A Novel Structural Damage Identification Method Using a Hybrid Deep Learning Framework

Abstract

In the past few years, structural health monitoring (SHM) has become an important technology to ensure the safety of structures. Structural damage identification methods based on machine learning techniques have gained wide attention due to the advantages of effectively extracting features from monitoring data. However, the existing machine learning-based methods heavily depend on manually selected feature parameters from raw signals. This will cause the selected feature to obtain the optimal solution for a specific condition but may fail to provide a similar performance in other cases. In addition, the feature selection takes a long time, which can fail to achieve real-time performance in a practical structure. To address these problems, this article proposes a hybrid deep learning framework for structural damage identification that includes three components, namely, ensemble empirical mode decomposition (EEMD), Pearson correlation coefficient (PCC), and a convolutional neural network (CNN). The proposed EEMD-PCC-CNN method is capable of automatically extracting features from raw signals to satisfy any damage identification objective. To evaluate the performance of the proposed EEMD-PCC-CNN method, a three-story building structure is investigated. The acceleration signal of the three-story building structure is first analyzed by EEMD. After obtaining the time-frequency information, PCC is utilized to select optimal time-frequency information as the input of the CNN for damage identification. Compared with other classical methods (SVM, KNN, RF, etc.), the experimental results show that the newly proposed EEMD-PCC-CNN method has significant performance advantages in damage identification. In addition, the accuracy of the proposed damage identification method is improved by more than 4% after utilizing EEMD in comparison with CNN alone.

Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends

“…Also, validation sets were added to adjust the DL model parameters better. The typical ratios of the training set, verification set, and test set are 6:2:2 [17,110], 7:2:1 [22,44], 8:1:1 [128,199] and so on.…”

“…Gradually, Non-Destructive Testing (NDT) methods, such as Acoustic Emission (AE) [9], ultrasonic [10], X-ray [11], magnetic particle inspection [12], eddy current [13], and other detection methods, are frequently utilized for monitoring the key component of the structure [13]. Currently, the most commonly used SHM methods are vibration-based SHM [14][15][16][17][18], AEbased SHM [9,19,20], Guided Wave (GW) based SHM [21][22][23][24][25], and Electro-Mechanical Impedance (EMI) based SHM [26,27]. Among them, vibration-based SHM is the most popular one by analyzing the relationship between vibration characteristics and damage states.…”

Application of Sonic Tests and Modal Identification in the Characterization of Masonry Walls

“…As the structural integrity can relate with natural frequencies, an analysis of periodical frequency measurements can be used to monitor the structural condition [7,10,11]. In the present day, several works have been proposed regarding the structural damage identification using different techniques, taking advantage of NDT to improve the location and the quantification of the damage [12][13][14][15][16].…”