Field rapid detection method of wind turbine blade fixing bolt defects based on FPGA

Abstract

In order to solve the problem that blade fixing bolt cannot be detected quickly and conveniently in the field in actual production, this paper proposed a field rapid detection method of wind turbine blade fixing bolt defects based on field programmable gate array (FPGA), and Yolov4-tiny is selected as the basic algorithm. Nonetheless, the original Yolov4-tiny was not suitable for detecting small defects, so this paper improved the Yolov4-tiny to enhance the detection effect. Next, the convolutional operations in the algorithm were encapsulated into intellectual property (IP) cores by high-level synthesis (HLS) and Vivado, and parallel computation was realized using FPGA features. In the end, using Python to call the IP core and the FPGA hardware library, this paper achieved the purpose of rapid detection. Compared with traditional detection methods and other algorithms, the accuracy and speed of this method are significantly improved, which has a good application value.

References

[1] YuG A, QinZ W, RongX M, et al.. Research on the influence of defects on the performance of bolted connections of wind turbine blades[J]. Acta Energiae Solaris Sinica, 2019, 40(11):3244-3249(in Chinese)

[2] TaoX, HouW, XuD, et al.. A review of surface defect detection methods based on deep learning[J]. Acta Automatica Sinica, 2021, 47(05):877-879(in Chinese)

[3] YuW Y, ZhangY, YaoH M, et al.. Visual inspection of surface defects based on lightweight reconstruction network[J]. Acta Automatica Sinica, 2020, 41(16):1-12(in Chinese)

[4] ChenC, ChaiZ L, XiaJ. Design and implementation of YOLOv2 accelerator based on Zynq 7000 FPGA heterogeneous platform[J]. Journal of frontiers of computer science & technology, 2019, 13(10):1677-1693(in Chinese)

[5] AdionoT, PutraA, SutisnaA, et al.. Low latency YOLOv3-tiny accelerator for low-cost FPGA using general matrix multiplication principle[J]. IEEE access, 2021, 9(08):141890-141913

[6] ZhuJ, WangJ L, WangB. Lightweight mask detection algorithm based on improved YOLOv4-tiny[J]. Chinese journal of liquid crystals and displays, 2021, 36(11):1525-1534 in Chinese)

[7] LiF D, GaoD Y, YangY Q. Small target deep convolution recognition algorithm based on improved YOLOv4[J]. International journal of machine learning and cybernetics, 2022, 3(12):982-990

[8] AdibhatlaA, ChihH, HsuC, et al.. Defect detection in printed circuit boards using you-only-look-once convolutional neural networks[J]. Electronics, 2020, 9(09):1547-1563

[9] AddieI B, TofaelA. Real time pear fruit detection and counting using YOLOv4 models and deep SORT[J]. Sensors, 2021, 21(14):4803-4811

[10] MándiÁ, MátéJ, RózsaD, et al.. Hardware accelerated image processing on FPGA based PYNQ-Z2 board[J]. Carpathian journal of electronic and computer engineering, 2021, 14(01):20-23

[11] BjergeK, SchougaardJ H, LarsenD E. A scalable and efficient convolutional neural network accelerator using HLS for a system-on-chip design[J]. Microprocessors and microsystems, 2021, 87(03):198-206

[12] HuynhT V. FPGA-based acceleration for convolutional neural networks on PYNQ-Z2[J]. International journal of computing and digital systems, 2022, 11(01):441-450

[13] MengT, TaoY, ChenZ Q. Depth evaluation for metal surface defects by eddy current testing using deep residual convolutional neural networks[J]. IEEE transactions on instrumentation and measurement, 2021, 70(02):1862-1871

[14] BouguezziS, BenF H, BelabedT, et al.. An efficient FPGA-based convolutional neural network for classification: Ad-MobileNet[J]. Electronics, 2021, 10(18):2272-2283

[15] RenZ H, FangF Z, YanN, et al.. State of the art in defect detection based on machine vision[J]. International journal of precision engineering and manufacturing-green technology, 2021, 2(06):1-31

[16] LiuJ, GeY F. Reconfigurable convolutional neural network accelerator based on ZYNQ[J]. Chinese journal of electronics, 2021, 49(04):729-735