Intelligent ice detection on wind turbine blades using semantic segmentation and class activation map approaches based on deep learning method

2022 ◽  
Vol 182 ◽  
pp. 1-16
Author(s):  
Kemal Hacıefendioğlu ◽  
Hasan Basri Başağa ◽  
Zafer Yavuz ◽  
Mohammad Tordi Karimi
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Turbine Blades ◽  
Semantic Segmentation ◽  
Learning Method ◽  
Wind Turbine Blades ◽  
Ice Detection ◽  
Activation Map

A review of integrating ice detection and mitigation for wind turbine blades

2019 ◽  
Vol 103 ◽  
pp. 269-281 ◽  
Author(s):  
Ezieddin Madi ◽  
Kevin Pope ◽  
Weimin Huang ◽  
Tariq Iqbal
Keyword(s):  
Wind Turbine ◽  
Turbine Blades ◽  
Wind Turbine Blades ◽  
Ice Detection

Metamodel-Assisted Ice Detection for Wind Turbine Blades

2011 ◽  
Author(s):  
Veruska Malave´ ◽  
Cameron J. Turner
Keyword(s):  
Wind Turbine ◽  
Health Management ◽  
Turbine Blades ◽  
Weather Conditions ◽  
Position Angle ◽  
Design Tool ◽  
Detection Technique ◽  
Wind Turbine Blades ◽  
Pitch Moment ◽  
Ice Detection

Icing is a complex atmospheric phenomenon that causes airflow disruption and degrades aerodynamically the original performance of the wind turbine blades (WTBs). This is due to blade sensitivity to minor changes in the airfoil geometry. Aerodynamic distortions induced by ice decrease the lift-to-draft ratio and pitch moment, increase the airfoil weight, and adversely alter the effectiveness of position angle and velocity. Typically, wind turbines exposed to all-weather conditions are equipped with icing prevention systems (IPS). However at the present time, no ice-detection technique has been proven effective, and the implementation of new strategies that effectively detect and mitigate blade icing adverse effects are needed. In this work, a WTB ice-detection technique that consists of a numerical design tool using Matlab/Simulink models and non-uniform rational B-spline (NURBs) based metamodeling algorithms is examined. This is carried out in terms of the blade icing effects on turbine aerodynamic performance in accordance to condition-based maintenance (CBM) and prognostics health management (PHM) techniques.

scholarly journals Risk Assessment and Value of Action Analysis for Icing Conditions of Wind Turbines Close to Highways

Energies ◽  
2019 ◽  
Vol 12 (14) ◽  
pp. 2653 ◽  
Author(s):  
Rastayesh ◽  
Long ◽  
Sørensen ◽  
Thöns
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Urban Areas ◽  
Detection System ◽  
Turbine Blades ◽  
Heating System ◽  
Economic Losses ◽  
Wind Turbine Blades ◽  
Heating Systems ◽  
Ice Detection

The paper presents research results from the Marie Skłodowska-Curie Innovative Training Network INFRASTAR in the field of reliability approaches for decision-making for wind turbines and bridges. This paper addresses the application of Bayesian decision analysis for installation of heating systems in wind turbine blades in cases where an ice detection system is already installed in order to allow wind turbines to be placed close to highways. Generally, application of ice detection and heating systems for wind turbines is very relevant in cases where the wind turbines are planned to be placed close to urban areas and highways, where risks need to be considered due to icing events, which may lead to consequences including human fatality, functional disruptions, and/or economic losses. The risk of people being killed in a car passing on highways near a wind turbine due to blades parts or ice pieces being thrown away in cases of over-icing is considered in this paper. The probability of being killed per kilometer and per year is considered for three cases: blade parts thrown away as a result of a partial or total failure of a blade, ice thrown away in two cases, i.e., of stopped wind turbines and of wind turbines in operation. Risks due to blade parts being thrown away cannot be avoided, since low strengths of material, maintenance or manufacturing errors, mechanical or electrical failures may result in failure of a blade or blade part. The blade (parts) thrown away from wind turbines in operation imply possible consequences/fatalities for people near the wind turbines, including in areas close to highways. Similar consequences are relevant for ice being thrown away from wind turbine blades during icing situations. In this paper, we examine the question as to whether it is valuable to put a heating system on the blades in addition to ice detection systems. This is especially interesting in countries with limited space for placing wind turbines; in addition, it is considered if higher power production can be obtained due to less downtime if a heating system is installed.

