Auto-Regressive Integrated Moving-Average Machine Learning for Damage Identification of Steel Frames

Abstract

Auto-regressive (AR) time series (TS) models are useful for structural damage detection in vibration-based structural health monitoring (SHM). However, certain limitations, e.g., non-stationarity and subjective feature selection, have reduced its wide-spread use. With increasing trends in machine learning (ML) technologies, automated structural damage recognition is becoming popular and attracting many researchers. In this paper, we combined TS modeling and ML classification to automatically extract damage features and overcome the limitation of non-stationarity. We propose a two-stage framework, namely auto-regressive integrated moving-average machine learning (ARIMA-ML) with modules for pre-processing, model parameter determination, feature extraction, and classification. Based on shaking table tests of a space steel frame, floor acceleration data were collected and labeled according to experimental observations and records. Subsequently, we designed three damage classification tasks for: (1) global damage detection, (2) local damage detection, and (3) local damage pattern recognition. The results from these three tasks indicated the robustness and accuracy of the proposed framework where 97%, 98%, and 80% average segment accuracy were achieved, respectively. The confusion matrix results showed the unbiased model performance even under an imbalanced-class distribution. In summary, the presented study revealed the high potential of the proposed ARIMA-ML framework in vibration-based SHM.

Structural nonlinear damage identification based on the information distance of GNPAX/GARCH model and its experimental study

“…After the optimal model structure of the GNPAX/ GARCH model was obtained, the K-L distance could be calculated from the acceleration time series data of the baseline state and the test state (damage scenarios). Two damage identification methods were used for comparison with the proposed method: (1) the damage identification method based on AR(30)/ARCH(5) model and SOVI proposed by Cheng et al 6 ; (2) the damage identification method based on ARX (25,15,30) model and K-L distance. In order to facilitate the comparison of the three methods, Equation (30) was used to transform the three damage indicators into the expression based on the dimensionless damage indicator…”

“…In order to more effectively extract the damage features in the structural acceleration time series, researchers often combine the time series method with other analysis methods for damage identification. Gao et al 15 proposed a two-stage damage identification method based on ARIMA (autoregressive integrated moving average) model and machine learning (ARIMA-ML). The ARIMA model was used to establish a time series model of the acceleration response, and a candidate model mechanism was introduced for damage identification.…”

Short term residential load forecasting using long short-term memory recurrent neural network

“…It combines auto-regressive (AR) and moving average (MA) models. The I stand for "integrated" represents the fact that the data have been substituted with a number, which is the difference between their values and the foregoing values [27]. ARIMA (p, d, q) [28] can be used to represent non-seasonal ARIMA.…”

Estimating small structural motions based on sparsity enforcement

“…K. Oh et al, 2017), system identification (Mu & Yuen, 2016;Perez-Ramirez et al, 2019;Yuen et al, 2019), damage identification Amezquita-Sanchez et al, 2017, and vibration control (Adeli & Saleh, 1997;Javadinasab Hormozabad et al, 2021;Li & Adeli, 2018). Vibration-based SHM was widely used (Farrar et al, 1999;Gao et al, 2021;Nair et al, 2006). Its essential idea is that structural deterioration information will change the physical properties of structures (e.g., frequency, damping © 2022 Computer-Aided Civil and Infrastructure Engineering.…”

“…In many important civil engineering applications, structural health monitoring (SHM) has been widely used for feature extraction (Li et al., 2017; B. K. Oh et al., 2017), system identification (Mu & Yuen, 2016; Perez‐Ramirez et al., 2019; Yuen et al., 2019), damage identification (Amezquita‐Sanchez & Adeli, 2019; Amezquita‐Sanchez et al., 2017, 2018), and vibration control (Adeli & Saleh, 1997; Javadinasab Hormozabad et al., 2021; Li & Adeli, 2018). Vibration‐based SHM was widely used (Farrar et al., 1999; Gao et al., 2021; Nair et al., 2006). Its essential idea is that structural deterioration information will change the physical properties of structures (e.g., frequency, damping ratio, and stiffness), which can be detected or controlled by measuring the abnormal responses of structural motions (Gutierrez Soto & Adeli, 2017, 2018; Soto & Adeli, 2019).…”