The fatigue behaviour of fibre-reinforced polymer composites is typically characterised by costly and time-consuming stress–life testing. This thesis explores an alternative, energy-based approach by adapting complex modulus-based linear viscoelastic theory to describe hysteresis energy dissipation in continuous fibre composites under tensile–tensile fatigue. A modified framework introducing energy-based R–ratio corrections enabled consistent definitions of a viscoelastic loss factor, cyclic dissipation ratios and critical dissipated energy (CDE) across stress levels and load ratios. Analysis of both a literature reference and experimentally tested laminates showed that effective loss factors correlated with Dynamic Mechanical Analysis (DMA) results. The intersection with pristine DMA values provided reliable estimates of high-cycle fatigue strength (HCFS), consistent with existing infrared thermography methods. CDE was identified as a robust fatigue failure criterion, independent of R in the intermediate to high-cycle regime. These findings highlight the potential of energy-based methods to reduce testing requirements while improving predictive capability in composite fatigue.

Composite over-wrapped pressure vessels are the state-of-the-art for hydrogen storage, with Type IV vessels currently using a thermoplastic liner and a thermoset composite. The next innovation, Type V vessels, aims to use a thermoplastic composite over-wrap that acts as both the barrier and container, requiring new materials and manufacturing methods like automated fibre placement.

To accurately characterize the new materials, the effect of their manufacturing process must be captured. While the standard split-disk test exists for wound specimens, it underpredicts their burst strength and fatigue life. Other attempts in literature have improved strength estimations but are not viable in fatigue, thus creating a challenge.

A new test method was developed, which uses a polyurethane ring to apply cyclic internal pressure. It was designed through finite-element analyses, fine-tuned through rigorous tests, and benchmarked against the standard method. It showed improved strain distribution and near-consistent performance in fatigue tests. Hence, it demonstrated potential for more accurate static and fatigue strength characterization of wound composites, with room for improvement through better alignment and even friction.

In this work, a conceptual design was created that integrates battery packs into the wings of a 90-seater electric aircraft. This was done under the challenging requirement of replacing over 35 tonnes of batteries more than once a year. The concept allows the batteries to move spanwise along a rail system and through the rib using a panel structure. The core of this concept is that it avoids the need to remove large skin panels of the wing. From the broader concept, a single component was analyzed in detail using non-linear finite-element models combined with fretting-fatigue analyses and physical testing.

This dissertation introduces a comprehensive end-to-end framework related to Prognostics and Health Management (PHM) strategy, with the goal of utilizing raw sensor (placed on a structure's components) data to make maintenance decisions for extending the structure's lifecycle. The study addresses key challenges in PHM, such as dealing with high-dimensional, multi-modal data, extracting features, predicting Remaining Useful Life (RUL), managing uncertainty, modeling repair scenarios, and optimizing maintenance decisions. All these challenges are organized in phases. These phases are namely, i) data collection, ii) feature extraction, iii) Health Indicator (HI) construction, iv) prognostics, v) modeling of maintenance actions, and vi) Post-Prognosis Decision-Making (PPDM). Each phase of the PHM strategy is developed independently but integrated into a cohesive framework, ensuring modularity, transparency, and adaptability across diverse applications.

A major contribution to the framework is proving that neural networks, a preferable approach for handling complex data, can become interpretable, thus unveiling the black-box nature of such models. In this regard, the ISTRUST model, an interpretable Transformer-based architecture for predicting RUL directly from raw sequential image data of a structure under fatigue loads, is proposed. By leveraging attention mechanisms, the model captures critical spatiotemporal features of structural damage, offering insights into prediction accuracy and variability. The model's interpretability highlights the understanding of its predictions. Simultaneously, via this interpretation, it is shown that predicting RUL directly from high-dimensional raw data is challenging or even impossible, necessitating focusing on each phase of the PHM strategy separately instead of unifying the majority of the PHM strategy in one model.

Central to the framework is the development of the Deep Soft Monotonic Clustering (DSMC) model, designed to extract meaningful features and then construct HIs from multi-modal data. This model extracts monotonic features that are related to each component's degradation. Subsequently, it considers these features to perform monotonic clustering representing HIs and enables the integration of those HIs into prognostic models to predict RUL across diverse domains.