A novel method to predict the stiffness evolution of in-service wind turbine blades based on deep learning models

2020 ◽  
Vol 252 ◽  
pp. 112702
Author(s):  
Hongwei Liu ◽  
Zhichun Zhang ◽  
Hongbo Jia ◽  
Quanlong Li ◽  
Yanju Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Turbine Blades ◽  
Learning Models ◽  
Wind Turbine Blades ◽  
Novel Method

Automatic image detection of multi-type surface defects on wind turbine blades based on cascade deep learning network

2021 ◽  
Vol 25 (2) ◽  
pp. 463-482
Author(s):  
Yulin Mao ◽  
Shuangxin Wang ◽  
Dingli Yu ◽  
Juchao Zhao
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Defect Detection ◽  
Surface Defects ◽  
Oil Pollution ◽  
Turbine Blades ◽  
Critical Factor ◽  
Wind Turbine Blades ◽  
Surface Defect Detection ◽  
Deep Learning Network

A safe operation protocol of the wind blades is a critical factor to ensure the stability of a wind turbine. Sensors are most commonly applied for defect detection on wind turbine blades (WTBs). However, due to the high cost and the sensitivity to stochastic noise, computer vision-guided automatic detection remains a challenge for surface defect detection on WTBs in particularly, its accuracy in locating defects is yet to be optimized. In this paper, we developed a visual inspection model that can automatically and precisely classify and locate the surface defects, through the utilization of a deep learning framework based on the Cascade R-CNN. In order to obtain high mean average precision (mAP) according to the characteristics of the dataset, a model named Contextual Aligned-Deformable Cascade R-CNN (CAD Cascade R-CNN) using improved strategies of transfer learning, Deformable Convolution and Deformable RoI Align, as well as context information fusion is proposed and a dataset with surface defects categorized and labeled as crack, breakage and oil pollution is generated. Moreover to alleviate the problem of false detection under a complex background, an improved bisecting k-means is presented during the test process. The adaptability and generalization of the proposed CAD Cascade R-CNN model were validated by each type of defects in dataset and different IoU thresholds, whereas, each of the above improved strategies was verified by gradual ablation experiments. Finally experiments that compared with the baseline Cascade R-CNN, Faster R-CNN and YOLO-v3 demonstrate its superiority over these existing approaches with a maximum of 92.1% mAP.

Guided wave–based approach for ice detection on wind turbine blades

2018 ◽  
Vol 42 (5) ◽  
pp. 483-495 ◽  
Author(s):  
Siavash Shoja ◽  
Viktor Berbyuk ◽  
Anders Boström
Keyword(s):  
Experimental Data ◽  
Wind Turbine ◽  
Composite Structures ◽  
Detection System ◽  
Turbine Blades ◽  
Guided Wave ◽  
Cold Climate ◽  
Wind Turbine Blades ◽  
Time Frequency ◽  
Ice Detection

An efficient ice detection system is an important tool to optimize the de-icing processes in wind turbines operating in cold climate regions. The aim of this work is to study the application of guided wave for ice detection on wind turbine blades. Computational model is developed to simulate guided wave propagation on composite structures. The model has been validated with experimental data obtained in cold climate laboratory. Effect of ice accretion on composite structures is studied in the time, frequency and wavenumber domains. In each case, post-processing algorithms as well as icing index are introduced which are sensitive to accumulated ice on the composite structure. The algorithms and icing index are applied to both simulation results and experimental data. Analysis of the obtained results has shown that the guided wave–based approach can be used for developing ice detection systems for wind turbine blades.

Sign in / Sign up

Export Citation Format

Share Document