Companies are increasingly using data to make decisions, also in the context of maintenance optimization. Data can help answer critical questions: When should maintenance be performed, what maintenance actions should be performed, or when to supply spare parts? However, not all relevant information is covered by the available data. For example, an upcoming period in which machinery will be used more intensively, or an interaction effect with another machine that is getting faulty. Furthermore, a well designed machine doesn’t fail too often, so it takes time before one can base predictions on data coming from this machine, and human knowledge may be required to judge which other machines may experience similar failure behavior. Therefore, in the foreseeable future, human knowledge and human judgement will remain of key importance.
We are collaborating in the project RAMSES with multiple organizations active in the area of maintenance. Our aim is to optimize maintenance planning, through the use of data and human judgement. That means that we want to determine when to involve humans in the decision-making process, and when not, how to integrate the human judgement, and how to present information to human decision-makers in such a way that they can understand the information and add their judgement. There is plenty of opportunity for rigorous, theoretically founded research with actual data from and implementation in practice, thus having impact both in academia and industry. Although we are certainly open to publishing a paper in a top AI conference, our primary outlet are (top) journals in the field of management science and operations research. For an impression of the type of research we perform, please have a look at the following papers:
- Imdahl, C., Hoberg, K., & Schmidt, W. (2021). Targeted automation of order decisions using machine learning. Available at SSRN 3822131. https://doi.org/10.2139/ssrn.4292438.
- Khosrowabadi, N., Hoberg, K., & Imdahl, C. (2022). Evaluating human behaviour in response to AI recommendations for judgemental forecasting. European Journal of Operational Research, 303(3), 1151-1167. https://doi.org/10.1016/j.ejor.2022.03.017.
- Van der Staak, B., Basten, R., van de Calseyde, P., Demerouti, E., & de Kok, T. (2024). Light-touch forecasting: A novel method to combine human judgment with statistical algorithms. International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2024.04.003.
- Akkermans, H., Basten, R., Zhu, Q., & Van Wassenhove, L. (2024). Transition paths for condition‐based maintenance‐driven smart services. Journal of Operations Management, 70(4), 548-567. https://doi.org/10.1002/joom.1295.
Start date: As soon as possible; 1 September 2025 the latest.