The dissertation further explores the impact of imperfect repairs on components, where repairs often leave the component in a state between fully restored and partially damaged. The health state of the component is measured via a stochastic recovery of the predicted RUL and a Bayesian inference-based model is employed to quantify this stochastic behavior. The imperfect repair (Bayesian) model can be also extended for multiple sequential repairs. This phase of the PHM strategy emphasizes the importance of understanding imperfect repair effectiveness to enhance maintenance strategies.

The final phase of the framework concerns PPDM. Given a set of maintenance actions, including replacements and imperfect repairs, and a set of operational conditions and constraints, PPDM is modeled as a Markov Decision Process and optimized via deep Reinforcement Learning. PPDM's ultimate target is to optimize the scheduling of maintenance actions proactively within a predefined horizon length.

Experimental validation is conducted on each of the proposed models. The ISTRUST model was validated on fatigue-loaded composite specimens, utilizing sequential raw image data taken by a camera. The DSMC model was tested using diverse datasets, including engineering and healthcare. The imperfect repair modeling was applied to tension-tension fatigue experiments on open-hole aluminum coupons, capturing stochastic recovery behavior after repairs. The same experiment was utilized for evaluating the PPDM framework.

Overall, a holistic end-to-end PHM framework lays the groundwork for advancing Condition-based Maintenance (CBM) strategies. By integrating advanced models for each phase of the PHM strategy, the research highlights practical opportunities for embedding PHM into CBM and encourages further innovation and refinement by other researchers in the field. Although the proposed PHM framework has been an initial attempt towards this direction, its capabilities can be further enhanced through improvements in data scalability, exploration of varied PPDM formulations, sensitivity analyses across PHM phases, and practical integration with CBM for broader system-level maintenance optimization.

Mission Aviation Fellowship (MAF) provides humanitarian aid using light aircraft to remote communities, separated by geographical obstacles or conflict. HumanAir aims to reduce their operating emissions by 50% while improving economic sustainability and maintaining operational versatility, by designing an innovative new aircraft within a timeframe of only 5 years. This report describes the design process and analysis of the HA-1 aircraft, the proposed solution to the problems encountered by MAF. The HA-1 aircraft achieves an emissions reduction of more than 50% while remaining competitive on cost, facilitated by the use of readily available Jet-A1 fuel instead of scarce leaded AVGAS. Therefore, the HA-1 will replace multiple of MAF’s ageing aircraft with a single sustainable alternative.

Fibre-reinforced polymer (FRP) composites have become indispensable in aerospace engineering over the past two decades, driving the need for efficient and standardized testing protocols to certify their reliability. However, no standardized protocol currently exists for fatigue testing of FRPs, particularly due to fibre bridging—a phenomenon prominent in testing but rarely encountered in real-world applications. This study investigates existing fatigue data processing techniques, with a primary focus on a regression-based approach that could standardize fatigue data analysis. Current fatigue delamination characterization methods often rely on single-parameter empirical models, which struggle to capture the complex interaction between cyclic and monotonic load components, expressed as ∆√G and Gmax, respectively. This study demonstrates that the regression method’s zero-bridging technique effectively incorporates both parameters, offering a comprehensive view of delamination growth by isolating it from fibre bridging effects. This approach suggests a shift away from the traditional 2D analysis to a 3D framework, which considers both Gmax and ∆√G, enabling a more accurate depiction of delamination behaviour across various stress ratios. Notably, the results reveal that zero-bridging data align on a common plane under consistent stress ratios, shifting as stress ratios increase. Additionally, fibre orientation influences data clustering, with similar orientations exhibiting stronger convergence than dissimilar ones. Comparison of this regression-based method with the modified Paris law reveals significant discrepancies in its current implementation, suggesting alternative approaches to address these limitations. This study also highlights the impact of data size and selection on the model behaviour, stressing their importance in accurate model representation. This research validates the regression method as a promising candidate for standardizing fatigue data processing, improving the precision and reliability of post-test analysis for fibre-reinforced polymer composites.

Additive Manufacturing (AM) has revolutionized the production of complex parts, particularly for superalloys in the aerospace industry due to their strength, corrosion resistance, and high-temperature performance. LPBF is notable for its precise control over complex geometries, with key parameters like laser power and scanning speed affecting the final product's quality. This study examines how build orientation, high stress ratios, and surface roughness impact the fatigue life of superalloy. Vertical and diagonal specimens were printed with identical heat treatments to isolate these variables. The diagonal specimens showed higher UTS but lower ductility compared to the vertical ones. Fatigue tests revealed that increased surface roughness in diagonal specimens reduced HCF performance, while their strength improved LCF behavior. Crack initiation was primarily at the surface in HCF, while internal defects caused some LCF failures. The proposed fatigue models aligned well with experimental data, offering valuable insights for future research.

