Structural Health Monitoring Of Wind Turbines Research Articles

Damage Detection and Localization at the Jacket Support of an Offshore Wind Turbine Using Transformer Models

Early detection of damage in the support structure (submerged part) of an offshore wind turbine is crucial as it can help to prevent emergency shutdowns and extend the lifespan of the turbine. To this end, a promising proof-of-concept is stated, based on a transformer network, for the detection and localization of damage at the jacket-type support of an offshore wind turbine. To the best of the authors’ knowledge, this is the first time transformer-based models have been used for offshore wind turbine structural health monitoring. The proposed strategy employs a transformer-based framework for learning multivariate time series representation. The framework is based on the transformer architecture, which is a neural network architecture that has been shown to be highly effective for natural language processing tasks. A down-scaled laboratory model of an offshore wind turbine that simulates the different regions of operation of the wind turbine is employed to develop and validate the proposed methodology. The vibration signals collected from 8 accelerometers are used to analyze the dynamic behavior of the structure. The results obtained show a significant improvement compared to other approaches previously proposed in the literature. In particular, the stated methodology achieves an accuracy of 99.96% with an average training time of only 6.13 minutes due to the high parallelizability of the transformer network. In fact, as it is computationally highly efficient, it has the potential to be a useful tool for implementation in real-time monitoring systems.

Rotor anisotropy as a blade damage indicator for wind turbine structural health monitoring systems

Structural damage of a rotor blade causes structural anisotropy of the rotor. In rotor dynamic, the anisotropy affects the symmetry of the rotor mode shapes, and the latter can be utilized to detect the blade damage. The mode shape symmetry can be characterized by relative blades’ magnitude and phase. The study examines the potential use of these parameters as rotor damage indicators.Firstly the indicators are studied analytically using a simple 6 degrees-of-freedom model of a rotating rotor. Floquet analysis is used due to the time periodic nature of the considered system. Floquet analysis allows one to perform analytical modal decomposition of the system and study the sensitivity of the damage indicators to the amount of damage. Secondly, operational modal analysis (OMA) is involved to extract the same damage indicators from simulated experimental data, which was synthesized via numerical simulations.Finally, the same procedure was applied to operating Vestas V27 wind turbine, first using the simulated experimental data obtained by using aeroelastic simulation code HAWC2 and then using the data acquired during the measurement campaign on a real wind turbine.The study demonstrates that the proposed damage indicators are significantly more sensitive than the commonly used changes in natural frequency, and in contrast to the latter, can also pinpoint the faulty blade. It is also demonstrated that these indicators can be derived from blades vibration data obtained from real life experiment.

Monitoring the Dynamics of a Helicopter Main Rotor With High-Speed Stereophotogrammetry

Stereophotogrammetry in conjunction with three-dimensional point tracking (3DPT) algorithms has proven to be a highly robust dynamic measurement technique on small, rotating bladed systems. This measurement technique can be scaled up to much larger systems and has several desirable features for helicopter and wind turbine structural health monitoring (SHM) applications that include: (1) it is noncontact and does not require the use of roll/slip rings for signal transmission; (2) the applied measurement targets negligibly affect the aerodynamics or structural mass/stiffness; and (3) position data can be collected on many hundreds of points over what is capable using conventional multichannel data acquisition (DAQ) systems. A field test was conducted in which operating data were collected on the main rotor of a helicopter in both grounded and hovering operating conditions. Part 1 of this work describes the experimental setup and DAQ process of the test performed and part 2 of this work presents some of the results including blade dynamics and extracted operating deflection shape information for the helicopter. The promising results presented in this work will serve as the foundation for the development of noncontacting SHM techniques that can be applied to large, rotating bladed structures while in operation.

An SHM View of a CFD Model of Lillgrund Wind Farm

Reliability of offshore wind farms is one of the key areas for the successful implementation of these renewable power plants in the energy arena. Failure of the wind turbine (WT) in general could cause massive financial losses but especially for structures that are operating in offshore sites. Structural Health Monitoring (SHM) of WTs is essential in order to ensure not only structural safety but also avoidance of overdesign of components that could lead to economic and structural inefficiency. A preliminary analysis of a machine learning approach in the context of WT SHM is presented here; it is based on results from a Computational Fluid Dynamics (CFD) model of Lillgrund Wind farm. The analysis is based on neural network regression and is used to predict the measurement of each WT from the measurements of other WTs in the farm. Regression model error is used as an index of abnormal response.

