A strain measurement model using a limited number of sensors for steel beam structures subjected to uncertain loadings

Oh, Byung Kwan; Hwang, Jin Woo; Lee, Jihoon; Kim, Yousok; Park, Hyo Seon

doi:10.1088/0957-0233/26/11/115007

Cited by 4 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…individual in one generation within the GA framework was set at 400, which is a relatively small number, based on the characteristics of premature convergence in the CNN training for structural response estimation. The number of design variables for determining the CNN architecture was set at six, as shown in Equation (5). The GA population size was set at 36, which is six times the number of the set design variables.…”

Section: B Optimization Results With Two Objective Functionsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Objective Optimization Method to Search for the Optimal Convolutional Neural Network Architecture for Long-Term Structural Health Monitoring

Kim

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

To ensure the safety of structures, structural health monitoring (SHM) techniques that use cutting-edge sensing technologies have been developed. However, in the process of long-term structural health monitoring, sensor defects and data loss commonly occur, which pose limitations in the current SHM technique. To recover lost data and predict structural responses, convolutional neural networks (CNNs) have been used in SHM, but no obvious technique or rule for configuring CNN architecture with optimal performance has been presented yet. This study proposes a method for searching for the optimal CNN architecture capable of predicting the structural response of structures to evaluate their long-term safety. In this method, multi-objective optimization, considering both prediction performance and CNN training efficiency, is presented as a strategy. The optimization method using the two objective functions is applied to the structural response estimation, and the characteristics of the derived solutions are examined. Furthermore, the solutions derived using the two objective functions are classified into two solution groups that are biased to each objective function, and a strategy for minimizing the discrepancy between the two solution groups is additionally presented based on their trade-off relationship. The architecture characteristics, estimation performance, and training efficiency of the solutions derived by setting the discrepancy as the third objective function are investigated. The CNN derived by the proposed method with the third objective function reduced 40.35% of computational cost compared with that derived with two objective functions while they showed similar accuracies for the response estimation. INDEX TERMS Convolutional neural network, data prediction, genetic algorithm, measurement, multiobjective optimization, structural health monitoring.

show abstract

Section: B Optimization Results With Two Objective Functionsmentioning

confidence: 99%

“…It is an index of the degree of deformation of local structural members when loads are applied on a structure. Technologies that use various strain sensors, such as vibrating wire strain gage [3] and fiber Bragg grating sensors [4], have been developed to evaluate the structural safety [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Optimization Method to Search for the Optimal Convolutional Neural Network Architecture for Long-Term Structural Health Monitoring

Kim

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Structural analysis and monitoring methods combined with sensing technology have attracted much attention in recent years, which has made good progress in breaking through the confusion caused by limited sensors, applying fiber optic sensing technology, and other advanced sensing technologies, and so on. For solving the problems of structural identification caused by limited sensors, a strain distribution measurement model and a sustainable strain‐sensing model were established to estimate the strain response of steel beam structures and high‐rise buildings, respectively (Oh, Hwang, Lee, Kim, & Park, 2015; Oh, Kim, Kim, Park, & Adeli, 2017). Considering the number of sensors and their proper locations, optimal sensor placement was discussed for the estimation of modal properties of bridge (Chang & Pakzad, 2014).…”

Section: Introductionmentioning

confidence: 99%

Internal force monitoring and estimation of a long‐span ring beam using long‐gauge strain sensing

Zhang

2020

Computer aided Civil Eng

View full text Add to dashboard Cite

The internal force information of curved beam members is important evidence for the stress state evaluation and design verification of long-span space structure during construction. Many structural analysis methods for curved beams have been proposed, but most are used to handle the complex geometric shapes. For stress state evaluation of long-span steel-concrete composite (SCC) ring beam, this article presents a method that employs a sectional strain distribution model (SSDM) and a fiber model to estimate the internal force distribution depending on the long-gauge strain. The SSDM of the ring beam used in the article is based on a mechanical model of two-dimensional (2-D) plane bending deformation and a three-dimensional (3-D) solid finite element model of curved beam members. The application range of the SSDM is defined by the divided different stress areas of ring beam based on the 3-D solid finite element model. Combined with the established SSDM and the different stress areas, the axial force and bending moment along the span are then identified separately based on the fiber model. In consideration of field monitoring, the influence of different sensor layout on the establishment of SSDM and the result of internal force identification is discussed. The results of the numerical studies show that the proposed methodology can identify the internal force distribution accurately. Internal force of long-span ring beam from Jiangsu Grand Theater during construction is also identified through the proposed method by using the strain monitoring data.

show abstract

“…A typical method to determine the maximum stress generated in structures is to use the strains measured by strain sensors, such as an electric strain gauge, a long gauge fiber optic sensor (LGFOS), a vibrating wire strain gauge (VWSG) and a fiber Bragg grating (FBG) [17][18][19][20][21][22][23], installed in locations where the maximum stress is expected to occur based on a structural analysis. However, the location where the maximum stress is generated in practice may differ from the maximum stress location predicted by the analysis since the location, shape, and amplitude of loads acting on the structures and boundary conditions of the structural members have a variety of uncertainties.…”

Section: Introductionmentioning

confidence: 99%

Vision-based stress estimation model for steel frame structures with rigid links

Park

2017

Meas. Sci. Technol.

View full text Add to dashboard Cite

This paper presents a stress estimation model for the safety evaluation of steel frame structures with rigid links using a vision-based monitoring system. In this model, the deformed shape of a structure under external loads is estimated via displacements measured by a motion capture system (MCS), which is a non-contact displacement measurement device. During the estimation of the deformed shape, the effective lengths of the rigid link ranges in the frame structure are identified. The radius of the curvature of the structural member to be monitored is calculated using the estimated deformed shape and is employed to estimate stress. Using MCS in the presented model, the safety of a structure can be assessed gauge-freely. In addition, because the stress is directly extracted from the radius of the curvature obtained from the measured deformed shape, information on the loadings and boundary conditions of the structure are not required. Furthermore, the model, which includes the identification of the effective lengths of the rigid links, can consider the influences of the stiffness of the connection and support on the deformation in the stress estimation. To verify the applicability of the presented model, static loading tests for a steel frame specimen were conducted. By comparing the stress estimated by the model with the measured stress, the validity of the model was confirmed.

show abstract

A strain measurement model using a limited number of sensors for steel beam structures subjected to uncertain loadings

Cited by 4 publications

References 27 publications

Multi-Objective Optimization Method to Search for the Optimal Convolutional Neural Network Architecture for Long-Term Structural Health Monitoring

Multi-Objective Optimization Method to Search for the Optimal Convolutional Neural Network Architecture for Long-Term Structural Health Monitoring

Internal force monitoring and estimation of a long‐span ring beam using long‐gauge strain sensing

Vision-based stress estimation model for steel frame structures with rigid links

Contact Info

Product

Resources

About