The fatigue damage caused by multiple-axle configurations is a key issue for pavement design. The standard fatigue test consists of the application of a continuous sinusoidal signal on a specimen, which enables the fatigue life to be described as a function of the strain level. For more complex loading signals, additional parameters were found to have an influence on the fatigue life of bituminous mixtures. In the French design method, the effect of multiple-axle loadings is simplified and taken into account via load equivalency factors using Miner's Law. In this article, we present a method for the computation of the fatigue life of bituminous mixtures under multiple-axle configurations that couples a structural approach and a material-based approach. The structural approach consists of a parametric study of real loading signals that enables the computation of the independent shape parameters characterising a loading signal. An experimental plan whose variables are the independent shape parameters was then defined and the synthetic loading signals constructed (material-based approach). The results of the laboratory fatigue tests enabled the computation of a multi-linear fatigue model that writes the fatigue life as a function of the independent shape parameters characterising the loading signal.

The integration of sustainable materials such as fly ash, blast-furnace slag, recycled aggregates, and seawater into concrete mixes offers significant potential for reducing the environmental impact of construction. However, traditional experimental methods for determining the compressive strength of these concrete mixes are time-consuming and resource-intensive. This study leverages Artificial Neural Networks (ANNs) and Machine Learning (ML) to develop a predictive model for the compressive strength of sustainable concrete, using a dataset of 768 concrete mix samples. Input variables include the concrete age as well as concrete composition, including cement, water, fine and coarse aggregates, seawater, fly ash, blast-furnace slag, and superplasticizer contents, while the output is the compressive strength. The developed model captures the non-linear relationships among these variables to predict compressive strength efficiently. The best ANN model achieved a test loss of 0.051, demonstrating its ability to accurately predict compressive strength and reduce reliance on traditional testing methods. Moreover, the model’s results were compared with those of alternative algorithms to ensure its validity. These findings highlight the potential of machine learning in advancing sustainable construction practices. A relevant future research direction is to analyze feature importance in machine learning models to identify key variables and guide more effective optimization and decision-making, in addition to extending their application to other material properties and advanced concrete mixes.

L'effet des chargements multi-essieux sur la durée de vie en fatigue des enrobés bitumineux est actuellement simplifié et pris en considération par des coefficients d'agressivité. C'est un enjeu important pour le transport écologique: augmenter la charge transportée par poids lourd donne une réduction du taux de gaz toxiques émis par tonne transportée. Pour étudier l'effet des chargements multiples, des signaux de déformation réels sont nécessaires. Le manège de fatigue du LCPC (Nantes, France) permet de mesurer les signaux de déformation dans une chaussée expérimentale. Les paramètres caractéristiques des signaux de déformation ont été déterminés pour cette base de données. Une analyse en composantes principales permet de tirer ceux qui sont indépendants et qui définissent un plan expérimental pour de futurs essais de fatigue de laboratoire ayant pour but de déterminer les effets des paramètres de forme sur la durée de vie en fatigue.

The h index has become a widely known indicator to assess the research impact of academic scholars. However, its application has been associated with some criticism regarding its ability to fully capture the quality and significance of an author's research contributions. In this paper, we present a novel approach to improve the evaluation of authors' publications by means of a Figure-of-Merit (FOM) that includes 5 distinct indicators, of which, an enhanced version of the h index. Named the Enhanced Research Quality Index (ERQI), it addresses the current limitations of existing solutions and offers a more comprehensive evaluation of research quality. The ERQI builds upon the concept that one metric is never sufficient to capture the performance of an academic scholar, while multiple ones are complex to handle and interpret. The proposed ERQI considers the total number of citations, papers and co-authors and can further differentiate researchers with equal h index. By incorporating measurable, and quantitative metrics, ERQI moves away from subjective and indirect factors such as journal reputation, citation context, citation patterns and self-citation righteousness, to offer a more nuanced and accurate representation of research quality. To demonstrate the effectiveness of the proposed metric, we conducted a comparative study using a real dataset of 31 researchers in one of the top 3 engineering faculties in Lebanon, and a randomly generated dataset of 1000 author profiles with >1 million citations. Our findings indicate that ERQI provides a more balanced assessment of research quality by reducing the shortcomings of one indicator. Furthermore, it exhibits a multidimensional effect that captures more efficiently the intrinsic value of scholarly contributions. By adopting ERQI, institutions can make informed decisions that recognize both the quantity and quality of an author's research output and can obtain insightful evaluation enabling fairer recognition of academic scholars' impact and innovation.