Development of wireless laser blade deflection monitoring system for mobile wind turbine management host

This study proposes a wireless laser displacement sensor system for in situ deflection monitoring of wind turbine blades. This system consists of a tower-installed laser displacement sensor system composed of a laser displacement sensor head, controller, Zigbee transmitter, and analog-to-digital converter module, combined with a mobile host that includes a Zigbee receiver and a laptop. In contrast to the approach of blade sensor installation, the laser displacement sensor system is installed in the tower to enable noncontact blade displacement monitoring. The concepts of direct noncontact remote sensing and actuation from the tower and remote power delivery from the tower to blade-installed sensors and actuators will enable various approaches for wind turbine structural health monitoring. The proposed system can easily identify problems related to deflection. The size of wind blades increases with energy demands. Due to the large size of wind turbines, current wind turbines are installed very high above ground level. It is impractical to monitor the results from laser displacement sensor through wired connection in these cases. Hence, wired connections of laser displacement sensors to base monitoring stations must be replaced with a wireless solution. This wireless solution is achieved using Zigbee technology. The output from the laser displacement sensor is fed to a microcontroller, which acts as an analog-to-digital converter. The output from the microcontroller is connected to the Zigbee transceiver module, which transmits the data, and at the other end, the Zigbee reads the data and displays it on a PC, from which users can monitor the condition of the wind blades.

Development of a FBG based distributed strain sensor system for wind turbine structural health monitoring

The development of a fiber Bragg grating (FBG) based distributed strain sensor system for real time structural health monitoring of a wind turbine rotor and its validation under a laboratory scale test setup is discussed in this paper. A 1 kW, 1.6 m diameter rotor, horizontal axis wind turbine with three instrumented blades is used in this study. The sensor system consists of strain sensors, surface mounted at various locations on the blade. At first the sensors are calibrated under static loading conditions to validate the FBG mounting and the proposed data collection techniques. Then, the capability of the sensor system coupled with the operational modal analysis (OMA) methods to capture natural frequencies and corresponding mode shapes in terms of distributed strains are validated under various non-rotating dynamic loading conditions. Finally, the sensor system is tested under rotating conditions using the wind flow from an open-jet wind tunnel, for both a baseline wind turbine and a wind turbine with a structurally modified blade. The blade was modified by attaching a lumped mass at the blade tip simulating structural damage or ice accretion. The dynamic characteristics of the baseline (healthy) blade and modified (altered) blade are compared to validate the sensor system’s ability for real time structural health monitoring of the rotor.

<i>In Situ</i> Blade Deflection Monitoring of a Wind Turbine Using a Wireless Laser Displacement Sensor Device within the Tower

With commercially viable global wind power potential, wind energy penetration is further expected to rise, as will the related problems. One issue is the collision of wind turbine blades with the tower during operation. Structured health monitoring is required to improve operational safety, minimize the risk of sudden failure or total breakdown, ensure reliable power generation, and reduce wind turbine life cycle costs. Large numbers of sensors such as fiber Bragg grating and piezoelectric devices have been attached to the structure, a design that is uneconomical and impractical for use in large wind turbines. This study proposes a single laser displacement sensor (LDS) system in which all of the rotating blades could be cost-effectively evaluated. Contrary to the approach of blade sensor installation, the LDS system is installed in the tower to enable noncontact blade displacement monitoring. The concept of a noncontact sensor and actuator and their energy delivery device installation in the tower will enable various approaches for wind turbine structural health monitoring. Blade bolt loosening causes deflection in the affected blade. Similarly, nacelle tilt or mass loss damage in the blade will result in changes in blade deflection, but the proposed system can identify such problems with ease. With the need of more energy, the sizes of wind blades are getting bigger and bigger. Due to the large size of wind turbine, nowadays wind turbines are installed very high above the ground or water level. It is impractical to monitor the results from LDS through wired connection in these cases. Hence, the wired connection of LDS to base (monitoring) station must be replaced by a wireless solution. This wireless solution is achieved using Zigbee technology. Zigbee operates in the industrial, scientific and medical (ISM) radio bands, typically 2.4 GHz, 915 MHz and 868 MHz. The output from the LDS is fed to the microcontroller which acts as an analog to digital converter. The output from the microcontroller is connected to the Zigbee transceiver module, which transmits the data and at the other end, the zigbee reads the data and displays on the PC from where user can monitor the condition of wind blades.

Feasibility of in situ blade deflection monitoring of a wind turbine using a laser displacement sensor within the tower

With the potential of commercially viable global wind power, the use of wind energy is expected to rise further, along with related problems. One issue is collision of the wind turbine blades with the tower during operation. Structural health monitoring is required to improve operational safety, minimize the risk of sudden failure or total breakdown, ensure reliable power generation, and reduce wind turbine life cycle costs. To this end, large numbers of sensors such as fiber Bragg grating and piezoelectric devices have been attached to the structure, which is uneconomical and impractical for large wind turbines. This study proposes a single laser displacement sensor (LDS) system in which all of the rotating blades can be cost-effectively evaluated. In contrast to the approach of blade sensor installation, the LDS system is installed in the tower to enable noncontact blade displacement monitoring. The concept of a noncontact sensor and actuator and their energy delivery device installed in the tower will enable various approaches for wind turbine structural health monitoring. Blade bolt loosening can cause deflection in an affected blade. Similarly, nacelle tilt or mass loss damage in a blade can result in changes in blade deflection, but the proposed system can detect such problems early on.