In this paper, a fuzzy-logic-based fault detection system is designed for a medical Internet of Nano Things architecture. The goal of this system is to detect the root cause and severity of the faults occurred in the in-body nanonetwork. Since nanomachines have very limited capabilities, the sampled data from the in-body nanonetwork is sent to cloud servers by means of an on-body micro-gateway. The fuzzy fault detection system was designed based on two well-known methods including Mamdani and Takagi–Sugeno–Kang (TSK) fuzzy systems. The performance of the proposed approach is evaluated on a theoretical model of medical in-body nanonetwork from the literature through in silico study. This nanonetwork includes eleven types of nanomachines which cooperate with each other within the arterial wall and interact with low-density lipoprotein (LDL), drug and signaling molecules in order to prevent the formation and development of Atherosclerosis plaques. Any fault in these nanomachines can highly take negative effect on treatment efficiency. The results of computer simulation and comparative study on 37 atherosclerosis patients demonstrate how the proposed approach could successfully detect the root cause and severity of the faults occurred in the nanonetwork.

在本文中，为医疗纳米物联网架构设计了一个基于模糊逻辑的故障检测系统。该系统的目标是检测体内纳米网络中发生的故障的根本原因和严重程度。由于纳米机器的能力非常有限，来自体内纳米网络的采样数据通过体内微网关发送到云服务器。模糊故障检测系统是基于两种众所周知的方法设计的，包括 Mamdani 和 Takagi-Sugeno-Kang (TSK) 模糊系统。所提出的方法的性能在从文献到计算机研究的医学体内纳米网络的理论模型上进行了评估。该纳米网络包括 11 种类型的纳米机器，它们在动脉壁内相互协作并与低密度脂蛋白 (LDL) 相互作用，药物和信号分子，以防止动脉粥样硬化斑块的形成和发展。这些纳米机器中的任何故障都会对处理效率产生很大的负面影响。对 37 名动脉粥样硬化患者进行计算机模拟和比较研究的结果证明了所提出的方法如何成功地检测出纳米网络中发生的故障的根本原因和严重程度。