基于热成像与传感器融合深度学习的网络硬件预测性故障检测
Predictive Failure Detection in Network Hardware Using Thermal Imaging and Deep Learning with Sensor Fusion
浏览论文内容
中文总结 AI 辅助
该研究提出结合热成像与电源传感器数据的多模态深度学习模型，经ROI预处理后可实现网络硬件早期故障的高精度预测，为数据中心主动维护提供支撑。
中文摘要 AI 辅助
非计划内的网络硬件故障会中断服务，导致数据中心产生高昂的停机损失。本文提出一种基于深度学习的预测性维护策略，利用热成像与电源传感器数据，检测路由器、交换机和服务器等设备故障的早期迹象。研究人员生成了模拟数据集，包含标注后的热图像与电源读数，对应正常、预警、危急三种运行状态。评估了三种在ImageNet上预训练的卷积神经网络（CNN）模型：ResNet-50、InceptionV3和VGG16，以及融合视觉与传感器时间序列信息的多模态CNN-LSTM融合模型。实验在有无预处理流程的条件下开展，预处理流程包括感兴趣区域（ROI）提取与归一化。未进行预处理时，CNN仅达到中等精度（如ResNet-50为52%）；基于ROI的预处理则显著提升了性能，ResNet-50的精度达到91%。CNN-LSTM模型取得了94%的最高精度，精确率与召回率均接近95%，证明了多模态融合的有效性。结果验证了领域特定预处理与传感器融合可大幅提升早期故障预测能力，为通过非侵入式监测实现网络硬件的主动维护提供了潜在基础。
英文摘要
Unplanned network hardware malfunctions can interrupt services and result in expensive downtime in data centers. A deep learning-based predictive maintenance strategy is presented that utilizes thermal imaging and power sensor data to detect early indicators of equipment breakdown in routers, switches, and servers. A simulated dataset was generated comprising annotated thermal pictures and power readings indicative of three operating states: Normal, Warning, and Critical. Three ImageNet-pretrained convolutional neural network (CNN) models ResNet-50, InceptionV3, and VGG16 were assessed together with a multi-modal CNN-LSTM fusion model that integrates visual and sensor time-series information. Experiments were performed with and without pre-processing procedures, including region-of-interest (ROI) extraction and normalization. In the absence of pre-processing, CNNs attained moderate accuracy (e.g., ResNet-50 at 52%), but ROI-based pre-processing significantly enhanced performance (ResNet-50 accuracy reaching 91%). The CNN-LSTM model attained the greatest accuracy of 94%, with precision and recall approaching 95%, illustrating the effectiveness of multi-modal fusion. The results validate that domain-specific pre-processing and sensor fusion substantially improve early failure prediction, providing a potential foundation for proactive maintenance of network hardware through non-intrusive monitoring.
