Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization (2403.01922v2)

Published 4 Mar 2024 in cs.LG and physics.flu-dyn

Abstract: In industrial and environmental monitoring, achieving real-time and precise fluid flow measurement remains a critical challenge. This study applies linear quantization in FPGA-based soft sensors for fluid flow estimation, significantly enhancing Neural Network model precision by overcoming the limitations of traditional fixed-point quantization. Our approach achieves up to a 10.10% reduction in Mean Squared Error and a notable 9.39% improvement in inference speed through targeted hardware optimizations. Validated across multiple data sets, our findings demonstrate that the optimized FPGA-based quantized models can provide efficient, accurate real-time inference, offering a viable alternative to cloud-based processing in pervasive autonomous systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (11)
  1. C. Qian, T. Ling, and G. Schiele, “Elasticai: Creating and deploying energy-efficient deep learning accelerator for pervasive computing,” in 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops).   IEEE, 2023, pp. 297–299.
  2. J. Tomperi, P. M. Rossi, and M. Ruusunen, “Estimation of wastewater flowrate in a gravitational sewer line based on a low-cost distance sensor,” Water Practice & Technology, p. wpt2022171, 2022.
  3. P. Yin, J. Lyu, S. Zhang, S. Osher, Y. Qi, and J. Xin, “Understanding straight-through estimator in training activation quantized neural nets,” arXiv preprint arXiv:1903.05662, 2019.
  4. N. Noori, T. Waag, H. Viumdal, R. Sharma, M. Jondahl, and A. Jinasena, “Non-newtonian fluid flow measurement in open venturi channel using shallow neural network time series and non-contact level measurement radar sensors,” in SPE Norway Subsurface Conference.   OnePetro, 2020.
  5. B. Jacob, S. Kligys, B. Chen, M. Zhu, M. Tang, A. Howard, H. Adam, and D. Kalenichenko, “Quantization and training of neural networks for efficient integer-arithmetic-only inference,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018.
  6. T. Ling, C. Qian, and G. Schiele, “On-device soft sensors: Real-time fluid flow estimation from level sensor data,” 2023.
  7. H. Liang, C. Song, Z. Li, and H. Yang, “Volume flow rate calculation model of non-full pipe multiphase flow based on ultrasonic sensors,” Physics of Fluids, vol. 35, no. 3, 2023.
  8. K. Chhantyal, H. Viumdal, S. Mylvaganam, and G. Elseth, “Ultrasonic level sensors for flowmetering of non-newtonian fluids in open venturi channels: Using data fusion based on artificial neural network and support vector machines,” in 2016 IEEE Sensors Applications Symposium (SAS).   IEEE, 2016, pp. 1–6.
  9. R. Krishnamoorthi, “Quantizing deep convolutional networks for efficient inference: A whitepaper,” arXiv preprint arXiv:1806.08342, 2018.
  10. A. Pappalardo. (2023) Xilinx/brevitas. [Online]. Available: https://doi.org/10.5281/zenodo.3333552
  11. S. Jain, A. Gural, M. Wu, and C. Dick, “Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks,” Proceedings of Machine Learning and Systems, pp. 112–128, 2020.
Citations (4)

Summary

We haven't generated a summary for this paper yet.