Wind Turbines Fault Diagnosis Using Ensemble Classifiers

Santos, Pedro; Villa, Luisa F.; Reñones, Aníbal; Bustillo, Andrés; Maudes, Jesús

doi:10.1007/978-3-642-31488-9_6

Cited by 10 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The cases that are significantly worse than this best method are indicated with an asterisk. The accuracy obtained by an SVM with linear kernels is also of a higher statistical significance than the results of a previous study of this dataset using ensembles (96.24%) [ 20 ].…”

Section: Resultsmentioning

confidence: 54%

“…Once signals from the sensors have been acquired, different techniques can be used to extract as much information as possible from these data, so as to build-up a suitable decision-making system for failure detection in wind turbines. Previous studies have applied different data-mining techniques to this industrial task, such as SVM [ 15 , 16 ], Bayesian networks [ 17 ], self-organizing maps [ 18 ], ANNs [ 19 ], ensemble classifiers [ 20 ] and neuro-fuzzy inference systems [ 16 ]. Moreover, recent works have proven the suitability of AI techniques for other similar industrial tasks, such as evaluation of the mechanical properties in rapid prototyping using ensembles [ 21 ], tool condition monitoring using ν -SVM [ 22 ] and ensembles of SVMs, hidden Markov model and the radius basis function [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

“…Similar schemes have been successfully applied to other industrial tasks, such as breakage detection [ 30 , 31 ] and roughness prediction [ 32 ]. In a previous study, we analyzed this dataset using ensemble classifiers [ 20 ], as this technique has been successfully applied to other similar industrial problems [ 24 , 32 ]. However, in this new work, we have obtained better statistically-significant results and a more reliable diagnosis system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An SVM-Based Solution for Fault Detection in Wind Turbines

Santos

Villa²,

Reñones³

et al. 2015

Sensors

Self Cite

188

108

View full text Add to dashboard Cite

Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets.

show abstract

Section: Resultsmentioning

confidence: 54%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An SVM-Based Solution for Fault Detection in Wind Turbines

Santos

Villa²,

Reñones³

et al. 2015

Sensors

Self Cite

188

108

View full text Add to dashboard Cite

show abstract

“…仿真和实验信号表明, 该方法对齿轮箱的工况波动具有较高的鲁棒性. 2012 年, 西班牙的 Santos 等人 [168] 在阶次跟踪的基础上, 通过时、频域的特征指标值, 采用集成分类器对风电行星齿轮箱的失衡和不对中故障进行识别和分类. 2012 年, 意大利的 Villa 等人 [169] 采用阶次跟踪和统计显著水平分析用于变转速下的风电齿轮箱诊断.…”

Section: 尺故障特征进行提取 2009 年加拿大劳伦森大学的unclassified

Dynamic signal analysis for speed-varying machinery: A review

Lin¹,

Zhao²

2015

Sci. Sin.-Tech.

View full text Add to dashboard Cite

“…Neither of these studies used ensembles for process modeling, a learning paradigm in which multiple learners (or regressors) are combined to solve a problem. A regressor ensemble can significantly improve the generalization ability of a single regressor and can provide better results than an individual regressor in many applications [30][31][32]. Ensembles have demonstrated their suitability for modeling macroscale milling and drilling [33][34][35][36], especially because they can achieve highly accurate prediction with lower tuning time of the model parameters [35].…”

Section: Introductionmentioning

confidence: 99%

Modelling Laser Milling of Microcavities for the Manufacturing of DES with Ensembles

Santos

Teixidor

Maudes

et al. 2014

Journal of Applied Mathematics

Self Cite

View full text Add to dashboard Cite

A set of designed experiments, involving the use of a pulsed Nd:YAG laser system milling 316L Stainless Steel, serve to study the laser-milling process of microcavities in the manufacture of drug-eluting stents (DES). Diameter, depth, and volume error are considered to be optimized as functions of the process parameters, which include laser intensity, pulse frequency, and scanning speed. Two different DES shapes are studied that combine semispheres and cylinders. Process inputs and outputs are defined by considering the process parameters that can be changed under industrial conditions and the industrial requirements of this manufacturing process. In total, 162 different conditions are tested in a process that is modeled with the following state-of-the-art data-mining regression techniques: Support Vector Regression, Ensembles, Artificial Neural Networks, Linear Regression, and Nearest Neighbor Regression. Ensemble regression emerged as the most suitable technique for studying this industrial problem. Specifically, Iterated Bagging ensembles with unpruned model trees outperformed the other methods in the tests. This method can predict the geometrical dimensions of the machined microcavities with relative errors related to the main average value in the range of 3 to 23%, which are considered very accurate predictions, in view of the characteristics of this innovative industrial task.

show abstract

Wind Turbines Fault Diagnosis Using Ensemble Classifiers

Cited by 10 publications

References 23 publications

An SVM-Based Solution for Fault Detection in Wind Turbines

An SVM-Based Solution for Fault Detection in Wind Turbines

Dynamic signal analysis for speed-varying machinery: A review

Modelling Laser Milling of Microcavities for the Manufacturing of DES with Ensembles

Contact Info

Product

Resources

About