Tiedo Tinga

This paper presents the Physics-Informed Impact Identification (Phy-ID) framework. It addresses the challenges of reconstructing impact parameters from passive sensor signals. Phy-ID integrates physical knowledge into machine learning across three complementary levels: how data representation is defined, how the model is built, and how optimisation is guided. Each level is described conceptually and illustrated with documented examples from previous work of the authors and the literature. Examples cover both established strategies and new directions yet to be applied to impact identification. By aligning model design with prior knowledge of composite structures under impact, Phy-ID provides a structured, scalable modelling approach. It targets improved robustness, interpretability, and generalisation in conditions of partial physical knowledge and limited experimental data, which are typical in real-world SHM.

One of the challenges apparent in the organisation of research projects is the uncertainties around the subject of demonstrators. A precise and detailed elicitation of the coverage for project demonstrators is often an afterthought and not sufficiently detailed during proposal writing. This practice leads to continuous confusion and a mismatch between targeted and achievable demonstration of results, hindering progress. The reliance on the Technology Readiness Level (TRL) scale as a loose descriptor does not help either. We propose a demonstrator requirements elaboration framework aiming to evaluate the feasibility of targeted demonstrations, making realistic adjustments, and assist in describing requirements. In doing so, we define five hierarchical levels of demonstration, clearly connected to expectations, e.g., work package interaction, and also connected to the project’s industrial use-cases. The considered application scope in this paper is the domain of software-intensive systems and industrial cyber-physical systems. A complete validation is not accessible, as it would require application of our framework at the start of a project and observing the results at the end, taking 4–5 years. Nonetheless, we have applied it to two research projects from our portfolio, one in the early stages and another in the final stages, revealing its effectiveness.

Energy estimation is critical to impact identification on aerospace composites, where low-velocity impacts can induce internal damage that is undetectable at the surface. Current methodologies for energy prediction are often constrained by data sparsity, signal noise, complex feature interdependencies, non-linear dynamics, massive design spaces, and the ill-posed nature of the inverse problem. This study introduces a physics-informed framework that embeds domain knowledge into machine learning through a dedicated input space. The approach combines observational biases, which guide the design of physics-motivated features, with targeted feature selection to retain only the most informative indicators. Features are extracted from time, frequency, and time-frequency domains to capture complementary aspects of the structural response. A structured feature selection process integrating statistical significance, correlation filtering, dimensionality reduction, and noise robustness ensures physical relevance and interpretability. Exploratory data analysis further reveals domain-specific trends, yielding a reduced feature set that captures essential dynamic phenomena such as amplitude scaling, spectral redistribution, and transient signal behaviour. Together, these steps produce a compact set of energy-sensitive indicators with both statistical robustness and physical significance, resulting in impact energy predictions that remain interpretable and traceable to measurable structural responses. Using this optimised input space, a fully-connected neural network is trained and validated with experimental data from multiple impact scenarios, including pristine and damaged states. The resulting model demonstrates significantly improved impact energy prediction accuracy, reducing errors by a factor of three compared to conventional time-series techniques and purely data-driven models.

Aerospace composite components require effective monitoring techniques to detect possible internal damage from impact events. To ensure reliable impact identification, sensor measurements can provide valuable information about impact energy and identify potential issues that may require further investigation. However, selecting the most appropriate sensor technology to measure impact force and energy is a challenge. In this article, a systematic and structured approach is presented to compare the expected performance of sensors and their metrological parameters in terms of their ability for impact identification in aerospace composites. The proposed methodology is demonstrated using an application example where fibre Bragg grating (FBG) are compared with piezoelectric (PZT) sensors through comprehensive tests. These tests include the correlation test, the sensitivity test, and the factor test. The correlation test showed a high agreement between FBG and PZT sensors in the time and frequency domain. The sensitivity test indicated a significant correlation between the signal features and the impact energy levels in the energy profiling diagrams, revealing nonlinearities and energy losses indicative of damage. Furthermore, these results emphasise the superior resolution of the FBG sensors and the comparable repeatability of the two sensor types. Finally, the factor test showed that FBG sensors are sensitive to different angles of incidence, while PZT sensors have a more stable directivity. Further analysis also showed that the signal strength of both sensor types decreases with increasing distance from the impact source. Overall, the proposed approach enables a thorough evaluation of the capabilities and limitations of both sensor types. Consequently, it provides information to make an informed decision on the most suitable sensor for impact monitoring systems.