Structural damage quantification using ensemble‐based extremely randomised trees and impulse response functions

Abstract

Summary This paper presents a development and application of decision tree‐based ensemble technique, extremely randomised tree (ERT) as a multi‐output regression model in structural damage quantification of civil engineering structures. Acceleration responses are measured from structures when an impact force is applied. Impulse response functions as structural vibration properties are extracted from the acceleration responses and are processed as input to the ERT. Moving averaging with a suitable window size is performed to reduce the effect of noise, and principal component analysis is performed further for the dimensionality reduction. The damage level is defined in terms of elemental stiffness reduction. Both numerical and experimental studies are conducted to investigate the capability of using the proposed approach for structural damage identification and quantification. The numerical studies are carried out on a simply supported beam and experimental validations on a steel frame structure in the laboratory. From the results, the proposed method can provide good elemental structural damage quantification results. The computational time for the proposed approach is much less than random forest (RF) technique that has been used for the same application using acceleration responses. The performance of the proposed approach is compared with RF in terms of identification accuracy and training efficiency.

Prediction of Degraded Infrastructure Conditions for Railway Operation

“…As a future work, some recommendations are made: Create a midterm plan for methodology validation in other infrastructures, determining more precisely the threshold values [ 19 ]. Design a methodology for the sensing of new infrastructures with the aim of implementing, from the beginning, health status supervision in real-time.…”

“…Create a midterm plan for methodology validation in other infrastructures, determining more precisely the threshold values [ 19 ].…”

“…The principal challenge is to obtain enough data to train the algorithms properly, avoiding overfitting at the same time as building a robust model [ 18 ]. As far as the Random Forest model is concerned, this machine learning algorithm can be implemented so as to evaluate the health of the structure by analyzing the stiffness variations, where impulse responses functioning as structural vibration properties are extracted from the acceleration responses [ 19 ]. Other studies have shown that RF models can efficiently lead to a good damage identification result with much lower computational demand and time compared to neural network training methods [ 15 ].…”

Condition Assessment of Highway Bridges Using Textual Data and Natural Language Processing- (NLP-) Based Machine Learning Models

“…To achieve fast and automated bridge condition rating, in the past few years, machine learning (ML) methods have enjoyed fast development based on relevant information from bridge database or inspection [20][21][22]. State-of-the-art algorithms include artifcial neural networks (ANN) [23][24][25], clustering [26,27], decision trees (DT) [28,29], support vector machines [30][31][32][33], ensemble learning methods [34][35][36][37][38], and unsupervised learning methods [39], which have indicated both high accuracy and efciency. Using the relevant historical inspection and inventory data and records of maintenance, Huang [40] developed an artifcial neural network (ANN) model to predict bridge deck deterioration with 11 features such as bridge age, deck length, number of lanes, number of spans, and design load.…”

Acoustic Emission-based Damage Detection and Classification in Steel Frame Structure Using Wavelet Transform and Random Forest

“…Jahangir et al [22]; proposed vibration responses from time-domain modal testing of prestressed concrete slabs are used to try to detect defects. Chencho et al [23]; described the invention and use of the extremely randomized tree (ERT) as a multi-output regression model in decision tree-based ensemble approach for quantifying structural damage to civil engineering structures. Jahangir et al [24]; determined the sites damage in RC beams, suggest a wavelet-based damage index.…”