On-site inspection of potential defects in wind turbine rotor blades with thermography

Wind Energy ◽  
2015 ◽  
Vol 19 (8) ◽  
pp. 1407-1422 ◽  
Author(s):  
Manoucher Doroshtnasir ◽  
Tamara Worzewski ◽  
Rainer Krankenhagen ◽  
Mathias Röllig
Keyword(s):  
Wind Turbine ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
On Site Inspection ◽  
Wind Turbine Rotor

Harmonization of new wind turbine rotor blades development process: A review

2014 ◽  
Vol 39 ◽  
pp. 874-882 ◽  
Author(s):  
B. Rašuo ◽  
M. Dinulović ◽  
A. Veg ◽  
A. Grbović ◽  
A. Bengin
Keyword(s):  
Wind Turbine ◽  
Development Process ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
Wind Turbine Rotor

Monitoring system of wind turbine rotor blades

2009 ◽  
Author(s):  
B. Frankenstein ◽  
L. Schubert ◽  
N. Meyendorf ◽  
H. Friedmann ◽  
C. Ebert
Keyword(s):  
Wind Turbine ◽  
Monitoring System ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
Wind Turbine Rotor

Powder binders used for the manufacturing of wind turbine rotor blades. Part 1. Characterization of resin-binder interaction and preform properties

2016 ◽  
Vol 39 (3) ◽  
pp. 708-717 ◽  
Author(s):  
Stefan Schmidt ◽  
Thorsten Mahrholz ◽  
Alexandra Kühn ◽  
Peter Wierach
Keyword(s):  
Wind Turbine ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
Resin Binder ◽  
Wind Turbine Rotor

Design of a fibrous composite preform for wind turbine rotor blades

2014 ◽  
Vol 56 ◽  
pp. 635-641 ◽  
Author(s):  
J. Zangenberg ◽  
P. Brøndsted ◽  
M. Koefoed
Keyword(s):  
Wind Turbine ◽  
Fibrous Composite ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
Wind Turbine Rotor

scholarly journals FPGA-Based Optical Surface Inspection of Wind Turbine Rotor Blades Using Quantized Neural Networks

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1824 ◽  
Author(s):  
Lino Antoni Giefer ◽  
Benjamin Staar ◽  
Michael Freitag
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Wind Turbine ◽  
Defect Detection ◽  
Detection System ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
Surface Inspection ◽  
Wind Turbine Rotor

Quantization of the weights and activations of a neural network is a way to drastically reduce necessary memory accesses and to replace arithmetic operations with bit-wise operations. This is especially beneficial for the implementation on field-programmable gate array (FPGA) technology that is particularly suitable for embedded systems due to its low power consumption. In this paper, we propose an in-situ defect detection system utilizing a quantized neural network implemented on an FPGA for an automated surface inspection of wind turbine rotor blades using unpiloted aerial vehicles (UAVs). Contrary to the usual approach of offline defect detection, our approach prevents major downtimes and hence expenses. To our best knowledge, our work is among the first to transfer neural networks with weight and activation quantization into a tangible application. We achieve promising results with our network trained on our dataset consisting of 8024 good and defected rotor blade patches. Compared to a conventional network using floating-point arithmetic, we show that the classification accuracy we achieve is only slightly reduced by approximately 0.6%. With this work, we present a basic system for in-situ defect detection with versatile usability.

Sign in / Sign up

Export Citation Format

Share Document