Machine Learning-Assisted Improved Anomaly Detection for Structural Health Monitoring

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 7; p. 3365
• Main Authors: Samudra, Shreyas, Barbosh, Mohamed, Sadhu, Ayan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 23-03-2023; MDPI
• Subjects: Algorithms; Analysis; Anomalies; anomaly detection; Artificial intelligence; Bridges; Classification; Data integration; Datasets; decision tree; Decision trees; Economic conditions; Global economy; Highway construction; Life assessment; Logistics; Machine learning; Multisensor fusion; Neural networks; Outliers (statistics); random forest; Sensors; Signal processing; Strain gauges; Structural health monitoring; Supply chains; Support vector machines; System effectiveness; Time series; vibration data; Wavelet transforms; China; decision tree; anomaly detection; structural health monitoring; random forest; machine learning; vibration data
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23073365

The importance of civil engineering infrastructure in modern societies has increased lately due to the growth of the global economy. It forges global supply chains facilitating enormous economic activity. The bridges usually form critical links in complex supply chain networks. Structural health monitoring (SHM) of these infrastructures is essential to reduce life-cycle costs, and determine their remaining life using advanced sensing techniques and data fusion methods. However, the data obtained from the SHM systems describing the health condition of the infrastructure systems may contain anomalies (i.e., distortion, drift, bias, outlier, noise etc.). An automated framework is required to accurately classify these anomalies and evaluate the current condition of these systems in a timely and cost-effective manner. In this paper, a recursive and interpretable decision tree framework is proposed to perform multiclass classification of acceleration data collected from a real-life bridge. The decision nodes of the decision tree are random forest classifiers that are invoked recursively after synthetically augmenting the training data before successive iterations until suitable classification performance is obtained. This machine-learning-based classification model evolved from a simplistic decision tree where statistical features are used to perform classification. The feature vectors defined for training the random forest classifiers are calculated using similar statistical features that are easy to interpret, enhancing the interpretability of the classifier models. The proposed framework could classify non-anomalous (i.e., normal) time-series of the test dataset with 98% accuracy.