Fibre metal laminates (FML) were initially conceived as a hybrid material, aiming to create synergy between the impact resistance of metals and excellent fatigue resistance of fibre reinforced polymers. The purpose of this approach was to overcome the limitations of single-material structures. However, despite its considerable promise, the use of the FML concept has primarily been confined to aerospace applications and heavily relies on synthetic fibres that carry significant environmental implications. Hence, given the growing concerns about climate change and the challenges posed by recycling glass fibre composites, a new generation of FMLs with a reduced carbon footprint should be envisaged.

Research on flax fibre composites reveals convincing mechanical properties and remarkable damping capacities. However, the broader adoption of these composites remains restricted primarily due to issues related to low impact resistance, moisture absorption and flammability concerns. The FML concept presents a viable solution to surmount these constraints, consequently facilitating the integration of these materials into primary structures. Hence, the research endeavour aimed to attain comprehensive insights into FLAx REinforced aluminium (FLARE), particularly focusing on its impact resistance and vibration damping capabilities, which are believed to be the principal benefits of this hybrid material.

The research goal was divided into three distinct research tasks: conducting experimental analyses to characterise the damping behaviour of FLARE, evaluating the impact resistance through experimental means, and validating predictive tools to offer initial insights into the design principles governing such a FML. FLARE, along with flax fibre reinforced epoxy (FFRE) and GLARE specimens, were manufactured using wet layup combined with vacuum bagging techniques.

First, tensile tests were conducted to validate the applicability of the metal volume fraction (MVF) approach in predicting the mechanical properties of FLARE. Intriguingly, the well-known non-linear behaviour exhibited by flax was not observed in the case of FLARE. The results revealed that while the MVF method provided a satisfactory approximation, it was the "inelastic" modulus of FFRE that predominantly contributed to the stiffness of FLARE.

Dynamic mechanical analysis and vibration beam tests were carried out to assess the influence of incorporating metallic layers on the vibration damping characteristics of flax fibre composites. The investigation revealed that the metallic layer predominantly governs the damping behaviour of the FML. Notably, an inverse rule of mixture emerged as the most effective means of approximating its loss factor.

Low-velocity impact tests were conducted to gain insights into the impact response of FLARE in comparison to conventional FMLs. The analysis indicated that the aluminium layers play a significant role in energy absorption, whereas the composite strength emerges as the critical factor influencing impact resistance. A quasi-static analytical model was also assessed, offering an initial estimation of the impact response, yet it warrants further refinement.

In conclusion, the FML concept holds promise for FLARE, but its application requires a novel approach compared to previous methods, to render FLARE viable for practical real-world applications.

In recent years, the wind energy industry shows more and more interest in composite materials manufactured with a new process called pultrusion. The advantage of pultruded composite plates includes high fiber volume fraction, low price and simplified blade manufacturing. However, pultruded plates are fully cured and crosslinking is absent at interlaminar interface, which may lead to potential risks when being applied into the real structure. This project focuses on characterizing and evaluating this new type of material.

Microscopy and burn-off test were carried out to measure the actual fiber volume fraction in the material. Roughness of interlaminar surface was measured with microscope by focus variation. These parameters are essential to understand the material.

To characterize the mechanical behaviour of the material, multiple different types of mechanical tests were carried out. Mode-I and mode-II interlaminar fracture toughness were tested with Double Cantilever Beam(DCB) and End-Notched Flexure(ENF) specimens. A new test procedure was developed to measure the mode-I interlaminar fatigue toughness of the material. For in-plane tensile and compression test, Finite Elements Methods(FEM) was used to optimize the specimen geometry in order to obtain results closest to actual material behaviour. During the tensile test, acoustic emission was measured to monitor the damage in the specimens in these tests. Fatigue tests with stress ratio R=0.1 and R=-1 were carried out to understand the fatigue behaviour of the material.

