Next Article in Journal
Resource-Aware Device Allocation of Data-Parallel Applications on Heterogeneous Systems
Next Article in Special Issue
Automatic Detection of Discrimination Actions from Social Images
Previous Article in Journal
Broadband Transition from Rectangular Waveguide to Groove Gap Waveguide for mm-Wave Contactless Connections
Previous Article in Special Issue
Underwater-Sonar-Image-Based 3D Point Cloud Reconstruction for High Data Utilization and Object Classification Using a Neural Network
Open AccessArticle

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

1
Faculty of Mathematics and Computer Science, University of Bremen, Cognitive Neuroinformatics, Enrique-Schmidt-Strasse 5, 28359 Bremen, Germany
2
BIBA-Bremer Institut für Produktion und Logistik GmbH, Hochschulring 20, 28359 Bremen, Germany
3
Faculty of Production Engineering, University of Bremen, Badgasteiner Strasse 1, 28359 Bremen, Germany
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(11), 1824; https://doi.org/10.3390/electronics9111824
Received: 8 September 2020 / Revised: 23 October 2020 / Accepted: 28 October 2020 / Published: 2 November 2020
(This article belongs to the Special Issue Application of Neural Networks in Image Classification)
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. View Full-Text
Keywords: quantized neural networks; defect detection; field-programmable gate array; quality inspection; parameter quantization quantized neural networks; defect detection; field-programmable gate array; quality inspection; parameter quantization
Show Figures

Figure 1

MDPI and ACS Style

Giefer, L.A.; Staar, B.; Freitag, M. FPGA-Based Optical Surface Inspection of Wind Turbine Rotor Blades Using Quantized Neural Networks. Electronics 2020, 9, 1824. https://doi.org/10.3390/electronics9111824

AMA Style

Giefer LA, Staar B, Freitag M. FPGA-Based Optical Surface Inspection of Wind Turbine Rotor Blades Using Quantized Neural Networks. Electronics. 2020; 9(11):1824. https://doi.org/10.3390/electronics9111824

Chicago/Turabian Style

Giefer, Lino A.; Staar, Benjamin; Freitag, Michael. 2020. "FPGA-Based Optical Surface Inspection of Wind Turbine Rotor Blades Using Quantized Neural Networks" Electronics 9, no. 11: 1824. https://doi.org/10.3390/electronics9111824

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop