Content area
Full text
Received 14 November 2020; accepted 18 November 2020
KEYWORDS
Civil structures; Machine learning; Deep learning; Structural engineering; System identification; Structural health monitoring; Vibration control; Structural design; Prediction.
Abstract. This article presents a review of selected articles about structural engineering applications of Machine Learning (ML) in the past few years. It is divided into the following areas: structural system identification, structural health monitoring, structural vibration control, structural design, and prediction applications. Deep neural network algorithms have been the subject of a large number of articles in civil and structural engineering. There are, however, other ML algorithms with great potential in civil and structural engineering that are worth exploring. Four novel supervised ML algorithms developed recently by the senior author and his associates with potential applications in civil/structural engineering are reviewed in this paper. They are the Enhanced Probabilistic Neural Network (EPNN), the Neural Dynamic Classification (NDC) algorithm, the Finite Element Machine (FEMa), and the Dynamic Ensemble Learning (DEL) algorithm.
© 2020 Sharif University of Technology. All rights reserved.
1.Introduction
Machine Learning (ML) is a key Artificial Intelligence (AI) technology that is impacting almost every field in a significant way from image recognition, e.g., pupil detection [1], multi-object tracking [2], video surveillance [3], multi-target regression [4], thermal infrared face identification [5], and human activity recognition [6], to various brain and neuroscience applications, e.g., building functional brain network [7], motor imagery brain-computer interface [8,9], mapping scalp to intracranial EEG [10], seizure detection [11], diagnosis of the Parkinson's disease [12], and characterization of the modulation of the hippocampal rhythms [13].
In general, an ML system consists of three components: inputs comprising a dataset of signals/images/features, the ML algorithm, and output which is associated with the phenomenon studied (see Figure 1). ML algorithms can be classified into three broad categories:
a) Supervised learning such as Support Vector Machine (SVM) [14], various neural network models, statistical regression, Random Forest (RF) [15], fuzzy classifiers [16], and Decision Trees (DTs);
b) Unsupervised learning such as various clustering algorithms, e.g., к-means clustering and hierarchical clustering [17], autoencoders, self-organizing maps, competitive learning [18], and deep Boltzmann machine;
c) Reinforcement learning such as Q-learning, Rlearning, and Temporal Difference (TD) learning [19].
The first journal article on civil engineering application of neural networks was published in...