This study evaluates the potential danger of hail impacts on stiffened composite aircraft structures. Test specimen are created using Carbon Fiber Reinforced Polymer (CFRP) with and without an Aluminium longitudinal stringer. These specimen are first indented to explore the effect and behaviour of stiffening elements and varying boundary conditions. Then an impact gun is used to impact the specimen with ice balls, simulating hail impacts in order to assess the potential danger of hail stones impacting the stiffened structure. It is concluded that the critical locations for damage formation are where deformations are most suppressed, such as the stringers and ribs of the aircraft. In these locations more damage at the same energy levels as well as a lower threshold energy level for damage initiation is observed. Additionally, it is shown that repeated impacts in close proximity of each other, such as during hailstorms, can increase the resulting damage compared to separate single impacts. Ice impacts demonstrate only a fraction of the kinetic energy is absorbed during an impact, but large hailstones occurring during rare hailstorms can definitely cause serious damage in the critical locations in aircraft. So, for future research, testing and certifying the potential of hail impacts must be recognised and determined in the critical stiffened locations within an aircraft

Fibre Metal Laminates (FMLs) have been widely utilised in aircraft structures for their specific strength, durability and damage tolerance. Most aircraft structures, due to their size, require joining, and FMLs allow for a special type of joint called the splice, a unique but a lesser known joint.

The bulk of research into the splice joint has been conducted in the early 2000s for the A380 program, where a specific type of splice has been implemented, the overlap splice. While it is a proven design, it was expected that other splice designs could be as good if not better than the overlap splice. Further, the pre-existing design guidelines on the splices were not suited for detailed design that would target specific mechanical strengths of the joint, like durability and
damage tolerance. Therefore, this research focused on design iterations of the two splice types, the butt splice and the overlap splice, that would provide insights into splice design guidelines against fatigue and demonstrate which splice configuration is a superior joint. An extension
of this research focuses on identification of location and lifetime to damage initiation within the splice using analytical numerical methods, which was previously done on uninterrupted FMLs, but not on spliced FMLs.

Research comprises of a multi-disciplinary approach, combining Finite Element Method (FEM), numerical predictive modelling and experimental investigations that then also doubled as means of validation of the models built. Design iterations were based on the influence that the parameters, labeled a through e, within the splice joint have on the overall stress field within the joint and how that affects the joint’s fatigue life to damage initiation, Ni, a fatigue
performance indicator of the study. It has been discovered that changing the tolerances within the splices provides little influence on the stress field within the splice, which resulted in several iterations of the splice design approaching smaller and more lightweight joint alterations. The designs showed excellent durability characteristics when compared to the Limit of Validity (LOV) cycles set by the aviation authorities, such as EASA and FAA. The Finite Element (FE) model was able to accurately depict the stress field within the splice, validated by the experimental data through strain fields captured using Digital Image Correlation (DIC) technique, and consequently accurately pointed to the location of damage initiation, which in all cases was the outer-most overlap on the flush side of the joint. Along with the adapted predictive numerical model it was possible to predict the damage initiation lives in the spliced specimens with a blunt notch. The predictions in the samples without the notch resulted in far lesser agreement with experiments. This was likely caused by to the limitations of the model, which only took into account quasi-static loading without damage and is highly dependent on the reference data used.

It was concluded that splices can be designed smaller and lighter than previously done due to the tighter tolerances allowed within the splice. Overlaps of 5 mm in both the unnotched butt splice and the unnotched overlap splice, however, resulted in an alternative damage progression mode, specifically a complete delamination of the external overlap rather than metal fatigue cracking. This is attributed to the rising average shear stress in the adhesive. Regardless, the smallest and lightest iterations of the butt splice and the overlap splice with
5 mm overlaps and gaps between aluminium interruptions showed excellent durability and the design iterations were found to affect the damage initiation life very little, considering that fatigue damage initiation is a subject to scatter. It is hard to draw a concrete conclusion on the damage tolerance of the updated designs due to alternative damage modes and lack of research thereof. While both splice types were deemed to be successful in their role of a joining structure, the butt splice was concluded to be superior to the overlap splice when it came to fatigue performance, consistently developing visible damage later than the overlap splice. This gap in fatigue performance is expected to expand if thicker layers or larger number of layers are to be considered. This is because of the secondary bending which occurred in the joint, more so for the overlap splice than the butt splice judging from FEA results and experiments.

