采用设置和不设置镉中子吸收体两种方式, 利用中国散裂中子源9号束线(CSNS-BL09)对65 nm微控制器进行了大气中子单粒子效应辐照测试. 测试中探测到的效应主要为单位翻转. 测试结果表明, 对于该款微控制器, 热中子引起的中子单粒子翻转占比约65%; 进一步分析表明, 热中子与¹⁰B反应产生的0.84 MeV ⁷Li可能是诱发微控制器单粒子翻转的主要因素.

Stray neutrons might cause several negative impacts. However, it is usually difficult to conduct precise stray neutron simulations using the Monte Carlo method. Therefore, in this study, a measurement technique was proposed to study the stray neutrons experimentally inside the neutron scattering instruments at China Spallation Neutron Source (CSNS). The adopted measurement instruments comprise an extended-range Bonner sphere spectrometer and a commercial neutron ambient-dose-equivalent dosimeter, which enables us to directly measure the neutron spectra and ambient-dose equivalent H*(10) values. Verification experiments were performed inside the BL06 beam line experimental area at CSNS at two exposed locations with different sample conditions. Comparison of the experimentally measured neutron spectra, integral neutron fluence, and H*(10) value with the simulations demonstrated the feasibility of using the proposed method for studying stray neutrons for the neutron instruments.

This research investigates atmospheric neutron-induced single event effects (SEEs) on advanced artificial intelligence (AI) chips during natural environment operation. The RK3588 neural processing unit (NPU) is the evaluated target chip, and its SEE is assessed through a combination of irradiation testing and software fault injection. During the irradiation test, the chip was exposed to a spectrum neutron at the China Spallation Neutron Source. Upon reaching a cumulative fluence of 8.25 × 10⁹ n·cm², a total of 14,018 soft errors were detected, of which 99.97% manifested as variations in target recognition accuracy and network inference latency. Among these variations, both detrimental effects (reduced target recognition accuracy or prolonged network inference time) and beneficial effects (enhanced target recognition accuracy or shortened network inference time) caused by single event effects were observed. In addition, atmospheric neutron single event effects were found to cause NPU operation suspension and system crashes. Based on the irradiation test results, failure predictions for neural processing units in real-world environments were estimated, and mitigation recommendations were proposed. Furthermore, software fault injections were employed to conduct in-depth analysis of detected soft errors during irradiation testing. This research provides support and references for the reliable application of artificial intelligence chips in natural environments.