A systematic review of data fusion techniques for optimized structural health monitoring

Hassani, Sahar; Dackermann, Ulrike; Mousavi, Mohsen; Li, Jianchun

doi:10.1016/j.inffus.2023.102136

Cited by 20 publications

(3 citation statements)

References 357 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Integrating information from multiple wireless sensors or sources. [34,47,48] Signal reconstruction Reconstruct missing or incomplete data.…”

Section: Methods Function Technique Referencementioning

confidence: 99%

See 1 more Smart Citation

Wireless Sensor Placement Optimization for Bridge Health Monitoring: A Critical Review

Chen,

Shi,

et al. 2024

Buildings

View full text Add to dashboard Cite

In recent years, wireless sensors have progressively supplanted conventional limited sensors owing to their attributes of small size, low cost, and high accuracy. Consequently, there has been a growing interest in leveraging wireless sensor networks for bridge structural health monitoring applications. By employing wireless sensor nodes to gather data from various segments of the bridge, information is relayed to a signal-receiving base station. Subsequently, the health status of the bridge is inferred through specific data processing and analysis, aiding monitoring personnel in making informed decisions. Nonetheless, there are limitations in this research, particularly pertaining to power consumption and efficiency issues in data acquisition and transmission, as well as in determining the appropriate wireless sensor types and deployment locations for different bridge configurations. This study aims to comprehensively examine research on the utilization of wireless sensor networks in the realm of bridge structural health monitoring. Employing a systematic evaluation methodology, more than one hundred relevant papers were assessed, leading to the identification of prevalent sensing techniques, data methodologies, and modal evaluation protocols in current use within the field. The findings indicate a heightened focus among contemporary scholars on challenges arising during the data acquisition and transmission processes, along with the development of optimal deployment strategies for wireless sensor networks. In continuing, the corresponding technical challenges are provided to address these concerns.

show abstract

“…Integrating information from multiple wireless sensors or sources. [34,47,48] Signal reconstruction Reconstruct missing or incomplete data.…”

Section: Methods Function Technique Referencementioning

confidence: 99%

“…Sensor fusion methods such as sensor selection, sensor calibration, feature fusion, and decision-level fusion. [34,47,48] Quality-aware aggregation Reliability and quality of data collected from different sensors when performing aggregation.…”

Section: Hierarchical Aggregationmentioning

confidence: 99%

Wireless Sensor Placement Optimization for Bridge Health Monitoring: A Critical Review

Chen,

Shi,

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…Information fusion, as a methodological approach, presents a promising solution to the challenge of managing uncertainty in complex systems. By integrating diverse sources of information, including both sensory and non-sensory data, information fusion aims to enhance decision-making processes by providing a more comprehensive and accurate understanding of the observed system [11].…”

Section: Uncertainty In Diagnosismentioning

confidence: 99%

Probabilistic Uncertainty-Aware Decision Fusion of Neural Network for Bearing Fault Diagnosis

Mostafavi,

Siami,

Friedmann

et al. 2024

PHME_CONF

View full text Add to dashboard Cite

Reliability is a central aspect of machine learning applications, especially in fault diagnosis systems, where only an accurate and reliable diagnosis system is economically justifiable, considering that any false diagnosis would lead to an increase in maintenance costs or a reduction in system efficiency. Recent advances in machine learning (ML) techniques have encouraged condition monitoring researchers to focus their efforts on finding suitable ML-based solutions for system condition assessment. However, to address the reliability issue, it is crucial to consider a larger amount of data measured by heterogeneous sensors on the system together with non-sensor information. The trend of data fusion has already started in other areas of ML application, and many of today's state-of-the-art models benefit from various types of fusion techniques to improve their accuracy. However, traditional classifiers do not provide any information about the prediction uncertainty, and they tend to show falsely high confidence when encountering low-quality data or previously unseen classes. Fusion of different data sources without considering the epistemic or aleatory uncertainty can lead to a deterioration of the result. Bayesian frameworks have traditionally been used to quantify uncertainty of systems; however, only recent advances made it possible to successfully implement Bayesian ML models. The research methodology was investigated using the MAFAULDA dataset generated by SpectraQuest's Machinery Fault Simulator. This simulator experimentally simulated various bearing conditions, including normal operation and inner and outer ring bearing failures, at variable speeds. The dataset consists of 1951 instances measured using two triaxial accelerometers, a microphone, and a tachometer. Diagnosis has been done via two multi label 1D Convolutional Neural Networks - each for a selected sensor - and their prediction along with their associated uncertainty quantity has been fused utilizing Bayesian model averaging. The methodology is capable of fusion of various decisions made based on different data sources and generate a unified decision with associated confidence level. Fusion process is uncertainty aware and application of 1D networks reduce the amount of data needed.

show abstract

Fusing deep learning features for parameter identification of a stochastic airfoil system

Feng,

Wang,

Liu

et al. 2024

Nonlinear Dyn

View full text Add to dashboard Cite

A systematic review of data fusion techniques for optimized structural health monitoring

Cited by 20 publications

References 357 publications

Wireless Sensor Placement Optimization for Bridge Health Monitoring: A Critical Review

Wireless Sensor Placement Optimization for Bridge Health Monitoring: A Critical Review

Probabilistic Uncertainty-Aware Decision Fusion of Neural Network for Bearing Fault Diagnosis

Fusing deep learning features for parameter identification of a stochastic airfoil system

Contact Info

Product

Resources

About