Design and Application of an Onboard Particle Identification Platform Based on Convolutional Neural Networks
Source abstract
Abstract
Space radiation particle detection plays a crucial role in scientific research and engineering practice, especially in particle species identification. Currently, commonly used in-orbit particle identification techniques include telescope methods, electrostatic analysis time of flight (ESA × TOF), time-of-flight energy (TOF × E), and pulse shape discrimination (PSD). However, these methods usually fail to utilize the full waveform information containing rich features, and their particle identification results may be affected by the random rise and fall of particle deposition and noise interference. In this study, a low-latency and lightweight onboard FPGA real-time particle identification platform based on full waveform information was developed utilizing the superior target classification, robustness, and generalization capabilities of convolutional neural networks (CNNs). The platform constructs diversified input datasets based on the physical features of waveforms and uses Optuna and Pytorch software architectures for model training. The hardware platform is responsible for the real-time inference of waveform data and the dynamic expansion of the dataset. The platform was utilized for deep learning training and the testing of the historical waveform data of neutron and gamma rays, and the inference time of a single waveform takes 4.9 microseconds, with an accuracy rate of over 97%. The classification expectation FOM (figure-of-merit) value of this CNN model is 133, which is better than the traditional pulse shape discrimination (PSD) algorithm’s FOM value of 0.8. The development of this platform not only improves the accuracy and efficiency of space particle discrimination but also provides an advanced tool for future space environment monitoring, which is of great value for engineering applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Nuclear Physics and Applications · Radiation Therapy and Dosimetry · Radiation Detection and Scintillator Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China
University of Chinese Academy of Sciences, Beijing 100049, China
Funding
National Natural Science Foundation of China
References (26)
Show source-provided references
1. Zhu, J. (2014). Research on Charged Particle Identification Methods Based on Pulse Shape Analysis. [Master’s Thesis, National University of Defense Technology].
2. Development of Charged Particle Identification Methods
3. Integrated ion and neutral particle analyzer for Chinese Mars mission
4. The brief introduction of particle identification
5. Particle identification using digital pulse shape discrimination in a nTD silicon detector with a 1 GHz sampling digitizer10.1016/j.nima.2018.03.052 ↗
6. Neutron measurement and inversion based on CLYC scintillator
7. Characterization of a Cs2LiYCl6: Ce3+ scintillator coupled with two silicon photomultiplier arrays of different sizes10.1016/j.nima.2019.162339 ↗
8. Considerations for Training an Artificial Neural Network for Particle Type Identification10.1109/TNS.2021.3103658 ↗
9. Ma, Y., Cao, Y., Vrudhula, S., and Seo, J.S. (2017, January 22–24). Optimizing Loop Operation and Dataflow in FPGA Acceleration of Deep Convolutional Neural Networks. Proceedings of the ACM/SIGDA International Symposium on Field-programmable Gate Arrays, Monterey, CA, USA.10.1145/3020078.3021736 ↗
10. Application of the pulse-shape technique to proton-alpha discrimination in Si-detector arrays10.1016/0168-9002(95)00488-2 ↗
11. Identification of light charged particles and heavy ions in silicon detectors by means of pulse-shape discrimination10.1109/23.506644 ↗
12. Particle identification in solid-state detectors by exploiting pulse shape information10.1016/0168-9002(92)90356-9 ↗
13. The pulse shape and the timing problem in solid state detectors—A review paper10.1109/TNS.1969.4325151 ↗
14. Zhu, J., Liu, G., Yang, J., and Zhang, L. (2014, January 13–15). Pulse Shape Analysis Comparison Research of Charged Particle Identification. Proceedings of the Seventeenth Annual National Conference on Nuclear Electronics and Nuclear Detection Technology, Shanghai, China.
15. A neural network classifier for electron identification on the DAMPE experiment10.1088/1748-0221/16/07/P07036 ↗
16. Real-time implementation of the neutron/gamma discrimination in an FPGA-based DAQ MTCA platform using a convolutional neural network10.1109/TNS.2021.3090670 ↗
17. Lu, J., Tuo, X., Yang, H., Luo, Y., Liu, H., Deng, C., and Wang, Q. (2022). Pulse-shape discrimination of SiPM array-coupled CLYC detector using convolutional neural network. Appl. Sci., 12.10.3390/app12052400 ↗
18. Khan, A., Hwang, H., and Kim, H.S. (2021). Synthetic Data Augmentation and Deep Learning for the Fault Diagnosis of Rotating Machines. Mathematics, 9.10.3390/math9182336 ↗
19. Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4–8). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.10.1145/3292500.3330701 ↗
20. Srinivas, P., and Katarya, R. (2022). hyOPTXg: OPTUNA hyper-parameter optimization framework for predicting cardiovascular disease using XGBoost. Biomed. Signal Process. Control, 73.10.1016/j.bspc.2021.103456 ↗
21. Shekhar, S., Bansode, A., and Salim, A. (2021, January 8–10). A Comparative study of Hyper-Parameter Optimization Tools. Proceedings of the 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), Brisbane, Australia.10.1109/CSDE53843.2021.9718485 ↗
22. Dai, D., Zhang, Y., Zhang, J., Hu, Z., Cai, Y., Sun, Q., and Zhang, Z. (2024). Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs. arXiv.
23. Goyal, R., Vanschoren, J., Van Acht, V., and Nijssen, S. (2021). Fixed-point quantization of convolutional neural networks for quantized inference on embedded platforms. arXiv.
24. A high-speed reusable quantized hardware accelerator design for CNN on constrained edge device10.1007/s10617-023-09274-8 ↗
25. Fast convolutional neural networks on FPGAs with hls4ml10.1088/2632-2153/ac0ea1 ↗
26. Liu, B., Zhou, Y., Feng, L., Fu, H., and Fu, P. (2022). Hybrid CNN-SVM Inference Accelerator on FPGA Using HLS. Electronics, 11.10.3390/electronics11142208 ↗