Development and application of random forest technique for element level structural damage quantification

Abstract

Summary This paper presents element level structural damage quantification using an ensemble‐based machine learning technique, namely, random forest technique, with acceleration responses from structures. The ensemble‐based approach provides a better prediction than an individual model. Random forest is a machine learning algorithm which has several decision trees to perform a task. The proposed approach develops a random forest as a regressor to predict multiple output variables, which is the vector of elemental level damage quantification results of the structure. Damage severity is identified as the reduction in the elemental stiffness parameters. The acceleration responses for single‐element and multiple element damage cases are generated and further processed to feed as input to the random forest. The acceleration responses from the sensor nodes are concatenated, and principal component analysis (PCA) is applied to reduce the uncorrelated input dimension. The proposed approach can provide good damage identification results efficiently with much less computational demand and time, compared to the neural network training methods and deep learning models. Moreover, fewer sensors are needed to measure acceleration responses to localise damage and quantify the damage level. To demonstrate the proposed method, a simply supported beam is used as an example in numerical studies. Different levels of noise in the acceleration responses and uncertainty in the finite element modelling are considered. Experimental studies on a steel frame structure with 70 elements are also conducted to investigate the performance of the proposed approach for structural damage quantification. Good identification results are obtained with an efficient training process.

Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights

“…This could explain the reason why these two papers appear to contradict. Chencho et al 210 (Level 1-2,4) developed a structural damage quantification based on RF and PCA for dimensionality reduction. The authors achieved an R -score of 89.2 and 95.3% for single-element and two-element damage cases, respectively.…”

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

“…Decision trees are nonparametric supervised machine learning algorithms, which can be used for both regression and classification problems. 32 However, a single decision tree usually suffers from overfitting, resulting in a high variance and a low bias. Breiman 33 proposed random forest (RF) to reduce the variance and increase the bias.…”

“…The variance problem is reduced by introducing randomness, taking ensembles of decision trees, using bootstrapped samples and splitting nodes at the best split. 28,[32][33][34] RF was used as a classifier to identify damage in a shear frame structure. 35 Further, Zhou et al 36 carried out a study by using the RF as a feature extractor to eliminate the least important features.…”

“…For classification problems, the majority vote of the classes is taken as the final output. A decision tree suffers from overfitting, resulting in a high variance, and RF reduces the variance by using multiple decision trees, bootstrapping the data and splitting nodes on the best split [32][33][34]38 from a set of randomly selected features. Although RF requires growing several decision trees using bootstrap data, it is still popular owning to low computational cost of growing the decision trees.…”

Estimating effluent turbidity in the drinking water flocculation process with an improved random forest model

“…Before that, the random forest (RF) algorithm has been successfully applied for solving regression and classification problems in many applications (Mohammed et al 2017;Li et al 2020). It is suitable for demonstrating the nonlinear effect of variables, and it can model complex interactions among variables (Chen et al 2020;Chencho et al 2020;Kou et al 2020;). However, the common RF has difficulty coping with seasonal and periodic changes in influent water quality (Peng et al 2020;Yang et al 2020).…”