Prognostics aims to predict the Remaining Useful Life (RUL) of engineering assets and is essential for effective Predictive Maintenance (PdM). Unlike preventive maintenance, PdM offers substantial cost benefits by scheduling maintenance only when needed. However, most existing prognostic models assume that repairs return an asset to an “as-good-as-new” condition. In practice, repairs are often imperfect, as they only partly restore the asset and may change its subsequent degradation behavior. This mismatch represents a major limitation of current prognostic approaches, as poor prognostic performance can lead to unnecessary maintenance actions or unexpected failure.

This paper proposes a fully Bayesian prognostic model, named the Sequential Bayesian Semi-Markov Framework (SBSM), that explicitly accounts for imperfect repair while being trained exclusively on data from non-repaired assets. The framework combines a Hidden Semi-Markov Model (HSMM) to represent the degradation model with a particle filter for the predictive step. Repair actions are incorporated as prior distributions that represent repair effectiveness, enabling repair uncertainty and prognostic uncertainty to be treated in a unified manner. This formulation allows post-repair degradation trajectories to differ from pre-repair behavior without retraining the model.

The approach is experimentally validated using an in-house dataset of aluminum open-hole specimens subjected to constant-amplitude fatigue loading, repaired via cold spray deposition, and tested to failure. Baseline (non-repaired) specimens are used for training, while repaired specimens are used exclusively for testing. The proposed method is compared against a Convolutional Neural Network (CNN) baseline. Results show that the SBSM achieves lower prediction error and improved probabilistic calibration, particularly under significant distributional shifts induced by more effective repairs. The framework demonstrates robust post-repair RUL prediction and well-calibrated uncertainty estimates, highlighting its potential for real-world predictive maintenance applications involving imperfect repair. ... Read more

Cold spray is well-known to be an attractive method for aerospace repair based on its solid-state deposition nature, demonstrating significant benefits compared to its conventional thermal spray counterparts. However, usage of cold spray for repair within an aviation context is currently limited to geometric restoration for minor damage, including nicks, dents, scratches, and minor corrosion, and will remain limited until the durability and damage tolerance of such repairs can be reliably demonstrated.

Current limitations in this regard surround the manufacturing-dependence of the produced depositions combined with lack of process standardization. In service, the quality of thermal spray coatings are typically evaluated using metrics such as adhesion strength, porosity, and hardness, and these parameters are therefore also often suggested for quality assurance of cold spray deposits. However, it is not clear if these metrics are also suitable and sufficient for assuring the quality of structural repairs.

The present work concerns assessment of the quality of cold spray repairs subjected to high cycle fatigue loading. Fatigue test results for Al6061 cold spray blend-out repair coupons on a like substrate manufactured using different process parameters and surface preparation methods are presented, with an emphasis on variability of, and interactions between, damage modes in fatigue. A comparison between quality metrics used for thermal spray coatings and cold spray fatigue performance are presented.

Acknowledgement: The work presented was supported by the Dutch Research Council Open Technology Programme ‘CSAR’ (grant no: 20434). ... Read more