Data-driven model development using Support Vector Machine for railway Overhead Contact Wire maintenance

2015 ◽  
Author(s):  
F.Q. Yuan ◽  
J.M. Lu
Keyword(s):  
Support Vector Machine ◽  
Model Development ◽  
Data Driven ◽  
Support Vector ◽  
Contact Wire

Physical-oriented and machine learning-based emission modeling in a diesel compression ignition engine: Dimensionality reduction and regression

2022 ◽  
pp. 146808742110707
Author(s):  
Aran Mohammad ◽  
Reza Rezaei ◽  
Christopher Hayduk ◽  
Thaddaeus Delebinski ◽  
Saeid Shahpouri ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Support Vector Machine ◽  
Factor Analysis ◽  
Dimensionality Reduction ◽  
Principal Component ◽  
Component Analysis ◽  
Data Driven ◽  
Support Vector ◽  
Emission Models ◽  
Emission Modeling

The development of internal combustion engines is affected by the exhaust gas emissions legislation and the striving to increase performance. This demands for engine-out emission models that can be used for engine optimization for real driving emission controls. The prediction capability of physically and data-driven engine-out emission models is influenced by the system inputs, which are specified by the user and can lead to an improved accuracy with increasing number of inputs. Thereby the occurrence of irrelevant inputs becomes more probable, which have a low functional relation to the emissions and can lead to overfitting. Alternatively, data-driven methods can be used to detect irrelevant and redundant inputs. In this work, thermodynamic states are modeled based on 772 stationary measured test bench data from a commercial vehicle diesel engine. Afterward, 37 measured and modeled variables are led into a data-driven dimensionality reduction. For this purpose, approaches of supervised learning, such as lasso regression and linear support vector machine, and unsupervised learning methods like principal component analysis and factor analysis are applied to select and extract the relevant features. The selected and extracted features are used for regression by the support vector machine and the feedforward neural network to model the NOx, CO, HC, and soot emissions. This enables an evaluation of the modeling accuracy as a result of the dimensionality reduction. Using the methods in this work, the 37 variables are reduced to 25, 22, 11, and 16 inputs for NOx, CO, HC, and soot emission modeling while maintaining the accuracy. The features selected using the lasso algorithm provide more accurate learning of the regression models than the extracted features through principal component analysis and factor analysis. This results in test errors RMSETe for modeling NOx, CO, HC, and soot emissions 19.22 ppm, 6.46 ppm, 1.29 ppm, and 0.06 FSN, respectively.

scholarly journals A Data-Driven Approach for Winter Precipitation Classification Using Weather Radar and NWP Data

Atmosphere ◽  
2020 ◽  
Vol 11 (7) ◽  
pp. 701
Author(s):  
Bong-Chul Seo
Keyword(s):  
Random Forest ◽  
Binary Classification ◽  
Weather Prediction ◽  
Model Development ◽  
Winter Precipitation ◽  
Ensemble Classification ◽  
Supervised Machine Learning ◽  
Data Driven ◽  
Support Vector ◽  
Data Driven Approach

This study describes a framework that provides qualitative weather information on winter precipitation types using a data-driven approach. The framework incorporates the data retrieved from weather radars and the numerical weather prediction (NWP) model to account for relevant precipitation microphysics. To enable multimodel-based ensemble classification, we selected six supervised machine learning models: k-nearest neighbors, logistic regression, support vector machine, decision tree, random forest, and multi-layer perceptron. Our model training and cross-validation results based on Monte Carlo Simulation (MCS) showed that all the models performed better than our baseline method, which applies two thresholds (surface temperature and atmospheric layer thickness) for binary classification (i.e., rain/snow). Among all six models, random forest presented the best classification results for the basic classes (rain, freezing rain, and snow) and the further refinement of the snow classes (light, moderate, and heavy). Our model evaluation, which uses an independent dataset not associated with model development and learning, led to classification performance consistent with that from the MCS analysis. Based on the visual inspection of the classification maps generated for an individual radar domain, we confirmed the improved classification capability of the developed models (e.g., random forest) compared to the baseline one in representing both spatial variability and continuity.

Data-driven thermal comfort model via support vector machine algorithms: Insights from ASHRAE RP-884 database

2020 ◽  
Vol 211 ◽  
pp. 109795 ◽  
Author(s):  
Xiang Zhou ◽  
Ling Xu ◽  
Jingsi Zhang ◽  
Bing Niu ◽  
Maohui Luo ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Thermal Comfort ◽  
Data Driven ◽  
Support Vector ◽  
Thermal Comfort Model

scholarly journals Forecasting of Landslide Displacement Using a Probability-Scheme Combination Ensemble Prediction Technique

