Amel Adouni

FDI based on Artificial Neural Network for Low-Voltage-Ride-Through in DFIG-based Wind Turbine

As per modern electrical grid rules, Wind Turbine needs to operate continually even in presence severe grid faults as Low Voltage Ride Through (LVRT). Hence, a new LVRT Fault Detection and Identification (FDI) procedure has been developed to take the appropriate decision in order to develop the convenient control strategy. To obtain much better decision and enhanced FDI during grid fault, the proposed procedure is based on voltage indicators analysis using a new Artificial Neural Network architecture (ANN). In fact, two features are extracted (the amplitude and the angle phase). It is divided into two steps. The first is fault indicators generation and the second is indicators analysis for fault diagnosis. The first step is composed of six ANNs which are dedicated to describe the three phases of the grid (three amplitudes and three angle phases). Regarding to the second step, it is composed of a single ANN which analysis the indicators and generates a decision signal that describes the function mode (healthy or faulty). On other hand, the decision signal identifies the fault type. It allows distinguishing between the four faulty types. The diagnosis procedure is tested in simulation and experimental prototype. The obtained results confirm and approve its efficiency, rapidity, robustness and immunity to the noise and unknown inputs.

Voltage dip fault detection and identification based on Principal Component Analysis: Application to Wind Energy Conversion System

This paper proposes a method for voltage dip fault voltage detection and diagnosis in a grid connected Wind Turbine Generator. The method is data-driven. From the measurements of the currents flowing into the grid, three features related to the trajectory of the current vector in the Concordia stationary reference frame are extracted. The evaluation of the features for fault diagnosis is done through Principal Component Analysis. In the subspaces spanned by the principal components (2D or 3D) the faults are detected and isolated. Simulation results prove the efficiency of the method.

Current vector trajectory analysis for dip voltage fault detection and identification: Application to wind generator turbine

This paper proposes a non-parametric method to detect grid voltage dip in a Wind Turbine Generator. The method is based on the analysis of the grid currents vector trajectory in the stationary reference frame. Two features (amplitude variation and angle deviation) are extracted for Fault Detection and Isolation. The approach is validated through simulation results of a Doubly Fed Induction Generator. The results show that the method is robust to parameter and load variations. The fault detection time duration is less than one cycle.

Application of parity space approach in fault detection of DC motors

This paper deals with a fault detection and isolation (FDI) of a DC motor described by linear dynamic models. Dynamic space parity approach is used to detect sensor and actuator faults. This approach is based on obtaining an input-output description of a given system and transforming it into the parity equations. Therefore, the theoretical symptoms matrix is established. The later is compared to an experimental one to isolate the faults. The validity and usefulness of the fault detection and isolation algorithms are thoroughly verified with experiments on 1kw DC motor using a dSpace system with DS1104 controller board based on digital signal processor (DSP) TMS320F240.

Open-circuit fault detection and diagnosis in pulse-width modulation voltage source inverters based on novel pole voltage approach

In this paper, fault detection and an isolation technique for an insulated-gate bipolar transistor open-circuit fault in a voltage source inverter are presented. This technique consists of analysing the pole voltage and providing the detection and the location of simple, simultaneous and multiple faults. Open-circuit faults can be detected by sensing the pole voltage of each leg and comparing it with the theoretical one. To improve the calculation speed and reliability of this technique and to avoid false diagnosis alarms, the fault detection and isolation scheme is based on a novel model of pole voltage taking into account the time delays due to the turn-on and turn-off process of the power switches. This method reduces the detection time and is applied for open-loop or closed-loop faults in a transient or steady state.

DC-DC converter fault diagnostic in PV system

The photovoltaic (PV) system productivity is a decisive factor. To achieve a high productivity, the system availability should be checked. So even under a faulty situation, the system should operate continuously. As a proposed solution, the fault tolerant control (FTC) is recommended. In advance of FTC strategy, the fault diagnosis should be achieved. This paper deals with the open circuit fault occurred in the DC-DC converter. The Artificial Neural Network (ANN) is used to estimate the current and the voltage feeding the resistive load. These signals are compared to the measured ones. So, the proposed approach allows generating different signals in order to detect and to isolate the open circuit fault. The signals are the residuals and the flags. The fault is successfully detected and isolated.

Data-driven approach for dip voltage fault detection and identification based on grid current vector trajectory analysis

This paper proposes a data driven approach for dip voltage fault detection and identification using the grid current vector trajectory in the stationary reference frame. Three features are extracted for the different operating conditions to build the database and analysed using Linear Discriminant Analysis to identify the fault type and subtype. In the subspaces spanned by the factorial components the four faults and eight out of nine faults subtype are successfully identified and isolated with an error rate less than 5%. Simulation results prove the efficiency of the proposed algorithm.

Dip fault detection and identification for wind conversion energy system

This paper addresses the problem of detecting voltage dips in Wind Turbine Generator connected to electrical grid. A procedure based on analysis of voltage indicators is proposed. It used the artificial neural network in order to extract the features (magnitudes and angle of each phase). The method is tested in simulation and the results approved its efficiency and rapidity. It could not only detect the dip fault but also identify the type of fault.