scholarly journals Stochastic Hybrid Estimator Based Fault Detection and Isolation for Wind Energy Conversion Systems with Unknown Fault Inputs

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2227 ◽  
Author(s):  
Yun-Tao Shi ◽  
Yuan Zhang ◽  
Xiang Xiang ◽  
Li Wang ◽  
Zhen-Wu Lei ◽  
...  
Keyword(s):  
Fault Detection ◽  
Wind Energy ◽  
Energy Conversion ◽  
Closed Loop ◽  
Stochastic Dynamics ◽  
Fault Detection And Isolation ◽  
Closed Loop System ◽  
Wind Energy Conversion ◽  
Discrete States ◽  
Hybrid Estimator

In recent years, the wind energy conversion system (WECS) has been becoming the vital system to acquire wind energy. However, the high failure rate of WECSs leads to expensive costs for the maintenance of WECSs. Therefore, how to detect and isolate the faults of WECSs with stochastic dynamics is the pressing issue in the literature. This paper proposes a novel comprehensive fault detection and isolation (FDI) method for WECSs. First, a stochastic model predictive control (SMPC) controller is studied to construct the closed-loop system of the WECS. This controller is based on the Markov-jump linear model, which could precisely establish the stochastic dynamics of the WECS. Meanwhile, the SMPC controller has satisfied control performance for the WECS. Second, based on the closed-loop system with SMPC, the stochastic hybrid estimator (SHE) is designed to estimate the continuous and discrete states of the WECS. Compared with the existing estimators for WECSs, the proposed estimator is more suitable for WECSs since it considers both the continuous and discrete states of WECSs. In addition, the proposed estimator is robust to the fault input. Finally, with the proposed estimator, the comprehensive FDI method is given to detect and isolate the actuators’ faults of the WECS. Both the system status and the actuators’ faults can be detected by the FDI method and it can effectively quantify the actuators’ fault by the fault residuals. The simulation results suggest that the SHE could effectively estimate the hybrid states of the WECS, and the proposed FDI method gives satisfied fault detection performance for the actuators of the WECS.

Bond Graph Algorithms for Fault Detection and Isolation in Wind Energy Conversion

2014 ◽  
Vol 39 (5) ◽  
pp. 4057-4076 ◽  
Author(s):  
Abd Essalam Badoud ◽  
Mabrouk Khemliche ◽  
Belkacem Ould Bouamama ◽  
Seddik Bacha
Keyword(s):  
Fault Detection ◽  
Wind Energy ◽  
Energy Conversion ◽  
Graph Algorithms ◽  
Bond Graph ◽  
Fault Detection And Isolation ◽  
Wind Energy Conversion

scholarly journals Robust Fault Detection of Wind Energy Conversion Systems Based on Dynamic Neural Networks

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Nasser Talebi ◽  
Mohammad Ali Sadrnia ◽  
Ahmad Darabi
Keyword(s):  
Neural Networks ◽  
Fault Detection ◽  
Wind Energy ◽  
Energy Conversion ◽  
Neural Model ◽  
Economic Losses ◽  
Normal System ◽  
Wind Energy Conversion ◽  
Wind Energy Conversion Systems ◽  
Energy Conversion Systems

Occurrence of faults in wind energy conversion systems (WECSs) is inevitable. In order to detect the occurred faults at the appropriate time, avoid heavy economic losses, ensure safe system operation, prevent damage to adjacent relevant systems, and facilitate timely repair of failed components; a fault detection system (FDS) is required. Recurrent neural networks (RNNs) have gained a noticeable position in FDSs and they have been widely used for modeling of complex dynamical systems. One method for designing an FDS is to prepare a dynamic neural model emulating the normal system behavior. By comparing the outputs of the real system and neural model, incidence of the faults can be identified. In this paper, by utilizing a comprehensive dynamic model which contains both mechanical and electrical components of the WECS, an FDS is suggested using dynamic RNNs. The presented FDS detects faults of the generator's angular velocity sensor, pitch angle sensors, and pitch actuators. Robustness of the FDS is achieved by employing an adaptive threshold. Simulation results show that the proposed scheme is capable to detect the faults shortly and it has very low false and missed alarms rate.

scholarly journals Relevance vector machine based fault classification in wind energy conversion system

2019 ◽  
Vol 9 (3) ◽  
pp. 1506
Author(s):  
Rekha S. N. ◽  
P. Aruna Jeyanthy ◽  
D. Devaraj
Keyword(s):  
Fault Detection ◽  
Wind Energy ◽  
Energy Conversion ◽  
Relevance Vector Machine ◽  
Gaussian Kernel ◽  
Wind Energy Conversion System ◽  
Training Time ◽  
Wind Energy Conversion ◽  
Conversion System ◽  
Energy Conversion System

<p>This Paper is an attempt to develop the multiclass classification in the Benchmark fault model applied on wind energy conversion system using the relevance vector machine (RVM). The RVM could apply a structural risk minimization by introducing a proper kernel for training and testing. The Gaussian Kernel is used for this purpose. The classification of sensor, process and actuators faults are observed and classified in the implementation. Training different fault condition and testing is carried out using the RVM implementation carried out using Matlab on the Wind Energy Conversion System (WECS). The training time becomes important while the training is carried out in a bigger WECS, and the hardware feasibility is prime while the testing is carried out on an online fault detection scenario. Matlab based implementation is carried out on the benchmark model for the fault detection in the WECS. The results are compared with the previously implemented fault detection technique and found to be performing better in terms of training time and hardware feasibility.</p>

scholarly journals SVM and RVM Fault Model for Wind Energy Conversion Systm

2019 ◽  
Vol 8 (4S2) ◽  
pp. 366-371
Keyword(s):  
Fault Detection ◽  
Wind Energy ◽  
Energy Conversion ◽  
Relevance Vector Machine ◽  
Detection Technique ◽  
Support Vector ◽  
Multiple Faults ◽  
Wind Energy Conversion ◽  
Identification Technique ◽  
Multi Class Classification

The paper present the fault identification technique for wind Energy conversion system based on SVM (support vector machines) and RVM. A Relevance Vector Machine based fault detection technique and support vector machine fault detection technique with the Benchmark Model of the WECS is carried out with Multi class classification... The proposed implementation would carry out simulation which would consider multiple faults occurring simultaneously with a comparison study of both techniques can be achieved. The algorithm is carried out and the results are found to be satisfactory. The results in MATLAB shows that effective memory usage of each technique.

Sign in / Sign up

Export Citation Format

Share Document