Multiclass anomaly detection in imbalanced structural health monitoring data using convolutional neural network

Abstract

Structural health monitoring (SHM) system aims to monitor the in-service condition of civil infrastructures, incorporate proactive maintenance, and avoid potential safety risks. An SHM system involves the collection of large amounts of data and data transmission. However, due to the normal aging of sensors, exposure to outdoor weather conditions, accidental incidences, and various operational factors, sensors installed on civil infrastructures can get malfunctioned. A malfunctioned sensor induces significant multiclass anomalies in measured SHM data, requiring robust anomaly detection techniques as an essential data cleaning process. Moreover, civil infrastructure often has imbalanced anomaly data where most of the SHM data remain biased to a certain type of anomalies. This imbalanced time-series data causes significant challenges to the existing anomaly detection methods. Without proper data cleaning processes, the SHM technology does not provide useful insights even if advanced damage diagnostic techniques are applied. This paper proposes a hyperparameter-tuned convolutional neural network (CNN) for multiclass imbalanced anomaly detection (CNN-MIAD) modelling. The hyperparameters of the proposed model are tuned through a random search algorithm to optimize the performance. The effect of balancing the database is considered by augmenting the dataset. The proposed CNN-MIAD model is demonstrated with a multiclass time-series of anomaly data obtained from a real-life cable-stayed bridge under various cases of data imbalances. The study concludes that balancing the database with a time shift window to increase the database has generated the optimum results, with an overall accuracy of 97.74%.

Online Real-Time Monitoring System of A Structural Steel Railway Bridge Using Wireless Smart Sensors

“…The main objective of the SHMS of the railway bridge is to provide serviceability, safety, and sustainability monitoring and assessment of the railway bridges during operation. A long-term SHM should include decision support systems, data management systems, data processing systems, data gathering and transmission systems, and sensory systems to achieve the objective above [16], [17], [27], [46]. All the systems should be integrated into one coordination and efficiently utilized by the manager to take actions and policies on the results.…”

“…However, it is also possible to evaluate railway bridge sustainability, serviceability, and safety using the data collected by the SHMS. SHMS has utilized the advancement of new sensing technologies over the past few decades [27]- [35]. Because of the advantages and tremendous benefits for applications that demand access to civil engineering structures, wireless approaches have been frequently used for SHMS [36]- [45].…”

Anomaly Detection in Structural Health Monitoring with Ensemble Learning and Reinforcement Learning

“…In the meticulous assessment stage, a detailed and exhaustive analysis was carried out, contrasting our suggested model with six distinct deep-learning contenders, namely TransAnoNet [13], AnoSegNet [14], WaveletCNN [15], GAN-VAE [30], CNN-MIAD [31], and VibroCNN. This evaluation aimed to provide an all-encompassing insight into the strengths of our model vis-à-vis established methods.…”

Drive-by Methodologies Applied to Railway Infrastructure Subsystems: A Literature Review—Part I: Bridges and Viaducts

“…It is of utmost importance to ensure that these structures are constantly monitored for their condition in order to guarantee the safety of passengers as well as avoid potential damage or delays caused by bridge failures. Over the past few decades, there has been a significant surge in the development of direct SHM approaches for railway bridges [3]. These approaches employ distinct sensor technologies to measure different parameters such as vibrations, deflection, deformation, temperature, and humidity, among others.…”