Arch Dam Deformation Prediction Model Based on PSO-SVM

2013 ◽  
Vol 351-352 ◽  
pp. 1306-1311 ◽  
Author(s):  
Jing Yang Liu ◽  
He Zhi Liu
Keyword(s):  
Prediction Model ◽  
Large Scale ◽  
Small Sample ◽  
Arch Dam ◽  
Support Vector ◽  
Model Parameters ◽  
Deformation Prediction ◽  
Dam Foundation ◽  
Model Based ◽  
Dam Deformation

Arch dam has gradually evolved as one of dam type as main large-scale hydraulic project, dam deformation prediction is an important part of dam safety monitoring, and it is difficult to forecast because of the complicated nonlinear characteristics of the monitoring data. Support Vector Machine (SVM) could solve the small sample, nonlinear high dimension problem due to the excellent generalization ability, and hence it has been widely used in the forecast of arch dam deformation. However, the forecast results considerably depend on the choice of SVM model parameters. In this paper, Particle Swarm Optimization (PSO), which has the characteristic of fast global optimization, was applied to optimize the parameters in SVM, and then the dam deformation prediction model based on PSO-SVM could be established. The model is applied to a certain arch dam foundation prediction. The accuracy of this employed approach was examined by comparing it with multiple regression method. In a word, the experimental results indicate that the proposed method based on PSO-SVM can be used in arch dam deformation prediction.

Pressure Prediction in Natural Gas Desulfurization Process Based on PCA and SVR

2014 ◽  
Vol 962-965 ◽  
pp. 564-569 ◽  
Author(s):  
Yan Chao Shao ◽  
Liang Jun Xu ◽  
Yan Zhu Hu ◽  
Xin Bo Ai
Keyword(s):  
Natural Gas ◽  
Prediction Model ◽  
Measured Data ◽  
Support Vector ◽  
Trend Prediction ◽  
Generalization Ability ◽  
Model Based ◽  
Scada System ◽  
Desulfurization Process ◽  
Natural Gas Desulfurization

Pressure monitoring is an important means to reflect the running status of the natural gas desulphurization process. By using the data mining technology, the interaction relationships between the pressure and other monitoring parameters are analyzed in this paper. A pressure trend prediction model is established to show the pressure status in the natural gas desulfurization process. Firstly, the theory of Principal Component Analysis (PCA) is used to reduce the dimensions of measured data from traditional Supervisory Control and Data Acquisition (SCADA) system. Secondly the principal components are taken as input data into the pressure trend prediction model based on multiple regression theory of Support Vector Regression (SVR). Finally the accuracy and the generalization ability of the model are tested by the measured data obtained from SCADA system. Compared with other prediction models, pressure trend prediction model based on PCA and SVR gets smaller MSE and higher correlation. The pressure trend prediction model gets better generalization ability and stronger robustness, and is an effective complement to SCADA system in the natural gas desulphurization process.

scholarly journals An Approach Using Adaptive Weighted Least Squares Support Vector Machines Coupled with Modified Ant Lion Optimizer for Dam Deformation Prediction

2020 ◽  
Vol 2020 ◽  
pp. 1-23 ◽  
Author(s):  
Yijun Chen ◽  
Chongshi Gu ◽  
Chenfei Shao ◽  
Hao Gu ◽  
Dongjian Zheng ◽  
...  
Keyword(s):  
Support Vector Machines ◽  
Least Squares ◽  
Weighted Least Squares ◽  
Support Vector ◽  
Deformation Prediction ◽  
Ant Lion Optimizer ◽  
Proposed Model ◽  
Vector Machines ◽  
Ant Lion ◽  
Dam Deformation

