Development of prescriptive AnalYtics baseD on aRtificial intElligence for iAMS

The overall DAYDREAMS objective is to move forward the integration and use of data and artificial/human trustworthy intelligence together with context-driven HMI for prescriptive Intelligent Asset Management Systems (IAMS) in railway by:

1. advancing in maintenance approach towards prescriptive asset management;
2. improving the decision-making process by developing multi-objective decision optimisation approaches taking into account all implications of IAMS decisions in the railway environment; and
3. reinforcing the role of the person-in-the-loop by designing and developing advanced context-driven HMIs to allow context- and risk-aware multiple-options decision-making processes.

The HMI will allow the person-in-the-loop to:

1. properly access and visualise predictions/metrics and models;
2. assess why and how the model predicts something;
3. Steer models by setting parameters; and
4. evaluate alternatives using parameter steering and extending this process through speculative execution.

The DAYDREAMS objective will be assessed by validating the proposed solution using the following two-step approach:

1. A first validation at TRL 4 of the approaches (developed prescriptive asset management) using several internal scenarios and one scenario provided by the CFM IN2SMART2 project;
2. A further validation of the DAYDREAMS methodologies integrated in a TRL 5 prototype using at least two scenarios: at least one internal scenario and the IN2SMART2 scenario. The validation will cover both the performances of the prototypes and its trust for future adoption in multi-actors environments.

The validation will be carried out by defining evaluation and validation metrics and KPIs:

1. linked to asset management problems to be solved by the involved Infrastructure Managers (IMs) and related baselines;
2. quantified and measurable;
3. referred to high-level KPIs defined in the S2R IMPACT2 CFM project; and
4. useful to address multi-objective optimisation.