It is recommended that a more extensive FE model is developed using the model built in this research as a foundation. The current model could be expanded in several ways, such as simulations of damage progression, individual modelling of the fibre layers, fibre failure models, and a curing simulation. This will improve the validity of the methodology, specifically concerning the unnotched splice specimens, and improve the predictions of not only initiation lives, but also failure lives.

Fiber Metal Laminates needs to be seen as a construct of its individual constituents rather than a material on which the industry has capitalized on. Therefore, analytical models must be made in order to predict the mechanical behavior of the laminates which would reduce the big test matrix for defining empirical values for design allowables. An analytical model made to predict the mid-section stress distribution of Fiber Metal Laminate plate with a centre round hole under uni-axial tension. The σ 0 ε-curve of the laminate is defined by the Metal Volume Fraction. Assuming that the elasto-plastic energy of a small strip is equal to the uni-axial imaginary elastic energy, the σ 0 ε-state of these small strips can be calculated. The elastic peak stress profile at the midsection is defined by a decreasing exponential equation with three parameters. The centre of the small strips are the points where the value of interest are determined. Predicting the net-section stress distribution under elasto-plastic loading is determined iteratively by using the Finite Width Correction Factor as a convergence factor between the applied and net-section load. The analytical model gives quite good and accurate results far into the plastic regime validated by DIC experiments and strain gauges. One of the major findings was that indeed it is possible to have delamination and fiber-bridging beneath the plastic zone, which had implications for determining accurately the Blunt Notch Strength.

Composite materials have multiple failure modes. Most of these failure modes are dedicated to the different layers, e.g., delamination. Unfortunately, these damages can occur internally, causing it to be invisible to the naked eye. A better understanding of how this happens and what causes it, is required to ensure safety. Therefore, for this research, delamination is the most interesting failure mode. Previous researches have primarily been focusing on quasi-statically loaded UD specimen. However, since a layup in a structural part of an aircraft consists of multiple layers with different fibre orientations, it is not guaranteed that a delamination will occur between two 0º plies. Furthermore, an aircraft is designed to be in service for decades and consequently is loaded thousands of times. A structure which is subjected to a cyclic loading will behave differently than one to a quasi-static loading. Hence, in aviation industries, tests with cyclically loaded specimens are more relevant. This research project focused on fatigue delamination crack growth of multi-directional interfaces. In order to generate mode I delamination, DCB specimens were manufactured and tested. Fatigue experiments were conducted to see the influence of the interface angle as well as that of the orientation of the interface angle. To cover most relevant delamination planes, tests with the following interface were conducted: 0º//0º, 45º//45º, 90º//90º, 0º//45º, 0º//90º, 45º//−45º and 30º//−60º. Furthermore, the crack fronts were monitored by means of C-scans and the fracture surfaces were examined. It was found that for all different interface orientations, fibres bridged. This was demonstrated with an increased delamination resistance for a longer crack. The nature of these bridging fibres, however, differed. Fibre bridging regarding to nesting showed a less significant increase in fracture resistance than bridging fibres due to oscillatory crack propagation behaviour. Furthermore, the different interfaces showed various crack fronts. The crack front tends to propagate towards the direction of the fibres of either of the fibre orientations around the interface.

This report describes the research I have done during my master thesis on the subject of the effect of temperature on fatigue delamination growth. It is the result of a thourough literature study and an extensive experimental campaign under supervision of René Alderliesten and Liaojun Yao. This report informs the reader about the process I have followed as well as the results I have obtained. This master thesis report would not have been possible without the support of several people. Firstly, the technicians of Delft Aerospace Structures and Materials Laboratory Fred Bosch, Victor Horbowiec, Johan Boender, Berthil Grashof, Dave Ruijtenbeek and Alexander Uithol. Thank you to Dimitrios Zarouchas for his help with the acoustic emission equipment. Special thanks go out to Roberto Motta for his advice and support on both practical and theoretical matters. Thank you to my second supervisor Liaojun Yao for the fruitful discussions and feedback I have received during my master thesis. Finally, my deepest gratitude goes out to my first supervisor René Alderliesten for his help, guidance, discussions and feedback.

