Model-Based Heterogeneous Data Fusion for Reliable Force Estimation in Dynamic Structures under Uncertainties

Khodabandeloo, Babak; Melvin, Dyan; Jo, Hongki

doi:10.3390/s17112656

Cited by 13 publications

(4 citation statements)

References 50 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shorter IRI evaluation length may include more localized (i.e., higher frequency) road roughness information. The acceleration has been known to better represent such higher‐frequency information than other metrics (Khodabandeloo, Melvin, & Jo, 2017). While the difference in the response metric showed consistent performance, the effects of CNN layer depth change were not that noticeable.…”

Section: Test Results—performance Of the Proposed Cnn Modelmentioning

confidence: 99%

Convolutional neural networks for pavement roughness assessment using calibration‐free vehicle dynamics

Jeong

Ditzler

2020

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Road roughness is a measure of how uncomfortable a ride is, and provides an important indicator for the needs of roadway maintenance or repavement, which is closely tied to the state and federal budget prioritization. As such, accurate and timely monitoring of deteriorating road conditions and following maintenance are essential to improve the overall ride quality on the road. Various technologies, including vehiclemounted laser profiling systems, have been developed and adopted for road roughness (e.g., IRI-International Roughness Index) measurement; however, their high cost limits their use. While recent advances in smartphone technologies allow us to use their embedded accelerometers for road roughness monitoring, the complicated process of necessary vehicle calibration hinders the widespread use of the technology in the actual practices. In this work, a deep learning IRI estimation method is proposed with the goal of using anonymous (i.e., calibration-free) vehicles and their responses measured by smartphones as road roughness sensors. A state-of-the-art deep learning algorithm (i.e., CNN-convolutional neural network) and multimetric vehicle dynamics data (i.e., accelerometer, gyroscope), possibly measured by drivers' smartphones, are employed for the purpose. Optimized CNN architecture and data configuration have been investigated to achieve the best performance. The efficacy of the proposed method has been numerically validated using real road IRI information (i.e., Speedway, Tucson, AZ), real driving speed profiles, and four different types of vehicle data with associated uncertainties.

show abstract

Section: Test Results—performance Of the Proposed Cnn Modelmentioning

confidence: 99%

Convolutional neural networks for pavement roughness assessment using calibration‐free vehicle dynamics

Jeong

Ditzler

2020

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Where T s , T d , T v , and T a are mapping matrices for strain, displacement, velocity and acceleration respectively. For the derivation of C d and D d matrices see ref (Khodabandeloo et al, 2017). The detailed steps for AKF are illustrated in algorithm 1 (Lourens et al, 2012);…”

Section: Fundamentalsmentioning

confidence: 99%

Multi-objective sensor placement optimization for structural response estimation under spatially varying dynamic loading of bridges

Saleem

2021

Advances in Structural Engineering

Self Cite

View full text Add to dashboard Cite

Although a lot of different types of sensors are available in the market only a limited number of sensors can be installed on a structure. Proper placement of these sensors plays a vital role in effectively achieving the objectives of a monitoring system. Sensor placement becomes especially critical in the case of bridges where the applied loading keeps on changing its location. A sensor layout that provides good quality structural response estimates for a given applied loading may not yield acceptable results for a different loading arrangement. Further, usually different types of sensors are installed on a structure e.g. strain gauges and accelerometers. These sensors measure different physical quantities having different units and orders of magnitude thus cannot be easily incorporated in a sensor placement optimization (SPO) process. So, this research work proposes a multi-objective sensor placement optimization approach that can effectively deal with different types of sensor measurements and spatially varying loading such as in the case of bridges. The proposed method employs an augmented Kalman filter (AKF) for structural response estimation and a multi-objective genetic algorithm for SPO. The AKF can effectively estimate structural response using a few heterogeneous noisy measurements while incorporating the modeling error. The effectiveness of the proposed method is demonstrated using a numerical example of a 3D truss bridge structure. The results show that the proposed multi-objective optimization method yields a sensor arrangement that remains effective against spatially varying dynamic loading.

show abstract

“…Although the displacement reconstruction method based on multi-source data is generally superior to the single physical quantity displacement reconstruction method, there are still problems such as dependence on observed displacement, inability to process multi-rate data, and excessive use of sensors [31][32][33]. At present, there is relatively little research on the deformation monitoring of monopole communication towers, and the relevant theories and methods are still immature.…”

Section: Introductionmentioning

confidence: 99%

Deformation Monitoring of Monopole Communication Towers Based on Multi-Source Data Fusion

Ji,

Ren,

et al. 2023

Buildings

View full text Add to dashboard Cite

Monopole communication towers play an irreplaceable role in modern communication systems. Because of its high flexibility, lateral loads control the deformation of a monopole communication tower. Dynamic displacement can be used to describe structural vibration characteristics and real-time deformation situations. Therefore, this article proposes a monopole communication tower deformation monitoring method based on multi-source data fusion using dynamic displacement as the evaluation indicator. This method calculates the strain displacement using the strain-mode superposition methodology. Then, the strain displacement and acceleration obtained are processed using Kalman filtering technology to reconstruct the real-time displacements of the monopole communication tower. The effectiveness of this method was verified using numerical simulations and model experiments, respectively. In addition, parametric analysis shows that this method is suitable for processing multi-rate data, has good noise resistance in strong noise environments, and can effectively reconstruct the displacement near the tower bottom. The results indicate that the method has favorable robustness and can accurately reconstruct low-frequency and high-frequency displacements of the monopole communication tower.

show abstract

Model-Based Heterogeneous Data Fusion for Reliable Force Estimation in Dynamic Structures under Uncertainties

Cited by 13 publications

References 50 publications

Convolutional neural networks for pavement roughness assessment using calibration‐free vehicle dynamics

Convolutional neural networks for pavement roughness assessment using calibration‐free vehicle dynamics

Multi-objective sensor placement optimization for structural response estimation under spatially varying dynamic loading of bridges

Deformation Monitoring of Monopole Communication Towers Based on Multi-Source Data Fusion

Contact Info

Product

Resources

About