2020 ◽  
Vol 17 (13) ◽  
pp. 4788 ◽  
Author(s):  
Junwei Ma ◽  
Xiao Liu ◽  
Xiaoxu Niu ◽  
Yankun Wang ◽  
Tao Wen ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Quantile Regression ◽  
Extreme Learning Machine ◽  
Data Driven ◽  
Ensemble Prediction ◽  
Three Gorges Reservoir Area ◽  
Support Vector ◽  
Landslide Displacement Prediction ◽  
Learning Machine

Data-driven models have been extensively employed in landslide displacement prediction. However, predictive uncertainty, which consists of input uncertainty, parameter uncertainty, and model uncertainty, is usually disregarded in deterministic data-driven modeling, and point estimates are separately presented. In this study, a probability-scheme combination ensemble prediction that employs quantile regression neural networks and kernel density estimation (QRNNs-KDE) is proposed for robust and accurate prediction and uncertainty quantification of landslide displacement. In the ensemble model, QRNNs serve as base learning algorithms to generate multiple base learners. Final ensemble prediction is obtained by integration of all base learners through a probability combination scheme based on KDE. The Fanjiaping landslide in the Three Gorges Reservoir area (TGRA) was selected as a case study to explore the performance of the ensemble prediction. Based on long-term (2006–2018) and near real-time monitoring data, a comprehensive analysis of the deformation characteristics was conducted for fully understanding the triggering factors. The experimental results indicate that the QRNNs-KDE approach can perform predictions with perfect performance and outperform the traditional backpropagation (BP), radial basis function (RBF), extreme learning machine (ELM), support vector machine (SVM) methods, bootstrap-extreme learning machine-artificial neural network (bootstrap-ELM-ANN), and Copula-kernel-based support vector machine quantile regression (Copula-KSVMQR). The proposed QRNNs-KDE approach has significant potential in medium-term to long-term horizon forecasting and quantification of uncertainty.

Simulation of Fluctuating Wind Speeds Based on Data-Driven Approaches

2014 ◽  
Vol 635-637 ◽  
pp. 1618-1623
Author(s):  
Yue Dan Wang ◽  
Chun Xiang Li
Keyword(s):  
Support Vector Machine ◽  
Bp Neural Network ◽  
Information Science ◽  
Prediction Models ◽  
Rapid Development ◽  
Data Driven ◽  
Support Vector ◽  
Wind Speeds ◽  
Fluctuating Wind ◽  
Simulation Time

With the rapid development of information science and technology, data-driven approaches are already being the research tide in many fields. BP neural network (BPNN), support vector machine (SVM) and least squares support vector machine (LS-SVM) are introduced and adopted to simulate fluctuating time-series wind speeds in this paper. The regression-prediction models developed by implementing machine interpolation learning are established respectively. And the original speeds used as learning and forecast samples for the simulation of the data-driven approaches are obtained through AR numerical modeling. Based on the comparison of evaluation index, the results show that the simulated fluctuating wind speeds through SVM and LS-SVM are more accurate than the simulated speeds through BPNN, but the simulation time of LS-SVM and BPNN are shorter than the SVM.

scholarly journals Least square-support vector machine based modeling for electric arc furnaces

2021 ◽  
Author(s):  
Leyla Vakilian
Keyword(s):  
Support Vector Machine ◽  
Electric Arc ◽  
Least Square ◽  
Data Driven ◽  
Electrical Network ◽  
Support Vector ◽  
Mathematical Methods ◽  
Base Function ◽  
Electric Arc Furnaces ◽  
Arc Furnaces

The process of making steel from the scrap metal by means of electric arc furnaces (EAF) has been used extensively in the industry. Accurate modelling of EAFs is, therefore, desired to assess their operations and their impacts on the electrical network. A number of approaches have already been used to model the v-i behavior of electric arc furnaces including mathematical methods and data-driven models. The objective of this thesis is to investigate the data-driven modelling methodologies, in particular, least square support vector machine (LS-SVM). The results obtained show that the proposed method with radial base function kernel provides the model to predict both arc current and arc voltage of EAFs.

scholarly journals Least square-support vector machine based modeling for electric arc furnaces

2021 ◽  
Author(s):  
Leyla Vakilian
Keyword(s):  
Support Vector Machine ◽  
Electric Arc ◽  
Least Square ◽  
Data Driven ◽  
Electrical Network ◽  
Support Vector ◽  
Mathematical Methods ◽  
Base Function ◽  
Electric Arc Furnaces ◽  
Arc Furnaces

The process of making steel from the scrap metal by means of electric arc furnaces (EAF) has been used extensively in the industry. Accurate modelling of EAFs is, therefore, desired to assess their operations and their impacts on the electrical network. A number of approaches have already been used to model the v-i behavior of electric arc furnaces including mathematical methods and data-driven models. The objective of this thesis is to investigate the data-driven modelling methodologies, in particular, least square support vector machine (LS-SVM). The results obtained show that the proposed method with radial base function kernel provides the model to predict both arc current and arc voltage of EAFs.

Sign in / Sign up

Export Citation Format

Share Document