The current generation of commercial aircrafts extensively use composite materials such as Carbon Fibre Reinforced Polymers (CFRP) in both exposed and primary structures. These materials lack through-thickness reinforcement and are hence susceptible to out-of-plane impact damages. Barely visible impact damage caused by low energy impacts poses a unique problem, since delaminations, de-bonding and cracking may be present below the surface layers without any indication of damage on the surface. The focus of this research is on one such scenario, multiple site low energy hail impacts, while the aircraft is on the ground. Taking into account the relevant parameters, a hail impact envelope was established both in terms of the initial kinetic energy and peak impact force. Further, contradictions found in literature over the influence of the compressive strength of hailstones were resolved. These were accomplished with the aid of a state-of-the-art finite element model and experiments in the laboratory. With help from a custom designed and assembled impact force measurement experimental setup a relation was established between impacts carried out with steel impactors and those with simulated hail ice impactors. Based on this relation, predictions are made on which hailstones have the potential to cause damages to CFRP structures.

With a growing demand for longer blades in the wind turbine industry for higher rated power per turbine, a structurally sound blade-root connection is of commercial importance. Bushing connections have been a commercially favoured design in the past few years, replacing the commonly used T-bolt connection as the joining method of choice. The new design replaces the barrel nut in the T-bolt with an axial bushing that the bolt connects to and can be assembled with the laminate during the lay-up stage of the blade skin. It has been theorised that it can result in a reliable connection due to the elimination of laminate stress concentrations. However, literature outlining the performance of a blade-root connection with bushings is lacking in the current body of knowledge. While several patents for bushing designs exist, they don’t provide verifiable results on their efficacy due to trademark laws. The objective of this project is to design and conduct a numerical study of a blade-root connection with bushings with an aim to replace the T-bolt connection, along with providing evidence of the effect of various parameters on the structural performance of the blade root. The design is to be based on a Suzlon Energy-make blade with a pitch circle diameter of 3m and a blade length of 63m. The project has been planned in three phases: (1) Design of the root; (2) Validation of the design; (3) Comparative analysis. Modelling and FE analysis has been carried out in the ANSYS environment. Parameters of the bolted connection have been determined according to industry standards provided by VDI and GL. Design validation was conducted based on structural constraints; the key design constraint relevant to the blade-root as a sub-component of the wind turbine is the accumulated fatigue damage. For the final phase of the study, various parameters associated with the assembled root were identified and tested in iterations and their effect on the structural performance, weight, and cost of the assembly were studied. The results confirm the hypothesis of reduction of stress concentrations within the laminate; this eliminates several failure modes associated with composite laminates at the blade root. As is, the bushing connection can be considered a viable alternative to the T-bolt joint. Within the connection, higher absolute stresses and stress gradients were developed in the bolt joining the blade to the hub. Hence, this was the area of focus for fatigue damage evaluations. Conservative estimates of the accumulated damage show values well within the acceptable range. The connection has been designed keeping several concurrent variables in mind. Given the commercial applicability of the design, a rigid optmized design is not feasible due to unpredictable parameters like certification costs, total assembly times, and procurement costs. Therefore, an effort has been made to understand the effect of varying component parameters. The design lends itself to flexibility of dimensioning and material choice within the sub-components; parameters can be optimised according to cost, manufacturability, and performance requirements. While the base design configuration for the bushing connection is heavier than the T-bolt design, improved fatigue performance can be seen as a favourable trade-off.

This report was written as part of the Design Synthesis Exercise, a 10 week project in which groups of 10 members create a design to obtain their bachelor’s degree at the Faculty of Aerospace Engineering. AirEco’s task is to design and develop a revolutionary and sustainable solution for the future of longrange commercial aviation.
This report deals with the final design, in which a longrange commercial (150250 passengers) aircraft with a propulsion system based on renewable energy principles is proposed...

The goal of this dissertation was to integrate the models developed by the Intelligent Maintenance Systems (IMS) group of ETH Zürich, with a dataset typical to the Structural Integrity and Composites (SI&C) group of the TU Delft. To achieve this objective, the open source Guided wave dataset from the NASA Prognostics Center of Excellence repository was selected.Three objectives have been studied:Integrated feature extraction. Here the goal was to use artificial intelligence (AI) to automatically extract features from raw audio signals.Predictive modelling. The goal was to use heterogeneous modelling to predict the remaining useful lifetime and the delamination growth in carbon fibre reinforced polymers (CFRP's).Domain adaptation. Here, the objective was to converge delamination predictions of one boundary condition such that a model could make predictions for a second boundary condition. The approach is novel to the SHM datasets used by the SI&C group and is first introduced in this dissertation.