# Predictive Failure Detection in Network Hardware Using Thermal Imaging and Deep Learning with Sensor Fusion

arXiv: https://arxiv.org/abs/2608.07582 · HTML: https://mlsanity.com/paper/2608.07582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 21 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 3 of 3)

- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Thermal Image-based Fault Diagnosis in Induction Machines via Self-Organized Operational Neural Networks](https://mlsanity.com/paper/2412.05901/) (2024)
- [CNN-LSTM Hybrid Deep Learning Model for Remaining Useful Life Estimation](https://mlsanity.com/paper/2412.15998/) (2024)

## Abstract (arXiv)

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.