4 January 2018 in IEEE Transactions on Sustainable Energy
The massive amounts of spatio-temporal data collected in today's wind farms have created a necessity for accurate spatio-temporal models. Despite the growing recognition for nonseparable spatio-temporal models, a significant reliance on separable, symmetric models is still the norm in today's renewable industry. We discover that the broad use of separable models is due to the handling of wind data in a setting that does not reveal their fine-scale spatio-temporal structure. The contribution of this research is twofold. First, we devise a special pair of spatio-temporal “lens” that allows us to see the fine-scale spatio-temporal variations and interactions, and subsequently, we conclude that local wind fields exhibit strong signs of nonseparability and asymmetry. Using one year of turbine-specific wind measurements, we show that asymmetry can, in fact, be detected in more than 93% of the time. Second, making use of the spatio-temporal lens, we propose an enhanced procedure for short-term wind speed forecast. Substantial improvements in forecast accuracy in both wind speed and wind power were observed. When combined with certain intelligent methods such as support vector machine, additional improvements are possible.
9 July 2018 in IEEE Transactions on Automation Science and Engineering
Anomalies are data points or a cluster of data points that lie away from the neighboring points or clusters and are inconsistent with the overall pattern of the data. Anomaly detection techniques help distinguish the anomalous observations from the regular ones, and thus provide the basis for developing a standard performance guideline for process control. The process of identifying anomalies becomes complicated in the absence of labeled training data as in supervised learning. Moreover, Euclidean distance between two points is less likely able to reflect the intrinsic structural distance imposed by the underlying manifold structure. In this paper, the authors propose a minimum spanning tree (MST)-based anomaly detection method. The merit of the method is that an MST provides a new distance measure, capable of capturing the relative connectedness of data points/clusters in a complicated manifold, and could be a better (dis)similarity metric, than the simple Euclidean distance, to identify anomalies in unsupervised learning settings. The proposed method is compared with 13 popular anomaly detection methods on 20 benchmark data sets, demonstrating a considerable improvement in its ability of identifying anomalies. Furthermore, the MST-based anomaly detection is applied to the data set from a hydropower turbine and demonstrates remarkable detection competence.
1 December 2017 in Renewable Energy
GPGeorgios Pechlivanoglou
17 March 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well.
2 November 2022 in Frontiers in Energy Research
Quantifying a wind turbine’s holistic, system-level power production efficiency in its commercial operating condition is one of the keys to reducing the levelized cost for energy of wind energy and thus contributing significantly to the Sustainable Development Goal 7.2: “By 2030, increase substantially the share of renewable energy in the global energy mix.” It is so important because designers and operators need an effective baseline quantification in order to be able to identify best practices or make operation and maintenance decisions that produce actual improvements. However, this task is highly challenging due to the stochastic nature of the wind and the complexity of wind turbine systems. It is imperative to carry out accurate, trust-worthy performance assessment and uncertainty quantification of wind turbine generators. This article provides a concise overview of the existing schools of thought in terms of wind turbine performance assessment and highlights a few important technical considerations for future research pursuit.
28 January 2020 in Structural Health Monitoring
The electromechanical coupling property of piezoelectric transducers gives rise to a promising class of structural fault diagnosis methods often referred to collectively as impedance-based approaches. One active line of research in the related literature is the development of data-driven methods that can leverage the available experimental impedance measurements to accurately pinpoint the location and severity of structural faults. In this article, we offer a new perspective to the problem by casting the impedance-based fault diagnosis into a statistical calibration formulation, which has gained a wide popularity in the industrial statistics community in the past two decades. Specifically, we decide to estimate the values of the fault attributes (e.g. location and severity) that achieve the closest match between the outputs from a finite element model and those experimentally solicited from the host structure. We further propose to couple this statistical formulation with a pre-screening procedure to reduce the calibration search space and mitigate parameter identifiability issues. In addition to the merit of capably diagnosing structural faults, the proposed approach extends various useful concepts from the statistical calibration literature to the structural health monitoring applications, such as the construction of surrogate models for modeling and predicting impedance changes, the explicit use of a bias function to correct for inherent inadequacies in finite element models, as well as the ability to produce continuous probability distributions for quantifying a fault’s severity. These additional benefits substantially enhance both the fault diagnosis capability and computational efficiency. We demonstrate the effectiveness of the proposed approach using two simulated and two experimental case studies from the literature.