Figure - uploaded by Morteza Moradi
Content may be subject to copyright.
The HIs' evaluation metrics for the 1 st and 2 nd level HIs constructed by TIM and TDM, respectively.
Source publication
Composite structures are highly valued for their strength-to-weight ratio, durability, and versatility, making them ideal for a variety of applications, including aerospace, automotive, and infrastructure. However, potential damage scenarios like impact, fatigue, and corrosion can lead to premature failure and pose a threat to safety. This highligh...
Contexts in source publication
Context 1
... evaluation metrics for the constructed HIs are presented in Table 3. Thanks to considering the time-dependency, all the scores for HI (2) are higher than those for HI (1) . ...Citations
... Of imperative importance is the input to these models, which are features capable of correlating to degradation [7,8]. Such features are usually referred to as health indicators (HIs) [9] and are an indirect output of the SHM data [10]. HIs can be directly tied to the damage accumulation displaying a non-linear behavior, as damage progression is usually non-linear. ...
... For the construction of capable HIs, researchers have turned their attention to advanced processing methodologies to create suitable HIs. Principal component analysis (PCA)-based algorithms [17,18,19], genetic programming [20,21], and other machine learning (ML) algorithms [10,22,23,24,25,26] are usually employed for this process. The favorable properties of such HIs make them more appropriate for use in more complex applications, like composite structures. ...
... where t is the running time and t EOL is the EoL operational time of the available training SSPs. Eq. (17) provides a HI in the range [0, 1], which can also be scaled by simply a multiplication in a coefficient [10,24,56]. The normalization via t 2 EOL is necessary to obtain the desired values for prognosability since each unit has a different lifetime. ...
Designing health indicators (HIs) for aerospace composite structures that demonstrate their health comprehensively, including all types of damage that can be adaptively updated, is challenging, especially under complex conditions like impact and compression-fatigue loadings. This paper introduces a new AI-based approach to designing reliable HIs (fulfilling requirements—monotonicity, prognosability, and trendability—referred to as ’Fitness’) for single-stiffener composite panels under fatigue loading using acoustic emission sensors. It incorporates complete ensemble empirical mode decomposition with adaptive noise for feature extraction, semi-supervised base deep learner models made of long short-term memory layers for information fusion, and a semi-supervised paradigm to simulate labels inspired by the physics of progressive damage. In this way, nondifferentiable prognostic criteria are implicitly implemented into the learning process. Ensemble learning, especially using a semi-supervised network built with bidirectional long short-term memory, improves HI quality while reducing deep learning randomness. The Fitness function equation has been modified to provide a more trustworthy foundation for comparison and enhance the practical reliability of the standard in prognostics and health management. Ablation experiments are conducted, including variations in dataset division and leave-one-out cross-validation, confirming the generalizability of the approach.
... The fact that RUL prediction and HI construction models are historical-dependent is a common drawback. It means that to enhance the performance of the HI and RUL prediction models, the temporal relationship between historical data from the starting point until the present moment should be considered [1,13,14]. As a result, prognostic and HI construction models function less efficiently when prior information, either entirely or partially from the beginning, is missing. ...
... In fact, a model is needed to map thousands of data points (as can be seen in experimental campaigns that generated extensive datasets-cite NASA and ReMAP) to a single HI value at the current time, regardless of the prior HIs. To address this challenge, data-driven approaches, especially AI, have drawn attention in diagnostic [27][28][29][30] and prognostic [13,31] applications thanks to their ability to discover complex and nonlinear relationships between data. Nevertheless, several constraints exist to extract proper HIs from GW data: Loss function of regression model 1. ...
... The optimal generator function is represented as a quadratic polynomial: where t is the operating time and t EoL is the time of the final failure. Eq. (10) results a HI in the range [0, 1], which can also be scaled by a multiplication in a coefficient [13,43]. The normalization via t 2 EOL is necessary to obtain the desired values for Pr since each unit has a different lifetime. ...
Developing comprehensive health indicators (HIs) for composite structures encompassing various damage types is challenging due to the stochastic nature of damage accumulation and uncertain events (like impact) during operation. This complexity is amplified when striving for HIs independent of historical data. This paper introduces an AI-driven approach, the Hilbert transform-convolutional neural network under a semi-supervised learning paradigm, to designing reliable HIs (fulfilling requirements, referred to as 'fitness'). It exclusively utilizes current guided wave data, eliminating the need for historical information. Ensemble learning techniques were also used to enhance HI quality while reducing deep learning randomness. The fitness equation is refined for dependable comparisons and practicality. The methodology is validated through investigations on T-single stiffener CFRP panels under compression-fatigue and dogbone CFRP specimens under tension-fatigue loadings, showing high performance of up to 93% and 81%, respectively, in prognostic criteria.
