”

“…Nevertheless, EMD-based forecast models are also subject to a number of drawbacks (Huang et al, 2014). The literature includes numerous studies on improving the performance of decomposition and prediction models in terms of additivity and generalization ability [146].…”

Flood Prediction Using Machine Learning, Literature Review

“…Nevertheless, the EMD-based forecast models are also subjected a number of drawbacks (Huang et al, 2014). Literature includes numerous research on improving the performance of decomposition and prediction models in terms of performance, additivity and generalization ability [123].…”