用30分钟正常数据训练，即可在边缘设备上快速检测液体传感器异常。
Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge
- 基于注意力机制的一类自编码器，仅需30分钟正常数据即可训练
- 在合成微异常上达到F1 0.72、精度0.89、召回0.61
- 模型仅31 kB，可在无AVX指令的边缘设备上低延迟运行
提出一种轻量级、可部署于边缘的传感器异常检测流程，用于化学与生物实验室。定制PCB采集七路传感器信号并通过本地网络传输。基于注意力的一类自编码器在仅30分钟正常数据训练后即达可用状态。尽管数据量小，测试中对合成微异常仍实现F1分数0.72、精确率0.89、召回率0.61。训练后的模型被转换为约31 kB的TensorFlow-Lite二进制文件，可在无AVX指令的安迪泰克ARK-1221L（x86边缘设备）上运行，端到端推理延迟低于两秒。从数据采集到部署的全流程在一小时内完成，表明该系统在引入新液体或传感器时可快速适应。
原文摘要 · Abstract (English)
A lightweight, edge-deployable pipeline is proposed for detecting sensor anomalies in chemistry and biology laboratories. A custom PCB captures seven sensor channels and streams them over the local network. An Attention-based One-Class Autoencoder reaches a usable state after training on only thirty minutes of normal data. Despite the small data set, the model already attains an F1 score of 0.72, a precision of 0.89, and a recall of 0.61 when tested on synthetic micro-anomalies. The trained network is converted into a TensorFlow-Lite binary of about 31 kB and runs on an Advantech ARK-1221L, a fan-less x86 edge device without AVX instructions; end-to-end inference latency stays below two seconds. The entire collect-train-deploy workflow finishes within one hour, which demonstrates that the pipeline adapts quickly whenever a new liquid or sensor is introduced.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。