![[The graphic presents 5 logos, in 3 rows. In the top row there is a logo of the XPM Project, which is an eyeball surrounded by a black-green spiral. Second and third rows present logotypes of the project funders. In the second row there are logos of French Agence Nationale de la Recherche and Portugese Fundação para a Ciência e a Tecnologia. The lowest row contains logos of Polish Narodowe Centrum Nauki and Swedish Vetenskapsrådet.]](https://portal.uj.edu.pl/documents/150784654/0/GIMP+logotypy.png/c8059dc6-2548-4d50-b9ba-dc9ee42449a2?t=1659012066842)
Nawigacja okruszkowa
Widok zawartości stron
Widok zawartości stron
Widok zawartości stron
XPM Project Structure
Below you can find general information about the project structure. The workplan included 7 work packages, further partitioned into tasks, briefly described on the sites listed on the left.
Consortium
- HU-Halmstad University, Sweden, PI: Slawomir Nowaczyk, Founder: VR
- IT-Inesc Tec, Portugal, PI: João Gama, Founder: FCT
- JU-Jagiellonian University, Poland, PI: Grzegorz J. Nalepa, Founder: NCN
- IMTLD-France IMT Lille-Douai, PI: Moamar Sayed-Mouchaweh, Founder: ANR
Dependencies
The project consists of 7 working packages (further called WPs), starting with WP0, ending with WP6. WP0 (Management) and WP6 (Dissemination) have organizational character and do not contain scientific tasks. WP1 is responsible for coordination of actions within other WPs and WP2 focuses on publishing the results of the research. WPs 1-5 conduct scientiific tasks and are interdependent, exchanging results between each other. The bulk of research is done within WP1 (Explainability layer for black-box PM), WP2 (Inherently explainable PM methods) and WP3 (Decision support for maintenance plans). Results achieved in WP1 and WP2 support the research conducted in the WP3. Effects of work in WP3 are then used during the research of WP4 (Evaluation Methods). Research done in WP4 helps to advance the work in all other research packages. It direclty supports WP1, WP2 and WP5 (Case StudieS), and indirectly supports WP3. The WP5 also bases on the research done by WP1-WP3. Case analysis done in WP5 helps to further develop evaluation methods established within WP4. ( The dependencies between the WPs in the project are also presented on the below graph. For the more specific information about each of the WPs, please click the menu on the left.
Widok zawartości stron
Working Packages Descriptions
The Management WP aims to ensure the proper execution of the project, early detection of any deviations and efficient way of finding solutions to issues discovered.
In this work package, we will develop an explainability layer for black-box models that include different aspects of prediction and self-adaptive modelling (SO1a). We will identify the proper context of explanations in PM in order to effectively interact with different actors from system operators to management staff. The outputs of this WP are, for each alarm, the location of the failure and root cause analysis, the severity and RUL, and expected impact on component performance.
In this work package, we will propose new methods for PM that are developed with explainability in mind and produce glass models (SO1b), by continuously involving domain experts during the model building process. We will use frequent feedback on interpretability and demonstrate how transparent and understandable models can be linked with the underlying data from the industrial monitoring systems. Through the top-down perspective, from domain knowledge to the data (as opposed to WP1 which follows the bottom-up approach), we will introduce the expert knowledge into the PM modelling process itself to better understand and explain industrial data. The outputs match WP1: failure location and root cause analysis (R1), severity and RUL (R2) and impact on component performance (R3).
This work package aims at understanding the physics of degradation (e.g., wear, cracks, clogging, corrosion) with respect to failure modes, their propagation mechanisms and the variables (e.g., operational, environmental, load) that are involved in the phenomena. By identifying key features and influencing factors on the critical components and the dynamic evolution of their degradation (R2), we develop an interactive decision support tool and HMI for prescriptive maintenance advice. It uses explanations supplied by models from WP1 and WP2 to present the degradation characteristics and explain their impacts on the selected performance criteria in the correct context (R3). Thus, it helps operators to understand the situation, create a suitable repair and maintenance plan (R4).
As explainability is always domain, context and task-dependent, it is challenging to measure on a general level. Therefore, in this WP, we will formulate a range of evaluation methods for explanations relevant for XPM (SO2a). Based on them, we will be able to assess the usefulness of explanations in the specific cases, as well as their contribution to the decision-making process in a broad sense.
In each case study, the effort will be shared between the leading partner and an additional partner. The four case studies will provide the necessary testbed diversity to assess the generality of results in the light of XPM objectives, as well as valuable feedback. This WP will also bring to XPM sector-wise domain knowledge that is fundamental to many future applications of XPM. We will use these scenarios to demonstrate the contributions of the project. THese will include: steel factory (JU), Electric heavy-duty vehicles (HU), Wind farms (IMTLD), Metro Porto (IT-Inesc Tec).
The goal of this package is to raise awareness about the XPM project and to boost interest in it in the related scientific communities and among different actors, including industry stakeholders. Furthermore, the objective is to disseminate knowledge to research and development teams beyond the project consortium.