In the aircraft engine Maintenance, Repair, and Overhaul (MRO) process, effective task planning relies heavily on the expertise of lead engineers. However, when predictive models are used to assist decision-making, issues with incomplete, unbalanced, and inconsistent data can lead to errors in the planning task. Therefore, reliable predictions are crucial for optimising the operational efficiency. This paper proposes a methodology to improve the prediction of maintenance times for an aircraft engine MRO process by integrating K-means clustering with Cosine and Jaccard similarity methods to define a reliable prediction interval. This methodology was compared with the predictions of the Simple Linear Regression method, which resulted in the prediction interval approach significantly reducing prediction errors, increasing prediction accuracy, while optimising process management and maintenance task planning throughout the MRO process.

Physics-Informed Neural Networks (PINNs) have emerged as a powerful frame- work for solving partial differential equations (PDEs). However, standard MLP- based PINNs often fail to converge when dealing with complex initial value problems, leading to solutions that violate causality and suffer from a spectral bias towards low-frequency components. To address these issues, we introduce NeuSA (Neuro-Spectral Architectures), a novel class of PINNs inspired by classi- cal spectral methods, designed to solve linear and nonlinear PDEs with variable coefficients. NeuSA learns a projection of the underlying PDE onto a spectral basis, leading to a finite-dimensional representation of the dynamics which is then integrated with an adapted Neural ODE (NODE). This allows us to overcome spectral bias, by leveraging the high-frequency components enabled by the spectral representation; to enforce causality, by inheriting the causal structure of NODEs, and to start training near the target solution, by means of an initialization scheme based on classical methods. We validate NeuSA on canonical benchmarks for lin- ear and nonlinear wave equations, demonstrating strong performance as compared to other architectures, with faster convergence, improved temporal consistency and superior predictive accuracy. Code and pretrained models are available in https://github.com/arthur-bizzi/neusa.