Structural deformation prediction model based on extreme learning machine algorithm and particle swarm optimization

Jiang, Shouyan; Zhao, Linxin; Du, Chengbin

doi:10.1177/14759217211072237

Cited by 10 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te measured radial deformation of PL13-5 is still taken for illustration. SOA, the grey wolf optimizer (GWO) [34], and particle swarm optimization (PSO) [35] are all utilized to search the optimal parameters of the GBDT, respectively, including the number m of trees, the tree depth h, and the learning rate v. Te search space of these parameters is [50, 400], [1,4], and [0, 1], respectively. Te maximum iteration number and the population size of the three algorithms are set to 400 and 30.…”

Section: Comparison Of Diferent Point Prediction Methodsmentioning

confidence: 99%

Interval Prediction Model of Deformation Behavior for Dam Safety during Long-Term Operation Using Bootstrap-GBDT

Zhao

Zhang

et al. 2023

Structural Control and Health Monitoring

View full text Add to dashboard Cite

Accurate and reliable prediction on structural deformation is a powerful means to evaluate the safety state of dams during long-term operation. This work is a contribution to the quantification of the cognitive and stochastic uncertainties in prediction models for the dam performance using measured time series, through constructing the prediction interval (PI) by an innovative model combined with the gradient boosting decision tree (GBDT) and the bootstrap method. The constructed PI, improved by the kernel density estimation (KDA), consists of an upper bound and a lower bound of the interval to provide a confidence level for dam deformation prediction. The bootstrap method combined with multiple GBDT is utilized to estimate the variance of the model bias, mainly derived from the cognitive uncertainties. The variance of random noise can be furtherly estimated through training the combined model to fit the residuals so as to indicate the stochastic uncertainties. The effectiveness of the newly proposed model is validated employing measured data of the Jinping Ι arch Dam. The results indicate that the methodology can obtain high-quality PIs and accurate prediction values and thus can provide strong support for better appraising dam performance during long-term operation.

show abstract

Section: Comparison Of Diferent Point Prediction Methodsmentioning

confidence: 99%

Interval Prediction Model of Deformation Behavior for Dam Safety during Long-Term Operation Using Bootstrap-GBDT

Zhao

Zhang

et al. 2023

Structural Control and Health Monitoring

View full text Add to dashboard Cite

show abstract

“…A great deal of research has been done in applying conventional measurement techniques to SHM [15]. Examples include statistical-based deformation health diagnosis models [16][17][18][19] and improved models with extreme learning machine [20], support vector regression (SVR) [21,22], artificial neural networks (ANNs) [23], random forests (RF) [24] and other intelligent algorithms. However, these models cannot explain the physical meaning of dam deformation or reflect the impact of construction interfaces.…”

Section: Introductionmentioning

confidence: 99%

Deformation health diagnosis of RCC dams considering construction interfaces based on monitoring data and numerical simulation

Chen,

Li,

Liu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The health diagnosis procedure applied to determine the deformation of a roller compacted concrete (RCC) dam is different from that of a conventional concrete dam. Hence, in this study, a deformation health diagnosis model was established for an RCC dam considering the construction interfaces by combining the hydrostatic component simulated using ABAQUS (2016), with the temperature and aging components calculated using a statistical method. The combined method can help monitor the structural health of RCC dams and determine the physical meaning and statistical law of deformation of RCC dams. During the simulation process, the geometric characteristics of the construction interfaces were modelled using the interface equivalent expansion method (IEEM). The material properties were modelled using multi-output least-squares support vector regression optimized with the Jaya algorithm (JA-MLS-SVR). A case study demonstrated that the established deformation–health diagnosis model has good fitting and prediction abilities. The model and methods proposed in this study provide a new concept for the behavior analysis and numerical simulation of mass composite structures similar to RCC dams.

show abstract

“…41,42 In hybrid methods, a metaheuristic method obtains the optimal value of the objective function approximately, then this value is used as the initial estimated value by a local search technique to determine the optimal value accurately. Metaheuristic methods such as particle swarm optimization (PSO), 43 genetic algorithms 44 and simulated annealing 45 are usually stochastic in nature and improve a randomly generated set of initial designs in a pseudorandom fashion. 46 This paper investigates the behaviour of a steel cantilever beam with a partially-fixed connection by presenting a FEMU process based on DIC and Powell particle swarm optimization (PPSO).…”

Section: Introductionmentioning

confidence: 99%

Performance assessment of steel cantilever beams based on connection behaviour using DIC technique and improved hybrid PSO algorithm

Khaloo

Amirahmadi

2023

Structural Health Monitoring

View full text Add to dashboard Cite

Cantilever beams can have various behaviour depending on the details of the connection. Partially-fixed connections have a different performance from conventionally-fixed connections, in which the exact information is not available. In this paper, using the finite element model updating (FEMU) of a steel cantilever beam, the support conditions of a partially-fixed connection and the behaviour of the beam are investigated. The FEMU is utilized as an appropriate technique for structural health monitoring, which requires the use of data acquisition methods from the structure. In this research, instead of using discrete sensors, displacement and strain information are continuously measured from the beam surface using the digital image correlation (DIC) method. The difference between the initial model and the data extracted from the DIC is determined by a cost function. A hybrid method called Powell particle swarm optimization is used to minimize the cost function. This method includes particle swarm optimization (PSO) as a global search technique and Powell optimization as a local search technique; the hybrid method achieves better performance by combining the two methods. A dynamic inertia weight is presented to improve the performance of the PSO algorithm. Abaqus software and Python programming have been used to carry out the FEMU process. Finally, the amount of rotation and displacement of support are calculated, and the dependency of beam behaviour on each of the variables is investigated. This method yields acceptable convergence of the results and can be extended to study other structural components.

show abstract

Structural deformation prediction model based on extreme learning machine algorithm and particle swarm optimization

Cited by 10 publications

References 38 publications

Interval Prediction Model of Deformation Behavior for Dam Safety during Long-Term Operation Using Bootstrap-GBDT

Interval Prediction Model of Deformation Behavior for Dam Safety during Long-Term Operation Using Bootstrap-GBDT

Deformation health diagnosis of RCC dams considering construction interfaces based on monitoring data and numerical simulation

Performance assessment of steel cantilever beams based on connection behaviour using DIC technique and improved hybrid PSO algorithm

Contact Info

Product

Resources

About