Extreme learning machine for fault detection and isolation in wind turbine

Bakri, Ayoub El; Koumir, Miloud; Boumhidi, Ismail

doi:10.1109/eitech.2016.7519584

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our approach, we use the extreme learning machine (ELM) [3,21] for intrusion detection. The ELM algorithm has been used in a diverse set of applications including water quality forecasting [22], optimization of industrial chemical productions [23], big data processing [24], speech enhancement [25], heart disease diagnosis [26], medical image segmentation [27], and fault detection [28,29].…”

Section: Related Workmentioning

confidence: 99%

Multi-layer intrusion detection system with ExtraTrees feature selection, extreme learning machine ensemble, and softmax aggregation

Sharma

Giri

Granmo

et al. 2019

EURASIP J. on Info. Security

View full text Add to dashboard Cite

Recent advances in intrusion detection systems based on machine learning have indeed outperformed other techniques, but struggle with detecting multiple classes of attacks with high accuracy. We propose a method that works in three stages. First, the ExtraTrees classifier is used to select relevant features for each type of attack individually for each (ELM). Then, an ensemble of ELMs is used to detect each type of attack separately. Finally, the results of all ELMs are combined using a softmax layer to refine the results and increase the accuracy further. The intuition behind our system is that multi-class classification is quite difficult compared to binary classification. So, we divide the multi-class problem into multiple binary classifications. We test our method on the UNSW and KDDcup99 datasets. The results clearly show that our proposed method is able to outperform all the other methods, with a high margin. Our system is able to achieve 98.24% and 99.76% accuracy for multi-class classification on the UNSW and KDDcup99 datasets, respectively. Additionally, we use the weighted extreme learning machine to alleviate the problem of imbalance in classification of attacks, which further boosts performance. Lastly, we implement the ensemble of ELMs in parallel using GPUs to perform intrusion detection in real time.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-layer intrusion detection system with ExtraTrees feature selection, extreme learning machine ensemble, and softmax aggregation

Sharma

Giri

Granmo

et al. 2019

EURASIP J. on Info. Security

View full text Add to dashboard Cite

show abstract

“…Nielson et al (2020) have improved the wind turbine power prediction via machine learning models, which is very useful for the multi-input system to implement the uncontrolled parameters (wind speed, air density, turbulence intensity Richardson number, and wind shear) for the 4-layer Feed-Forward Back-Propagation (FFBP) Artificial Neural Network (ANN) to reduce the Mean Absolute Error (MAE). Bakri et al (2016) have concluded that fault detection needs a fast modeling algorithm to detect the residual signal which is the difference between the predictive power by the Extreme Learning Machine (ELM) and the actual measured power. Shair et al (2021) have published a detailed comparison of models-based stability analysis of wind power systems in time and frequency domains.…”

Section: Introductionmentioning

confidence: 99%

“…Well-established models of wind energy systems facilitate the simulations of the turbine-generator units' power variations in advance and allow timely and authentic decision-makings by operators and engineers in the plant control center. However, there are many recognized techniques for time-based dynamic modeling; and thus there is an urgent demand to provide a comprehensive comparison of the different modeling techniques for the suitability of future applications, such as prediction (Qatamin et al, 2020), control of the turbines (Labidi et al, 2017), reduction of fluctuation (Ahmad and Mohamed, 2019), fault detection (Bakri et al, 2016), and so on. Several modeling techniques are produced in the past years, which can be computationally classified into three categories: Physics-based Models, System Identification (SI) Models, and Machine Learning or ANN Models.…”

Section: Introductionmentioning

confidence: 99%

A comparative study of wind turbine-generator modeling techniques: Physical modeling, subspace identification, and dynamic neural networks

2021

View full text Add to dashboard Cite

The increase of the favorable impacts of wind energy on the environment and the global energy requires overall understanding of the modeling methods that are commonly used for time-based simulation of wind energy systems. This paper introduces a comprehensive comparison of three salient modeling techniques of wind energy conversion systems, which are: the physical modeling, subspace system identification, and Dynamic Neural Network (ANN). The models have been created with the different modeling philosophies with the aid of historical data-sets representing four apart days of operation. The real system incorporates (TWT-1.65) type Wind-Turbine intergated with Multi-Pole Synchronous Generators (MPSG). The compariosn provides some crucial answers to the concerns of which technique is suited for an application, consequently, the comparison includes quantitative and qualitative measures. This article can be considered as a brief guide for future researchers to have thorough understanding of the modeling concepts in the field of wind engineering.

show abstract