# Machine Learning based Laser Failure Mode Detection

arXiv: https://arxiv.org/abs/2203.11729 · HTML: https://mlsanity.com/paper/2203.11729/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 13 references that are in the map.
- First posted on arXiv 19 Mar 2022.

## Built on by (most cited first, 1 of 1)

- [A Machine Learning-based Framework for Predictive Maintenance of Semiconductor Laser for Optical Communication](https://mlsanity.com/paper/2211.02842/) (2022)

## Abstract (arXiv)

Laser degradation analysis is a crucial process for the enhancement of laser reliability. Here, we propose a data-driven fault detection approach based on Long Short-Term Memory (LSTM) recurrent neural networks to detect the different laser degradation modes based on synthetic historical failure data. In comparison to typical threshold-based systems, attaining 24.41% classification accuracy, the LSTM-based model achieves 95.52% accuracy, and also outperforms classical machine learning (ML) models namely Random Forest (RF), K-Nearest Neighbours (KNN) and Logistic Regression (LR).