AI-Assisted Condition Monitoring (AIA-CM) based on data-driven optimal signal processing

Position is funded by – COFUND, Marie Skłodowska-Curie Actions (MSCA), Horizon Europe, European Union.

Offer Description

The Australia France Network of Doctoral Excellence (AUFRANDE) is a highly ambitious interdisciplinary doctoral program linking France and Australia, with a strong support from the industry. AUFRANDE seeks to recruit excellent doctoral researchers of any nationality, gender, and background from around the world. AUFRANDE offers the recruited researchers an outstanding experience with excellent working conditions, including full-time employment contract in France with attractive salaries including social security benefits, a unique international research environment, and an innovative research training program in which they will deepen core scientific skills and develop new ones in complementary disciplines and sectors. International mobility is a core feature of the program with a residential year in Australia and participation in regular events where researchers share common experiences and build a sustainable community, laying a strong foundation for long-term impact on future collaborations and careers.

PhD description

Condition monitoring critically relies on signal processing for transforming the raw data (vibration, angular speed, strain, etc.) into interpretable features (scalar indicators, spectra , histogram, etc.). One everlasting challenge is to select the signal processing algorithms among a huge number of candidates, while the best choice is obviously case-dependent. Another challenge is to properly use signal processing algorithms, while they often rely on several critical hyperparameters whose optimal setting is again data dependent. The aim of this research project is to propose a solution to these issues, by making signal processing transparent to the user. It consists in developing a machine learning approach, where each algorithm together with its set of hyperparameters is seen as a probabilistic object in a Bayesian hierarchical framework. The idea is to simultaneously test several candidate algorithms and select the best ones, or a combination of them, according to a given dataset, and to jointly update the values of the hyperparameters that most likely explain the data. The approach will be demonstrated for bid data processing, on open datasets consisting of large numbers of signals recorded on different machines.