A dam deformation prediction model based on adaptive weighted least squares support vector machines (AWLSSVM) coupled with modified Ant Lion Optimization (ALO) is proposed, which can be utilized to evaluate the operational states of concrete dams. First, the Ant Lion Optimizer, a novel metaheuristic algorithm, is used to determine the punishment factor and kernel width in the least squares support vector machine (LSSVM) model, which simulates the hunting process of antlions in nature. Second, aiming to solve the premature convergence phenomenon, Levy flight is introduced into the ALO to improve the global optimization ability. Third, according to the statistical characteristics of the datum error, an improved normal distribution weighting rule is applied to update the weighted value of data samples based on the learning result of the LSSVM model. Moreover, taking a concrete arch dam in China as an example, the horizontal displacement recorded by a pendulum is used as a study object. The accuracy and validity of the proposed model are verified and evaluated based on the four evaluating criteria, and the results of the proposed model are compared with those of well-established models. The simulation results demonstrate that the proposed model outperforms other models and effectively overcomes the influence of outliers on the performance of the model. It also has high prediction accuracy, produces excellent generalization performance, and can be a promising alternative technique for the analysis and prediction of dam deformation and other fields, including flood interval prediction, the stock price market, and wind speed forecasting.

Wavelet support vector machine-based prediction model of dam deformation

2018 ◽  
Vol 110 ◽  
pp. 412-427 ◽  
Author(s):  
Huaizhi Su ◽  
Xing Li ◽  
Beibei Yang ◽  
Zhiping Wen
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Support Vector ◽  
Dam Deformation

Model-Based EEG Analysis: Proposal and Verification of Mathematical Model for Application to Neurotechnology

2019 ◽  
Author(s):  
Kenyu Uehara ◽  
Takashi Saito
Keyword(s):  
Mathematical Model ◽  
Binary Classification ◽  
Least Square ◽  
Mental Condition ◽  
Support Vector ◽  
Model Parameters ◽  
Eeg Analysis ◽  
Analysis Method ◽  
Model Based ◽  
Proposed Model

Abstract We have modeled dynamics of EEG with one degree of freedom nonlinear oscillator and examined the relationship between mental state of humans and model parameters simulating behavior of EEG. At the IMECE conference last year, Our analysis method identified model parameters sequentially so as to match the waveform of experimental EEG data of the alpha band using one second running window. Results of temporal variation of model parameters suggested that the mental condition such as degree of concentration could be directly observed from the dynamics of EEG signal. The method of identifying the model parameters in accordance with the EEG waveform is effective in examining the dynamics of EEG strictly, but it is not suitable for practical use because the analysis (parameter identification) takes a long time. Therefore, the purpose of this study is to test the proposed model-based analysis method for general application as a neurotechnology. The mathematical model used in neuroscience was improved for practical use, and the test was conducted with the cooperation of four subjects. model parameters were experimentally identified approximately every one second by using least square method. We solved a binary classification problem of model parameters using Support Vector Machine. Results show that our proposed model-based EEG analysis is able to discriminate concentration states in various tasks with an accuracy of over 80%.

Design and implementation of construction cost prediction model based on SVM and LSSVM in industries 4.0

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Miao Fan ◽  
Ashutosh Sharma
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Original Data ◽  
Construction Cost ◽  
Support Vector ◽  
Competitive Growth ◽  
Cost Prediction ◽  
Content Type ◽  
Model Based ◽  
Standard Support Vector Machine

PurposeIn order to improve the accuracy of project cost prediction, considering the limitations of existing models, the construction cost prediction model based on SVM (Standard Support Vector Machine) and LSSVM (Least Squares Support Vector Machine) is put forward.Design/methodology/approachIn the competitive growth and industries 4.0, the prediction in the cost plays a key role.FindingsAt the same time, the original data is dimensionality reduced. The processed data are imported into the SVM and LSSVM models for training and prediction respectively, and the prediction results are compared and analyzed and a more reasonable prediction model is selected.Originality/valueThe prediction result is further optimized by parameter optimization. The relative error of the prediction model is within 7%, and the prediction accuracy is high and the result is stable.

Sign in / Sign up

Export Citation Format

Share Document