In this work we are addressing the problem of statistical modeling of the joint distribution of data collected from wind turbines interacting due to collective effect of their placement in a wind-farm, the wind characteristics (speed/orientation) and the turbine control. Operating wind turbines extract energy from the wind and at the same time produce wakes on the down-wind turbines in a park, causing reduced power production and increased vibrations, potentially contributing in a detrimental manner to fatigue life. This work presents a Variational Auto-Encoder (VAE) Neural Network architecture capable of mapping the high dimensional correlated stochastic variables over the wind-farm, such as power production and wind speed, to a parametric probability distribution of much lower dimensionality. We demonstrate how a trained VAE can be used in order to quantify levels of statistical deviation on condition monitoring data. Moreover, we demonstrate how the VAE can be used for pretraining an inference model, capable of predicting the power production of the farm together with bounds on the uncertainty of the predictions. Examples employing simulated wind-farm Supervisory Control And Data Acquisition (SCADA) data are presented. The simulated farm data are acquired from a Dynamic Wake Meandering (DWM) simulation of a small wind farm comprised of nine 5MW turbines in close spacing using OpenFAST. The contribution of this work lies in the introduction of state-of-the-art machine learning techniques in the general context of condition monitoring and uncertainty quantification. We show how the high dimensional joint probability distribution of condition monitoring parameters can be analyzed by exploiting the underlying lower dimensional structure of the data imposed by the physics of the problem. The process of making use of the trained joint distribution for the purposes of inference under uncertainty and condition monitoring is clearly exposed.
Wind turbine fatigue estimation is based on time‐consuming Monte Carlo simulations for various wind conditions, followed by cycle‐counting procedures and the application of engineering damage models. The outputs of the fatigue simulations are large in volume and of high dimensionality, as they typically consist of estimates on finite‐element computational meshes. The strain and stress tensor time series, which are the primary quantities of interest when considering the problem of fatigue estimation, are dictated by complex vibration characteristics due to the coupled effect of aerodynamics, structural dynamics, geometrically non‐linear mechanics, and control. A Variational Auto‐Encoder (VAE) is trained in order to model the probability distribution of the accumulated fatigue on the root cross‐section of a simulated wind turbine blade. The VAE is conditioned on historical data that correspond to coarse wind‐field measurement statistics, such as mean hub‐height wind speed, standard deviation of hub‐height wind speed and shear exponent. In the absence of direct measurements of structural loads, the proposed technique finds applications in making long‐term probabilistic deterioration predictions from historical Supervisory, Control, and Data Acquisition (SCADA) data, while capturing the inherent aleatoric uncertainty due to the incomplete information on strain time series of the wind turbine structure, when only SCADA data statistics are available.
A computational approach for the estimation of fatigue degradation of composite wind turbine blades by means of time domain aero-servo-elastic simulations is proposed. Wind turbine blades are subjected throughout their lifetime to highly stochastic loading. Fatigue damage of the composite reinforcement of the wind turbine blades has been identified early on in the wind turbine design practice as a factor driving design. A simple fatigue accumulation model is utilized for the spar cap reinforcement of a wind-turbine blade. Non-Negative Matrix Factorization (NMF) for the damage accumulation random field is used for dimensionality reduction. An approximate computationally efficient model, relying on Polynomial Chaos Expansion (PCE) of the damage state with respect to probabilistically modelled mean wind and turbulence intensity is derived. The framework is exemplified in a case-study of a 1.5MW wind turbine.
Attempts have been made recently in the field of population-based structural health monitoring (PBSHM), to transfer knowledge between SHM models of different structures. The attempts have been focussed on homogeneous and heterogeneous populations. A more general approach to transferring knowledge between structures, is by considering all plausible structures as points on a multidimensional base manifold and building a fibre bundle. The idea is quite powerful, since, a mapping between points in the base manifold and their fibres, the potential states of any arbitrary structure, can be learnt. A smaller scale problem, but still useful, is that of learning a specific point of every fibre, i.e. that corresponding to the undamaged state of structures within a population. Under the framework of PBSHM, a data-driven approach to the aforementioned problem is developed. Structures are converted into graphs and inference is attempted within a population, using a graph neural network (GNN) algorithm. The algorithm solves a major problem existing in such applications. Structures comprise different sizes and are defined as abstract objects, thus attempting to perform inference within a heterogeneous population is not trivial. The proposed approach is tested in a simulated population of trusses. The goal of the application is to predict the first natural frequency of trusses of different sizes, across different environmental temperatures and having different bar member types. After training the GNN using part of the total population, it was tested on trusses that were not included in the training dataset. Results show that the accuracy of the regression is satisfactory even in structures with higher number of nodes and members than those used to train it.
In this work, a novel approach, termed GNN-tCNN, is presented for the construction and training of Remaining Useful Life (RUL) models. The method exploits Graph Neural Networks (GNNs) and deals with the problem of efficiently learning from time series with non-equidistant observations, which may span multiple temporal scales. The efficacy of the method is demonstrated on a simulated stochastic degradation dataset and on a real-world accelerated life testing dataset for ball-bearings. The proposed method learns a model that describes the evolution of the system implicitly rather than at the raw observation level and is based on message-passing neural networks, which encode the irregularly sampled causal structure. The proposed approach is compared to a recurrent network with a temporal convolutional feature extractor head (LSTM-tCNN), which forms a viable alternative for the problem considered. Finally, by taking advantage of recent advances in the computation of reparametrization gradients for learning probability distributions, a simple, yet efficient, technique is employed for representing prediction uncertainty as a gamma distribution over RUL predictions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.