Fault Diagnosis of Advanced Wind Turbine Benchmark using Interval-based ARRs and Observers

Abstract

Abstract-This paper proposes a model-based fault diagnosis approach for wind turbines and its application to a realistic wind turbine fault diagnosis benchmark. The proposed fault diagnosis approach combines the use of analytical redundancy relations (ARRs) and interval observers. Interval observers consider an unknown but bounded description of the model parametric uncertainty and noise using the the so-called set-membership approach. This approach leads to formulate the fault detection test by means of checking if the measurements fall inside the estimated output interval, obtained from the mathematical model of the wind turbine and noise/parameter uncertainty bounds. Fault isolation is based on considering a set of ARRs obtained from structural analysis of the wind turbine model and a fault signature matrix that considers the relation of ARRs and faults. The proposed fault diagnosis approach has been validated on a 5MW wind turbine using the NREL FAST simulator. The obtained results are presented and compared with other approaches proposed in the literature.Index Terms-Analytical redundant relations, interval-based observers, model-based fault diagnosis, wind turbines.

Real-time fault diagnosis and fault-tolerant control

“…There are three papers that deal with model-based fault diagnosis methods [12][13][14], all with applications to wind turbine energy systems. In the paper [12] contributed by Simani et al, Takagi-Sugeno fuzzy model based fault detection and isolation methods are proposed, where the fuzzy models are derived using fuzzy clustering and dynamic system identification techniques.…”

“…The effectiveness of the proposed approach is tested on the data acquired from the simulated wind turbine benchmark. The paper [13] authored by Sanchez et al, applies a model-based diagnosis approach to an advanced wind turbine benchmark under several fault scenarios by using interval based analytical redundancy relations (static and dynamic) and observers. In most cases, Real-Time Fault Diagnosis and Fault-Tolerant Control the proposed methods have proven to be able to detect faults with different types (e.g., scaling, offset and stuck) by taking into account modelling errors and measurement noises in the 5MW benchmark.…”

“…Twelve selected papers pay attention on fault diagnosis methods and applications [10][11][12][13][14][15][16][17][18][19][20][21], and the other eleven papers are concentrated on real-time fault tolerant control and applications [22][23][24][25][26][27][28][29][30][31][32]. We are going to overview the selected papers following fault diagnosis techniques and fault-tolerant control techniques sequentially.…”

“…Therefore, knowledge-based diagnosis method is also called data-driven fault diagnosis methods (e.g., see the survey paper [10,11]). The selected research papers [12][13][14][15][16][17][18][19][20][21] fall into the respective categories readily (e.g., see Table 1). …”

A Data-Mining Approach for Wind Turbine Power Generation Performance Monitoring Based on Power Curve

“…But traditional datamining methods which detect weakened performance through building model training of the datasets with certain ratio generally have inevitable prediction error, so the identification of the poor power generation performance of turbines is not accurately for the real-time data [3][4][5].…”