Wavelet support vector machine-based prediction model of dam deformation

Su, Huaizhi; Li, Xing; Yang, Bo; Wen, Zhiping

doi:10.1016/j.ymssp.2018.03.022

Cited by 187 publications

(104 citation statements)

References 31 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…SVM is a new supervised learning method developed in statistical learning theory that performs well in solving small sample, nonlinear, and high dimensional problems [27]. To date, SVM has been widely used in various fields of structural engineering, including dam safety, scour monitoring, civil architecture, etc., due to its potential in nonlinear regression, function approximation, and pattern recognition [28][29][30][31]. In brief, SVM can effectively deal with the data modeling problem under the condition of limited samples because of superior generalization ability and dimensionality insensitivity [32].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Ultimate Axial Capacity of Square Concrete-Filled Steel Tubular Short Columns Using a Hybrid Intelligent Algorithm

Ren

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

It is crucial to study the axial compression behavior of concrete-filled steel tubular (CFST) columns to ensure the safe operation of engineering structures. The restriction between steel tubular and core concrete in CFSTs is complex and the relationship between geometric and material properties and axial compression behavior is highly nonlinear. These challenges have prompted the use of soft computing methods to predict the ultimate bearing capacity (abbreviated as Nu) under axial compression. Taking the square CFST short column as an example, a mass of experimental data is obtained through axial compression tests. Combined with support vector machine (SVM) and particle swarm optimization (PSO), this paper presents a new method termed PSVM (SVM optimized by PSO) for Nu value prediction. The nonlinear relationship in Nu value prediction is efficiently represented by SVM, and PSO is used to select the model parameters of SVM. The experimental dataset is utilized to verify the reliability of the PSVM model, and the prediction performance of PSVM is compared with that of traditional design methods and other benchmark models. The proposed PSVM model provides a better prediction of the ultimate axial capacity of square CFST short columns. As such, PSVM is an efficient alternative method other than empirical and theoretical formulas.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Ultimate Axial Capacity of Square Concrete-Filled Steel Tubular Short Columns Using a Hybrid Intelligent Algorithm

Ren

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Evaluation indexes are accuracy, precision, recall and f-score, which are introduced subsequently as next 4 equations. In addition, Table 3 explains variables of equations (5)- (8). Figure 3 illustrates different accuracy rates of 6 classification models, while Figure 4 shows precision, recall, and f-score of these classifiers.…”

Section: Performance Comparisonmentioning

confidence: 99%

“…There are various methods available to mine data, including text mining, classification, association rules, clustering, outlier analysis and so on. Some researchers have utilized data mining techniques to explore the better ways to construct and operate hydropower engineering [6][7][8][9]. This study pays attention to predicting possible technical problems of hydropower engineering with the help of data mining, which has almost not been studied before.…”

Section: Introductionmentioning

confidence: 99%

Predicting Technical Problems of Hydropower Engineering Using eXtreme Gradient Boosting

Zhu¹

2018

SJAMS

View full text Add to dashboard Cite

Nowadays, water shortage is increasingly severe, which has huge negative influence on daily life. Constructing hydropower engineering is one of the approaches to alleviate such problem. Therefore, it's worth settling technical problems of hydropower engineering timely, which will help people not only make better use of water resources but also get rid of various security risks. To achieve such goal, this study predicts potential technical problems that hydropower engineering might happen. In order to utilize the large amount of data, data mining techniques are used to solve this multi-classification problem. First of all, plenty of data is preprocessed. Particularly, because of the complexity of text data, text mining techniques are applied to transform the unstructured data to structural data. Then, eXtreme Gradient Boosting (XGBoost) is applied to make the classification. To validate efficiency of the model, comparisons are made among XGBoost, Gradient Boosting Decision Tree, Random Forest, Decision Tree, k-Nearest Neighbor and Bernoulli Naïve Bayes from the perspective of accuracy, precision, recall and f-score. The experimental result shows that XGBoost is more suitable to solve this classification problem. This study provides engineering inspectors with helpful suggestions of particular technical problems that need attention, and further enables people to inspect engineering more efficiently and effectively.

show abstract

“…For data-driven methods, with the development of soft computing techniques, the modeling algorithms improved from the simple linear regression methods [11][12][13] to the advanced machine learning methods such as support vector machines (SVM) [14,15] and artificial neural network (ANN) [16]. In recent years, many synthetic models that integrate several machine learning methods also have been carried out [17,18]. Unlike the finite element methods that simulate the dam's behavior based on the design structural and material properties, data-driven methods cope with monitored data in real world.…”

Section: Introductionmentioning

confidence: 99%

Integrating the Finite Element Method with a Data‐Driven Approach for Dam Displacement Prediction

Shao

Meng

et al. 2020

Advances in Civil Engineering

View full text Add to dashboard Cite

Both numerical simulations and data-driven methods have been applied in dam’s displacement modeling. For monitored displacement data-driven methods, the physical mechanism and structural correlations were rarely discussed. In order to take the spatial and temporal correlations among all monitoring points into account, we took the first step toward integrating the finite element method into a data-driven model. As the data-driven method, we selected the random coefficient model, which can make each explanatory variable coefficient of all monitoring points following one or several normal distributions. In this way, explanatory variables are constrained. Another contribution of the proposed model is that the actual elastic modulus at each monitoring point can be back-calculated. Moreover, with a Lagrange polynomial interpolation, we can obtain the distribution field of elastic modulus, rather than gaining one value for the whole dam in previous studies. The proposed model was validated by a case study of the concrete arch dam in Jinping-I hydropower station. It has a better prediction precision than the random coefficient model without the finite element method.

show abstract

Wavelet support vector machine-based prediction model of dam deformation

Cited by 187 publications

References 31 publications

Prediction of Ultimate Axial Capacity of Square Concrete-Filled Steel Tubular Short Columns Using a Hybrid Intelligent Algorithm

Prediction of Ultimate Axial Capacity of Square Concrete-Filled Steel Tubular Short Columns Using a Hybrid Intelligent Algorithm

Predicting Technical Problems of Hydropower Engineering Using eXtreme Gradient Boosting

Integrating the Finite Element Method with a Data‐Driven Approach for Dam Displacement Prediction

Contact Info

Product

Resources

About