Evaluation of Machine Learning Methods for Monitoring the Health of Guyed Towers

This paper presents the development of a methodology to detect and evaluate faults in cable-stayed towers, which are part of the infrastructure of Brazil’s interconnected electrical system. The proposed method increases system reliability and minimizes the risk of service failure and tower collapse through the introduction of predictive maintenance methods based on artificial intelligence, which will ultimately benefit the end consumer. The proposed signal processing and interpretation methods are based on a machine learning approach, where the tower vibration is acquired from accelerometers that measure the dynamic response caused by the effects of the environment on the towers through wind and weather conditions. Data-based models were developed to obtain a representation of health degradation, which is primarily based on the finite element model of the tower, subjected to wind excitation. This representation is also based on measurements using a mockup tower with different types of provoked degradation that was subjected to ambient changes in the laboratory. The sensor signals are preprocessed and submitted to an autoencoder neural network to minimize the dimensionality of the resources involved, being analyzed by a classifier, based on a Softmax configuration. The results of the proposed configuration indicate the possibility of early failure detection and evolution evaluation, providing an effective failure detection and monitoring system.

Influence of the Flexible Tower on Aeroelastic Loads of the Wind Turbine

The finite element discretization of a tower system based on the two-node Euler-Bernoulli beam is carried out by taking the cubic Hermite polynomial as the form function of the beam unit, calculating the structural characteristic matrix of the tower system, and establishing the wind turbine-nacelle-tower multi-degree-of-freedom finite element numerical model. The equation for calculating the aerodynamic load for any nacelle attitude angle is derived. The effect of the flexible tower vibration feedback on the aerodynamic load of the wind turbine is studied. The results show that, when the stiffness of the tower is large, the effect of having tower vibration feedback or not on the aeroelastic load of the wind turbine is small. For the more flexible tower system, wind-induced vibration time-varying feedback will cause larger aeroelastic load variations, especially the top of the tower overturning moment, thus causing a larger impact on the dynamic behavior of the tower downwind and crosswind. As the flexibility of the tower system increases, the interaction between tower vibration and pneumatic load is also gradually increasing. Taking into account the influence of flexible towers on the aeroelastic load of a wind turbine can help predict the pneumatic load of a wind turbine more accurately and improve the efficiency of wind energy utilization on the one hand and analyze the dynamic behavior of the flexible structure of a wind turbine more accurately on the other hand, which is extremely beneficial to the structural optimization of wind turbine.

Influence of the Flexible Tower on Aeroelastic Loads of the Wind Turbine

Based on the two-node Euler-Bernoulli beam, the tower system is discretized by finite element method, and the cubic Hermite polynomial is taken as the shape function of the beam element, and the structural characteristic matrix of the tower system is calculated, and the wind turbine-nacelle-tower multi-degree of freedom is established Finite element numerical model. The aerodynamic load calculation formula for any nacelle attitude angle is deduced. The influence of the vibration feedback of the flexible tower on the aerodynamic load of the wind turbine is studied. The results show that when the rigidity of the tower is large, the impact of tower vibration feedback on the aeroelastic load of the wind turbine is small. For a tower system with greater flexibility, the time-varying feedback of wind-induced vibration will cause greater aeroelastic load changes, especially the overturning moment of the tower top, which will cause a greater impact on the dynamic behavior of the tower in the downwind and crosswind directions. As the flexibility of the tower system increases, the interaction between tower vibration and aerodynamic load is gradually increasing. Taking the impact of the flexible tower on the aeroelastic load of the wind turbine into account, on the one hand, helps to predict the wind more accurately. The aerodynamic load of the wind turbine improves the efficiency of wind energy utilization. On the other hand, it can more accurately analyze the dynamic behavior of the flexible structure of the wind turbine, which is extremely beneficial to the structural optimization design of the wind turbine.

Dynamic Analysis of Flexible Wind Turbine Tower by a Transfer Matrix Method

To generate more power, wind turbine rotors are growing in size and consequently, wind turbine tower are becoming increasingly taller and more flexible. As a result, fluid–structure interaction (FSI) of the flexible tower caused by strong wind is a very important phenomenon, and tower vibration must be carefully considered. In this paper, the physical model of the wind turbine tower is simplified appropriately, and then a multi-body dynamics model of wind turbine tower system is established based on Transfer Matrix Method of Multibody System (MSTMM). Compared with the data from finite element model (FEM) and field tests, the simulation results show that the model has a good accuracy. By coupling the mode shapes with two degrees of freedom (2-DOF) wake oscillator model, the dynamic responses of the flexible tower are computed. The influence of various foundation stiffness and top mass on tower vibration is studied systematically using this model. The results indicate that different boundary conditions can affect the maximum amplitude and displacement along the axis of the tower. This work provides a reference for dynamic modeling and simulation of high-rise flexible structure, and the prediction of the maximum amplitude of the tower vibration, which can be used for aeroelastic control purpose.

Vertical Stiffness Functions of Rigid Skirted Caissons Supporting Offshore Wind Turbines

Suction Bucket Jackets (SBJs) need to be fundamentally designed to avoid rocking modes of vibration about the principal axes of the set of foundations and engineered towards sway-bending modes of tower vibration. Whether or not such type of jackets exhibit rocking modes depends on the vertical stiffness of the caissons supporting them. This paper therefore derives closed form solutions for vertical stiffness in three types of ground profiles: linear, homogenous, and parabolic. The expressions are applicable to suction caissons having an aspect ratio (depth: diameter) between 0.2 and 2 (i.e., 0.2 < L/D < 2). The work is based on finite element analysis followed by non-linear regression. The derived expressions are then validated and verified using studies available in literature. Finally, an example problem is taken to demonstrate the application of the methodology whereby fundamental natural frequency of SBJ can be obtained. These formulae can be used for preliminary design and can also be used to verify rigorous finite element analysis during detailed design.

Effective wind speed estimation based on a data-driven model of wind turbine tower deflection

The deflection of the wind turbine tower can provide us with rich information about the effective wind speed. In this paper, a new method for effective wind speed estimation is proposed based on tower deflection. The tower vibration model is derived and a subspace identification method is used to identify the model parameters. An online estimator of aerodynamic thrust force based on the identified tower model is designed and then implemented using a Kalman filter together with a recursive least squares algorithm. The estimated aerodynamic thrust force is then used as an input to a neural network estimator, which is trained to invert the aerodynamic thrust force equation and estimate the effective wind speed. In order to show the performance of the proposed estimator, the estimated thrust force and wind speed are compared and verified with a third-party simulation data of a 1.5 MW wind turbine. The comparison shows close agreement between their values.

Design and Verification of the LQR Controller Based on Fuzzy Logic for Large Wind Turbine

In this study, a linear quadratic regulator based on the fuzzy logic (LQRF) control algorithm for a variable-speed variable-pitch wind turbine was designed. In addition, to verify the optimum performance of the controller, simulations and wind tunnel tests were conducted. In the simulation, the performances of the proportional-integral (PI) and LQRF algorithms were compared in the transition region and the rated power region. In the wind tunnel test, the applicability of the LQRF algorithm was verified by comparing it with the conventional PI algorithms. The results showed that when compared with the PI control, the proposed LQRF control reduced the tower vibration by up to 12.50% depending on the operating region. Furthermore, the power deviation was reduced by 38.93%. These tests confirmed that the proposed LQRF control increases the power performance and structural stability of wind turbines compared with conventional PI controls.