CEGE4All: Service Management & Performance Seminar

We are pleased to invite you to the next CEGE4ALL: Service Management & Performance Seminar, presented by Ou Tang (Linköping University), entitled “Data analytics of maintenance policies in Product-as-a-Service environment.”

Date: 19 March
Time: 17:00–18:30
Location: Católica Porto Business School – PortoCampus – Room EP004

The seminar will take place in a hybrid format. Participants may attend in person (room EP004) or online.

Register Here

Registration is mandatory. Please register by 18 March, indicating whether you will attend in person or online. The access link will be sent by email to online participants after registration.

Ou Tang is Professor of Production Economics at Linköping University, Sweden. He is Editor of the International Journal of Production Economics and former President of the International Society of Inventory Research (ISIR). His research interests include inventory modelling, production planning and control, closed-loop supply chains, supply chain risk management, sustainable supply chain management, and operations management topics related to China. He has published more than 100 scientific articles, including 60 in international journals, such as the European Journal of Operational Research, the International Journal of Production Economics, and the Production and Operations Management, among others.

Abstract
Original equipment manufacturers are increasingly adopting Product-as-a-Service strategies. In this context, maintenance responsibility must ensure equipment reliability to guarantee efficient operations at customers’ facilities. Since maintenance decisions largely depend on product failure time, which is influenced by usage patterns, differentiating maintenance policies can reduce failures and maintenance costs.
However, this requires methods capable of identifying customer groups within datasets that contain heterogeneous failure information. This study therefore proposes a model and an algorithm to estimate parameters through the analysis of higher-order moments in a mixed Weibull distribution, enabling the identification of underlying customer groups. The advantage of distinguishing these groups becomes evident when no single group clearly dominates, when the failure rate is increasing and high, or when downtime costs are significant. Using real company data, the study identifies products with this potential. Moreover, when the bimodality coefficient is medium or high and the ratio between two scale factors is large, the distribution tends to exhibit two modes, making it essential to distinguish between different customer groups. The proposed model and algorithm allow these conditions to be identified through data and moment analysis. The study’s results provide guidance for improving maintenance performance in Product-as-a-Service environments.