# Optimizing Predictive Maintenance in Intelligent Manufacturing: An Integrated FNO-DAE-GNN-PPO MDP Framework

arXiv: https://arxiv.org/abs/2511.05594 · HTML: https://mlsanity.com/paper/2511.05594/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 60 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Graph Neural Networks: Taxonomy, Advances and Trends](https://mlsanity.com/paper/2012.08752/) (2020)
- [A neural operator-based surrogate solver for free-form electromagnetic inverse design](https://mlsanity.com/paper/2302.01934/) (2023)
- [Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes](https://mlsanity.com/paper/1912.10325/) (2019)
- [A Note on Optimization Formulations of Markov Decision Processes](https://mlsanity.com/paper/2012.09417/) (2020)
- [Noise Learning Based Denoising Autoencoder](https://mlsanity.com/paper/2101.07937/) (2021)
- [Energy Efficient Computation Offloading in Aerial Edge Networks With Multi-Agent Cooperation](https://mlsanity.com/paper/2302.09021/) (2023)
- [FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis](https://mlsanity.com/paper/2108.12373/) (2021)
- [Data-driven design of fault diagnosis for three-phase PWM rectifier using random forests technique with transient synthetic features](https://mlsanity.com/paper/2211.02631/) (2022)
- [On Minimizing Total Discounted Cost in MDPs Subject to Reachability Constraints](https://mlsanity.com/paper/2103.09295/) (2021)
- [A useful technique for piecewise deterministic Markov decision processes](https://mlsanity.com/paper/2006.06827/) (2020)
- [Risk-sensitive discounted cost criterion for Continuous-time Markov decision processes on a general state space](https://mlsanity.com/paper/2104.12366/) (2021)
- [Gradual-impulsive control for continuous-time Markov decision processes with total undiscounted costs and constraints: linear programming approach via a reduction method](https://mlsanity.com/paper/2112.02674/) (2021)
- [Reversible Markov decision processes and the Gaussian free field](https://mlsanity.com/paper/2207.05217/) (2022)

## Abstract (arXiv)

In the era of smart manufacturing, predictive maintenance (PdM) plays a pivotal role in improving equipment reliability and reducing operating costs. In this paper, we propose a novel Markov Decision Process (MDP) framework that integrates advanced soft computing techniques - Fourier Neural Operator (FNO), Denoising Autoencoder (DAE), Graph Neural Network (GNN), and Proximal Policy Optimisation (PPO) - to address the multidimensional challenges of predictive maintenance in complex manufacturing systems. Specifically, the proposed framework innovatively combines the powerful frequency-domain representation capability of FNOs to capture high-dimensional temporal patterns; DAEs to achieve robust, noise-resistant latent state embedding from complex non-Gaussian sensor data; and GNNs to accurately represent inter-device dependencies for coordinated system-wide maintenance decisions. Furthermore, by exploiting PPO, the framework ensures stable and efficient optimisation of long-term maintenance strategies to effectively handle uncertainty and non-stationary dynamics. Experimental validation demonstrates that the approach significantly outperforms multiple deep learning baseline models with up to 13% cost reduction, as well as strong convergence and inter-module synergy. The framework has considerable industrial potential to effectively reduce downtime and operating expenses through data-driven strategies.