An Integrated Machine Learning Algorithm for Separating the Long-Term Deflection Data of Prestressed Concrete Bridges

Abstract

Deflection is one of the key indexes for the safety evaluation of bridge structures. In reality, due to the changing operational and environmental conditions, the deflection signals measured by structural health monitoring systems are greatly affected. These ambient changes in the system often cover subtle changes in the vibration signals caused by damage to the system. The deflection signals of prestressed concrete (PC) bridges are regarded as the superposition of different effects, including concrete shrinkage, creep, prestress loss, material deterioration, temperature effects, and live load effects. According to multiscale analysis theory of the long-term deflection signal, in this paper, an integrated machine learning algorithm that combines a Butterworth filter, ensemble empirical mode decomposition (EEMD), principle component analysis (PCA), and fast independent component analysis (FastICA) is proposed for separating the individual deflection components from a measured single channel deflection signal. The proposed algorithm consists of four stages: (1) the live load effect, which is a high-frequency signal, is separated from the raw signal by a Butterworth filter; (2) the EEMD algorithm is used to extract the intrinsic mode function (IMF) components; (3) these IMFs are utilized as input in the PCA model and some uncorrelated and dominant basis components are extracted; and (4) FastICA is applied to derive the independent deflection component. The simulated results show that each individual deflection component can be successfully separated when the noise level is under 10%. Verified by a practical application, the algorithm is feasible for extracting the structural deflection (including concrete shrinkage, creep, and prestress loss) only caused by structural damage or material deterioration.

Prediction of Concrete Fragments Amount and Travel Distance under Impact Loading Using Deep Neural Network and Gradient Boosting Method

“…However, a large amount of data is required in machine learning for training, and it is time-consuming to gather such a large amount of date through actual experiments. To this end, finite element method (FEM) has been employed to increase the training data [ 2 , 4 , 5 ]. Through FEM, any cracks in a concrete structure are simulated by deleting elements, as reported by Lee and Kim et al [ 6 , 7 , 8 , 9 ].…”

Acoustic Inspection of Concrete Structures Using Active Weak Supervision and Visual Information

“…The other end of the machine learning spectrum is called unsupervised learning. In [11], Mode Decomposition, Principal Component Analysis, and Independent Component Analysis were used for concrete bridge inspection. In [12,13], clustering methods were used.…”

Automated Modal Analysis for Tracking Structural Change during Construction and Operation Phases

“…Though the key algorithm of the OMA technique, such as the subspace stochastic identification (SSI) method [3], can be automated in order to track the evolution of modal parameters and detect structural changes under operational conditions [10,11,12,13], some obstacles still exist for a fully automated modal analysis (AMA) procedure. They are summarized as follows:…”