Maintenance decisions often involve choosing between replacement and repair. The shortage of essential replacement parts has led to increased exploration of repair methodologies. However, repairs are often imperfect, leading to additional uncertainties in predicting the component's future condition. Existing approaches in the literature for modeling imperfect repairs struggle when repair dynamics are unknown requiring a large amount of data to be reliable. Furthermore, current methods are very task-specific, which limits the optimization of maintenance planning of varying components. This research addresses these challenges by conceptualizing imperfect repair effects as a stochastic increase in Remaining Useful Life (RUL). An existing deep learning model extracts prognostic-related features that can be utilized by any prognostic model to estimate RUL based on sensor data. Then, the proposed imperfect repair model predicts the RUL increase post-repair. This method offers three key benefits: (i) proactive post-repair assessment for improved maintenance, (ii) a data-driven repair model compatible with existing prognostic models, and (iii) flexibility in adapting to different repair techniques. Evaluation of the proposed model is conducted through tension-tension fatigue experiments on aerospace-grade aluminium specimens subject to imperfect repair. Results demonstrate the model's ability to accurately estimate the post-repair stochastic RUL increase.

The work presented here focuses on the structural health monitoring (SHM) of a foreign object damage (FOD) composite panel equipped with an innovative printed piezoelectric transducer network. The 3D woven composite FOD panel measures approximately 800 mm × 320 mm, is curved with a cross-sectional thickness varying from approximately 2 mm to 12 mm, and a stainless-steel leading edge is bonded at one of its sides. The core idea explored here is to rely on an innovative screen-printing technology to print a full piezoelectric transducer a flowing to successfully achieve SHM on such a complex composite structure. This work is being carried out within the European project MORPHO - H2020. After printing a 25 elements PZT network, a four points bending fatigue experimental campaign using the PZT network along with other sensor technologies (embedded optical fibres with FBG sensors and acoustic emission sensors) is carried out. This unique experimental campaign allows to generate data and will help to develop diagnostic and prognostic methodologies for remaining life estimation and SHM of the FOD panel. It is demonstrated here through impedance measurements that the printing process associated with the printed PZT transducers is highly repeatable thus validating its use at a larger industrial scale. Furthermore, the printed piezoelectric transducers a re shown to be able to detect foreign object impact and sense Lamb waves signals. This innovative printing technology for PZT transducers network is thus extremely promising. It is furthermore highly advantageous to use the printed transducers for SHM instead of regular ceramic ones as this technology is non-intrusive, add negligible weight, can be printed during the manufacturing process, and arrays of transducers ensure easy availability of another transducer in case of failure of one.