FPGA Accelerated Deep Learning for Industrial and Engineering Applications: Optimal Design Under Resource Constraints

被引:0
|
作者
Liu, Yanyi [1 ]
Du, Hang [1 ]
Wu, Yin [1 ]
Mo, Tianli [1 ]
机构
[1] Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Peoples R China
来源
ELECTRONICS | 2025年 / 14卷 / 04期
关键词
object detection; YOLOv4-Tiny; refined resource management strategy; predefined interface latency; dynamic bit width tuning quantization;
D O I
10.3390/electronics14040703
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In response to the need for deploying the YOLOv4-Tiny model on resource-constrained Field-Programmable Gate Array (FPGA) platforms for rapid inference, this study proposes a general optimization acceleration strategy and method aimed at achieving fast inference for object detection networks. This approach centers on the synergistic effect of several key strategies: a refined resource management strategy that dynamically adjusts FPGA hardware resource allocation based on the network architecture; a dynamic dual-buffering strategy that maximizes the parallelism of data computation and transmission; an interface access latency pre-configuration strategy that effectively improves data throughput; and quantization operations for dynamic bit width tuning of model parameters and cached variables. Experimental results on the ZYNQ7020 platform demonstrate that this accelerator operates at a frequency of 200 MHz, achieving an average computing performance of 36.97 Giga Operations Per Second (GOPS) with an energy efficiency of 8.82 Giga Operations Per Second per Watt (GOPS/W). Testing with a metal surface defect dataset maintains an accuracy of approximately 90% per image, while reducing the inference delay per frame to 185 ms, representing a 52.2% improvement in inference speed. Compared to other FPGA accelerator designs, the accelerator design strategies and methods proposed in this study showcase significant enhancements in average computing performance, energy efficiency, and inference latency.
引用
收藏
页数:22
相关论文
共 50 条
  • [41] Deep Reinforcement Learning-Based Computation Offloading and Optimal Resource Allocation in Industrial Internet of Things with NOMA
    Gao, Haofeng
    Guo, Xing
    2022 11TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS (ICCCAS 2022), 2022, : 198 - 203
  • [42] Optimal control design under structural and communication constraints
    Voulgaris, PG
    MULTIDISCIPLINARY RESEARCH IN CONTROL, 2003, 289 : 47 - 61
  • [44] Optimal Design of Dilution Experiments Under Volume Constraints
    Maryam Zolghadr
    Sergei Zuyev
    Journal of Agricultural, Biological and Environmental Statistics, 2016, 21 : 663 - 683
  • [45] Optimal Design of Dilution Experiments Under Volume Constraints
    Zolghadr, Maryam
    Zuyev, Sergei
    JOURNAL OF AGRICULTURAL BIOLOGICAL AND ENVIRONMENTAL STATISTICS, 2016, 21 (04) : 663 - 683
  • [46] Optimal Design of the Bearingless Induction Motor for Industrial Applications
    Chen, Jiahao
    Severson, Eric L.
    2019 IEEE ENERGY CONVERSION CONGRESS AND EXPOSITION (ECCE), 2019, : 5265 - 5272
  • [47] Optimal deep learning based image compression technique for data transmission on industrial Internet of things applications
    Sujitha, Ben
    Parvathy, Velmurugan Subbiah
    Lydia, E. Laxmi
    Rani, Poonam
    Polkowski, Zdzislaw
    Shankar, K.
    TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES, 2021, 32 (07):
  • [48] Optimal deep learning based image compression technique for data transmission on industrial Internet of things applications
    Sujitha, Ben
    Parvathy, Velmurugan Subbiah
    Lydia, E. Laxmi
    Rani, Poonam
    Polkowski, Zdzislaw
    Shankar, K.
    Transactions on Emerging Telecommunications Technologies, 2021, 32 (07)
  • [49] Optimal production and inventory policy for multiple products under resource constraints
    DeCroix, GA
    Arreola-Risa, A
    MANAGEMENT SCIENCE, 1998, 44 (07) : 950 - 961
  • [50] An Optimal Method of Task Balancing for Aircraft Subassembly under Resource Constraints
    Yan, Zhenguo
    Li, Yuan
    Zhang, Jie
    Zhou, Xiaobo
    MATERIALS PROCESSING TECHNOLOGIES, PTS 1 AND 2, 2011, 154-155 : 1530 - 1537